AI Models Comparison
Compare AI model pricing and benchmarks across providers including OpenAI, Anthropic, Google, AWS Bedrock, Azure, Mistral, and more. Filter by model capabilities like vision, function calling, and reasoning support. Find the most cost-effective model for your use case. Currently tracking 1,771 models across 99 providers.
The data is based on LiteLLM, maintained by the open-source community, and benchmark data from Artificial Analysis. The latest update occurred on February 27, 2026 at 12:00 AM UTC
Model | Provider | Input Price, $ | Output Price, $ | Price Compare | Context | Max Output | Intelligence | Coding | |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Pro Preview |  Google Vertex AI | 2.00 | 12.00 | compare | 1.0M | 66K | 49.8 | 46.5 | |
| Gemini 3 Pro |  Replicate | 2.00 | 12.00 | compare | N/A | N/A | 49.8 | 46.5 | |
| Gemini 3 Pro Preview |  OpenRouter | 2.00 | 12.00 | compare | 1.0M | 66K | 49.8 | 46.5 | |
| Gemini 3 Pro Preview |  GMI Cloud | 2.00 | 12.00 | compare | 1.0M | 66K | 49.8 | 46.5 | |
| Gemini 3 Pro Preview |  GitHub Copilot | N/A | N/A | compare | 128K | 64K | 49.8 | 46.5 | |
| Gemini 3 Pro Preview |  Google Gemini | 2.00 | 12.00 | compare | 1.0M | 66K | 49.8 | 46.5 | |
| GPT-5.2 | OpenRouter | 1.75 | 14.00 | compare | 272K | 128K | 49.4 | 48.7 | |
| GPT-5.2-chat |  OpenAI | 1.75 | 14.00 | compare | 128K | 16K | 49.4 | 48.7 | |
| GPT-5.2 | GMI Cloud | 1.75 | 14.00 | compare | 410K | 32K | 49.4 | 48.7 | |
| GPT-5.2 | GitHub Copilot | N/A | N/A | compare | 128K | 64K | 49.4 | 48.7 | |
| GPT-5.2 |  Azure OpenAI | 1.75 | 14.00 | compare | 272K | 128K | 49.4 | 48.7 | |
| GPT-5.1-chat | OpenAI | 1.25 | 10.00 | compare | 128K | 16K | 47.7 | 44.7 | |
| GPT-5.1 | GMI Cloud | 1.25 | 10.00 | compare | 410K | 32K | 47.7 | 44.7 | |
| GPT-5.1 | GitHub Copilot | N/A | N/A | compare | 128K | 64K | 47.7 | 44.7 | |
| Databricks GPT 5 1 |  Databricks | 1.25 | 10.00 | compare | 272K | 128K | 47.7 | 44.7 | |
| GPT-5.1 | Azure OpenAI | 1.38 | 11.00 | compare | 272K | 128K | 47.7 | 44.7 | |
| Kimi K2.5 |  Together AI | 0.500 | 2.80 | compare | 256K | 256K | 46.8 | 39.5 | |
| Kimi K2.5 | OpenRouter | 0.600 | 3.00 | compare | 262K | 262K | 46.8 | 39.5 | |
| Moonshotai.kimi K2.5 |  AWS Bedrock | 0.600 | 3.00 | compare | 262K | 262K | 46.8 | 39.5 | |
| Kimi K2.5 |  Moonshot AI (Kimi) | 0.600 | 3.00 | compare | 262K | 262K | 46.8 | 39.5 | |
| Kimi K2p5 |  Fireworks AI | 0.600 | 3.00 | compare | 262K | 262K | 46.8 | 39.5 | |
| GPT-5 | Replicate | 1.25 | 10.00 | compare | N/A | N/A | 44.6 | 36.0 | |
| GPT-5-codex | OpenRouter | 1.25 | 10.00 | compare | 272K | 128K | 44.6 | 38.9 | |
| GPT-5 | OpenRouter | 1.25 | 10.00 | compare | 272K | 128K | 44.6 | 36.0 | |
| GPT-5-chat | OpenAI | 1.25 | 10.00 | compare | 128K | 16K | 44.6 | 36.0 | |
| GPT-5 | GMI Cloud | 1.25 | 10.00 | compare | 410K | 32K | 44.6 | 36.0 | |
| GPT-5 | GitHub Copilot | N/A | N/A | compare | 128K | 128K | 44.6 | 36.0 | |
| Databricks GPT 5 | Databricks | 1.25 | 10.00 | compare | 272K | 128K | 44.6 | 36.0 | |
| GPT-5-chat | Azure OpenAI | 1.25 | 10.00 | compare | 128K | 16K | 44.6 | 36.0 | |
| Glm 4.7 |  Z AI (Zhipu) | 0.600 | 2.20 | compare | 200K | 128K | 42.1 | 36.3 | |
| Zai.glm 4.7 | AWS Bedrock | 0.600 | 2.20 | compare | 200K | 128K | 42.1 | 36.3 | |
| Glm 4.7 Maas |  Vertex AI (Z AI) | 0.600 | 2.20 | compare | 200K | 128K | 42.1 | 36.3 | |
| GLM 4.7 | Together AI | 0.450 | 2.00 | compare | 200K | 200K | 42.1 | 36.3 | |
| Glm 4.7 | OpenRouter | 0.400 | 1.50 | compare | 203K | 64K | 42.1 | 36.3 | |
| Glm 4.7 |  Novita AI | 0.600 | 2.20 | compare | 205K | 131K | 42.1 | 36.3 | |
| GLM 4.7 FP8 | GMI Cloud | 0.400 | 2.00 | compare | 203K | 16K | 42.1 | 36.3 | |
| Glm 4 7 251222 |  Volcengine (ByteDance) | N/A | N/A | compare | 205K | 131K | 42.1 | 36.3 | |
| Glm 4p7 | Fireworks AI | 0.600 | 2.20 | compare | 203K | 203K | 42.1 | 36.3 | |
| Minimax M2.5 | OpenRouter | 0.300 | 1.10 | compare | 197K | 66K | 41.9 | 37.4 | |
| MiniMax M2.5 |  MiniMax | 0.300 | 1.20 | compare | 1.0M | 8K | 41.9 | 37.4 | |
| DeepSeek Reasoner |  DeepSeek | 0.280 | 0.420 | compare | 131K | 66K | 41.7 | 36.7 | |
| GPT-5 mini | Replicate | 0.250 | 2.00 | compare | N/A | N/A | 41.2 | 35.3 | |
| GPT-5 mini | OpenRouter | 0.250 | 2.00 | compare | 272K | 128K | 41.2 | 35.3 | |
| GPT-5 mini | OpenAI | 0.250 | 2.00 | compare | 272K | 128K | 41.2 | 35.3 | |
| GPT-5 mini | GitHub Copilot | N/A | N/A | compare | 128K | 64K | 41.2 | 35.3 | |
| Databricks GPT 5 Mini | Databricks | 0.250 | 2.00 | compare | 272K | 128K | 41.2 | 35.3 | |
| GPT-5 mini | Azure OpenAI | 0.250 | 2.00 | compare | 272K | 128K | 41.2 | 35.3 | |
| Grok 4 |  xAI | 3.00 | 15.00 | compare | 256K | 256K | 40.7 | 40.5 | |
| Grok 4 |  Vercel AI Gateway | 3.00 | 15.00 | compare | 256K | 256K | 40.7 | 40.5 | |
| Grok 4 | Replicate | 7.20 | 36.00 | compare | N/A | N/A | 40.7 | 40.5 | |
| Grok 4 | OpenRouter | 3.00 | 15.00 | compare | 256K | 256K | 40.7 | 40.5 | |
| Xai.grok 4 |  Oracle Cloud (OCI) | 3.00 | 15.00 | compare | 128K | 128K | 40.7 | 40.5 | |
| Grok 4 |  Azure AI | 3.00 | 15.00 | compare | 131K | 131K | 40.7 | 40.5 | |
| o3 | Vercel AI Gateway | 2.00 | 8.00 | compare | 200K | 100K | 38.4 | 38.4 | |
| o3 | OpenAI | 2.00 | 8.00 | compare | 200K | 100K | 38.4 | 38.4 | |
| Openai O3 |  Gradient AI | 2.00 | 8.00 | compare | 100K | N/A | 38.4 | 38.4 | |
| o3 | Azure OpenAI | 2.00 | 8.00 | compare | 200K | 100K | 38.4 | 38.4 | |
| Claude Sonnet 4.5 |  Anthropic (Vertex AI) | 3.00 | 15.00 | compare | 200K | 64K | 37.1 | 33.5 | |
| Claude Sonnet 4.5 | Vercel AI Gateway | 3.00 | 15.00 | compare | 1.0M | 64K | 37.1 | 33.5 | |
| Claude 4.5 Sonnet | Replicate | 3.00 | 15.00 | compare | N/A | N/A | 37.1 | 33.5 | |
| Claude Sonnet 4.5 | OpenRouter | 3.00 | 15.00 | compare | 1.0M | 1.0M | 37.1 | 33.5 | |
| Claude Sonnet 4.5 | GMI Cloud | 3.00 | 15.00 | compare | 410K | 32K | 37.1 | 33.5 | |
| Claude Sonnet 4.5 | GitHub Copilot | N/A | N/A | compare | 128K | 16K | 37.1 | 33.5 | |
| Databricks Claude Sonnet 4 5 | Databricks | 3.00 | 15.00 | compare | 200K | 64K | 37.1 | 33.5 | |
| Claude Sonnet 4.5 |  AWS Bedrock | 3.00 | 15.00 | compare | 200K | 64K | 37.1 | 33.5 | |
| Claude Sonnet 4.5 |  Anthropic | 3.00 | 15.00 | compare | 200K | 64K | 37.1 | 33.5 | |
| Claude Sonnet 4.5 | Azure AI | 3.00 | 15.00 | compare | 200K | 64K | 37.1 | 33.5 | |
| Minimax M2 Maas |  Vertex AI (MiniMax) | 0.300 | 1.20 | compare | 197K | 197K | 36.1 | 29.2 | |
| Minimax M2 | OpenRouter | 0.255 | 1.02 | compare | 205K | 205K | 36.1 | 29.2 | |
| Minimax M2 | Novita AI | 0.300 | 1.20 | compare | 205K | 131K | 36.1 | 29.2 | |
| MiniMax M2 | MiniMax | 0.300 | 1.20 | compare | 200K | 8K | 36.1 | 29.2 | |
| Minimax.minimax M2 | AWS Bedrock | 0.300 | 1.20 | compare | 128K | 8K | 36.1 | 29.2 | |
| Minimax M2 | Fireworks AI | 0.300 | 1.20 | compare | 4K | 4K | 36.1 | 29.2 | |
| Kat Coder Pro | Novita AI | 0.300 | 1.20 | compare | 256K | 128K | 36.0 | 18.3 | |
| Claude Opus 4.5 | Anthropic (Vertex AI) | 5.00 | 25.00 | compare | 200K | 64K | 35.3 | 42.9 | |
| Claude Opus 4.5 | Vercel AI Gateway | 5.00 | 25.00 | compare | 200K | 64K | 35.3 | 42.9 | |
| Claude Opus 4.5 | OpenRouter | 5.00 | 25.00 | compare | 200K | 32K | 35.3 | 42.9 | |
| Claude Opus 4.5 | GMI Cloud | 5.00 | 25.00 | compare | 410K | 32K | 35.3 | 42.9 | |
| Claude Opus 4.5 | GitHub Copilot | N/A | N/A | compare | 128K | 16K | 35.3 | 42.9 | |
| Databricks Claude Opus 4 5 | Databricks | 5.00 | 25.00 | compare | 200K | 64K | 35.3 | 42.9 | |
| Claude Opus 4.5 | Anthropic | 5.00 | 25.00 | compare | 200K | 64K | 35.3 | 42.9 | |
| Claude Opus 4.5 | Azure AI | 5.00 | 25.00 | compare | 200K | 64K | 35.3 | 42.9 | |
| Claude Opus 4.5 | AWS Bedrock | 5.00 | 25.00 | compare | 200K | 64K | 35.3 | 42.9 | |
| Gemini 3 Flash Preview | Google Vertex AI | 0.500 | 3.00 | compare | 1.0M | 66K | 35.0 | 37.8 | |
| Gemini 3 Flash Preview | OpenRouter | 0.500 | 3.00 | compare | 1.0M | 66K | 35.0 | 37.8 | |
| Gemini 3 Flash Preview | GMI Cloud | 0.500 | 3.00 | compare | 1.0M | 66K | 35.0 | 37.8 | |
| Gemini 3 Flash Preview | Google Gemini | 0.500 | 3.00 | compare | 1.0M | 66K | 35.0 | 37.8 | |
| DeepSeek V3.2 Speciale | Azure AI | 0.580 | 1.68 | compare | 164K | 164K | 34.1 | 37.9 | |
| GPT-oss-120b |  IBM watsonx | 0.150 | 0.600 | compare | 8K | 8K | 33.3 | 28.6 | |
| GPT-oss-120b |  Weights & Biases | 0.015 | 0.060 | compare | 131K | 131K | 33.3 | 28.6 | |
| GPT-oss-120b-maas |  Vertex AI (OpenAI) | 0.150 | 0.600 | compare | 131K | 33K | 33.3 | 28.6 | |
| GPT-oss-120b | Together AI | 0.150 | 0.600 | compare | 128K | N/A | 33.3 | 28.6 | |
| GPT-oss-120b |  SambaNova | 3.00 | 4.50 | compare | 131K | 131K | 33.3 | 28.6 | |
| GPT-oss-120b | Replicate | 0.180 | 0.720 | compare | N/A | N/A | 33.3 | 28.6 | |
| GPT-oss-120b |  OVHcloud | 0.080 | 0.400 | compare | 131K | 131K | 33.3 | 28.6 | |
| GPT-oss-120b | OpenRouter | 0.180 | 0.800 | compare | 131K | 33K | 33.3 | 28.6 | |
| GPT-oss-120b-1 | AWS Bedrock | 0.150 | 0.600 | compare | 128K | 128K | 33.3 | 28.6 | |
| GPT-oss:120b-cloud |  Ollama | N/A | N/A | compare | 131K | 131K | 33.3 | 28.6 | |
| GPT-oss-120b | Novita AI | 0.050 | 0.250 | compare | 131K | 33K | 33.3 | 28.6 | |
| GPT-oss-120b-mxfp-GGUF |  Lemonade (AMD) | N/A | N/A | compare | 131K | 33K | 33.3 | 28.6 | |
| GPT-oss-120b |  Groq | 0.150 | 0.600 | compare | 131K | 33K | 33.3 | 28.6 | |
| GPT-oss-120b | Fireworks AI | 0.150 | 0.600 | compare | 131K | 131K | 33.3 | 28.6 | |
| GPT-oss-120b |  DeepInfra | 0.050 | 0.450 | compare | 131K | 131K | 33.3 | 28.6 | |
| Databricks GPT OSS 120B | Databricks | 0.150 | 0.600 | compare | 131K | 131K | 33.3 | 28.6 | |
| GPT-oss-120b |  Cerebras | 0.350 | 0.750 | compare | 131K | 33K | 33.3 | 28.6 | |
| GPT-oss-120b | Azure AI | 0.150 | 0.600 | compare | 131K | 131K | 33.3 | 28.6 | |
| o4 mini | Vercel AI Gateway | 1.10 | 4.40 | compare | 200K | 100K | 33.1 | 25.6 | |
| o4 mini | Replicate | 1.00 | 4.00 | compare | N/A | N/A | 33.1 | 25.6 | |
| o4 mini | OpenAI | 1.10 | 4.40 | compare | 200K | 100K | 33.1 | 25.6 | |
| o4 mini | Azure OpenAI | 1.10 | 4.40 | compare | 200K | 100K | 33.1 | 25.6 | |
| Claude Sonnet 4 | Anthropic (Vertex AI) | 3.00 | 15.00 | compare | 1.0M | 64K | 33.0 | 30.6 | |
| Claude 4 Sonnet | Vercel AI Gateway | 3.00 | 15.00 | compare | 200K | 64K | 33.0 | 30.6 | |
| Claude 4 Sonnet | Replicate | 3.00 | 15.00 | compare | N/A | N/A | 33.0 | 30.6 | |
| Claude Sonnet 4 | OpenRouter | 3.00 | 15.00 | compare | 1.0M | 64K | 33.0 | 30.6 | |
| Claude 4 Sonnet |  Heroku (Salesforce) | N/A | N/A | compare | 8K | N/A | 33.0 | 30.6 | |
| Claude Sonnet 4 | GMI Cloud | 3.00 | 15.00 | compare | 410K | 32K | 33.0 | 30.6 | |
| Claude Sonnet 4 | GitHub Copilot | N/A | N/A | compare | 128K | 16K | 33.0 | 30.6 | |
| Claude 4 Sonnet | DeepInfra | 3.30 | 16.50 | compare | 200K | 200K | 33.0 | 30.6 | |
| Databricks Claude Sonnet 4 | Databricks | 3.00 | 15.00 | compare | 200K | 64K | 33.0 | 30.6 | |
| Claude 4 Sonnet | Anthropic | 3.00 | 15.00 | compare | 1.0M | 64K | 33.0 | 30.6 | |
| Claude Sonnet 4.20250514 | AWS Bedrock | 3.00 | 15.00 | compare | 1.0M | 64K | 33.0 | 30.6 | |
| Grok 3 Mini | xAI | 0.300 | 0.500 | compare | 131K | 131K | 32.1 | 25.2 | |
| DeepSeek V3.2 Maas |  Vertex AI (DeepSeek) | 0.560 | 1.68 | compare | 164K | 33K | 32.1 | 34.6 | |
| DeepSeek V3.2 | OpenRouter | 0.280 | 0.400 | compare | 164K | 164K | 32.1 | 34.6 | |
| DeepSeek V3.2 | Novita AI | 0.269 | 0.400 | compare | 164K | 66K | 32.1 | 34.6 | |
| DeepSeek V3.2 | GMI Cloud | 0.280 | 0.400 | compare | 164K | 16K | 32.1 | 34.6 | |
| DeepSeek V3p2 | Fireworks AI | 0.560 | 1.68 | compare | 164K | 164K | 32.1 | 34.6 | |
| DeepSeek V3.2 | DeepSeek | 0.280 | 0.400 | compare | 164K | 164K | 32.1 | 34.6 | |
| DeepSeek V3 2 251201 | Volcengine (ByteDance) | N/A | N/A | compare | 98K | 33K | 32.1 | 34.6 | |
| V3.2 | AWS Bedrock | 0.740 | 2.22 | compare | 164K | 164K | 32.1 | 34.6 | |
| DeepSeek V3.2 | Azure AI | 0.580 | 1.68 | compare | 164K | 164K | 32.1 | 34.6 | |
| Qwen3 Max | Novita AI | 2.11 | 8.45 | compare | 262K | 66K | 31.4 | 26.4 | |
| Qwen3 Max |  DashScope (Alibaba) | N/A | N/A | compare | 258K | 66K | 31.4 | 26.4 | |
| Kimi K2 Instruct 0905 | Together AI | 1.00 | 3.00 | compare | 262K | N/A | 30.9 | 25.9 | |
| Kimi K2 0905 | Novita AI | 0.600 | 2.50 | compare | 262K | 262K | 30.9 | 25.9 | |
| Kimi K2 0905 Preview | Moonshot AI (Kimi) | 0.600 | 2.50 | compare | 262K | 262K | 30.9 | 25.9 | |
| Kimi K2 Instruct 0905 | Groq | 1.00 | 3.00 | compare | 262K | 16K | 30.9 | 25.9 | |
| Kimi K2 Instruct 0905 | Fireworks AI | 0.600 | 2.50 | compare | 262K | 33K | 30.9 | 25.9 | |
| Kimi K2 Instruct 0905 | DeepInfra | 0.500 | 2.00 | compare | 262K | 262K | 30.9 | 25.9 | |
| Claude 3 7 Sonnet | Anthropic (Vertex AI) | 3.00 | 15.00 | compare | 200K | 8K | 30.8 | 26.7 | |
| o1 | Vercel AI Gateway | 15.00 | 60.00 | compare | 200K | 100K | 30.8 | 20.5 | |
| Claude 3 7 Sonnet | Vercel AI Gateway | 3.00 | 15.00 | compare | 200K | 64K | 30.8 | 26.7 | |
| o1 | Replicate | 15.00 | 60.00 | compare | N/A | N/A | 30.8 | 20.5 | |
| Claude 3.7 Sonnet | Replicate | 3.00 | 15.00 | compare | N/A | N/A | 30.8 | 26.7 | |
| o1 | OpenRouter | 15.00 | 60.00 | compare | 200K | 100K | 30.8 | 20.5 | |
| Claude 3.7 Sonnet | OpenRouter | 3.00 | 15.00 | compare | 200K | 128K | 30.8 | 26.7 | |
| o1 | OpenAI | 15.00 | 60.00 | compare | 200K | 100K | 30.8 | 20.5 | |
| Claude 3 7 Sonnet | Heroku (Salesforce) | N/A | N/A | compare | 8K | N/A | 30.8 | 26.7 | |
| Anthropic Claude 3.7 Sonnet | Gradient AI | 3.00 | 15.00 | compare | 1K | N/A | 30.8 | 26.7 | |
| Eu.anthropic.claude 3 7 Sonnet 20250219 V1 | AWS Bedrock | 3.00 | 15.00 | compare | 200K | 8K | 30.8 | 26.7 | |
| Claude 3 7 Sonnet | DeepInfra | 3.30 | 16.50 | compare | 200K | 200K | 30.8 | 26.7 | |
| Databricks Claude 3 7 Sonnet | Databricks | 3.00 | 15.00 | compare | 200K | 128K | 30.8 | 26.7 | |
| Claude 3 7 Sonnet | Anthropic | 3.00 | 15.00 | compare | 200K | 64K | 30.8 | 26.7 | |
| o1 | Azure OpenAI | 15.00 | 60.00 | compare | 200K | 100K | 30.8 | 20.5 | |
| Mimo V2 Flash | OpenRouter | 0.090 | 0.290 | compare | 262K | 16K | 30.4 | 25.8 | |
| Mimo V2 Flash | Novita AI | 0.100 | 0.300 | compare | 262K | 32K | 30.4 | 25.8 | |
| Gemini 2.5 Pro | Vercel AI Gateway | 2.50 | 10.00 | compare | 1.0M | 66K | 30.3 | 46.7 | |
| Gemini 2.5 Pro | OpenRouter | 1.25 | 10.00 | compare | 1.0M | 8K | 30.3 | 46.7 | |
| Gemini 2.5 Pro | GitHub Copilot | N/A | N/A | compare | 128K | 64K | 30.3 | 46.7 | |
| Gemini pro | Google Gemini | 1.25 | 10.00 | compare | 1.0M | 66K | 30.3 | 46.7 | |
| Gemini 2.5 Pro |  Google Vertex AI | 1.25 | 10.00 | compare | 1.0M | 66K | 30.3 | 46.7 | |
| Gemini 2.5 Pro | DeepInfra | 1.25 | 10.00 | compare | 1.0M | 1.0M | 30.3 | 46.7 | |
| Databricks Gemini 2 5 Pro | Databricks | 1.25 | 10.00 | compare | 1.0M | 66K | 30.3 | 46.7 | |
| Glm 4.6 | Z AI (Zhipu) | 0.600 | 2.20 | compare | 200K | 128K | 30.2 | 30.2 | |
| Glm 4.6 | Vercel AI Gateway | 0.450 | 1.80 | compare | 200K | 200K | 30.2 | 30.2 | |
| GLM 4.6 | Together AI | 0.600 | 2.20 | compare | 200K | 200K | 30.2 | 30.2 | |
| Glm 4.6 | OpenRouter | 0.400 | 1.75 | compare | 203K | 131K | 30.2 | 30.2 | |
| Glm 4.6 | Novita AI | 0.550 | 2.20 | compare | 205K | 131K | 30.2 | 30.2 | |
| Glm 4p6 | Fireworks AI | 0.550 | 2.19 | compare | 203K | 203K | 30.2 | 30.2 | |
| Glm 4.7 Flash | OpenRouter | 0.070 | 0.400 | compare | 200K | 32K | 30.1 | 25.9 | |
| Qwen3 235B A22b Thinking 2507 | Novita AI | 0.300 | 3.00 | compare | 131K | 33K | 29.5 | 23.2 | |
| Qwen3 235B A22b Thinking 2507 | Fireworks AI | 0.220 | 0.880 | compare | 262K | 262K | 29.5 | 23.2 | |
| Grok Code Fast 1 | xAI | 0.200 | 1.50 | compare | 256K | 256K | 28.7 | 23.7 | |
| Grok Code Fast 1 | Azure AI | 0.200 | 1.50 | compare | 131K | 131K | 28.7 | 23.7 | |
| DeepSeek V3.1 Terminus | Novita AI | 0.270 | 1.00 | compare | 131K | 33K | 28.5 | 31.9 | |
| DeepSeek V3p1 Terminus | Fireworks AI | 0.560 | 1.68 | compare | 128K | 8K | 28.5 | 31.9 | |
| DeepSeek V3.1 Terminus | DeepInfra | 0.270 | 1.00 | compare | 164K | 164K | 28.5 | 31.9 | |
| Qwen3 Coder Next | AWS Bedrock | 0.600 | 1.44 | compare | 262K | 8K | 28.3 | 22.9 | |
| DeepSeek V3.1 | Weights & Biases | 0.055 | 0.165 | compare | 128K | 128K | 28.1 | 28.4 | |
| DeepSeek V3.1 Maas | Vertex AI (DeepSeek) | 1.35 | 5.40 | compare | 164K | 33K | 28.1 | 28.4 | |
| DeepSeek V3.1 | Together AI | 0.600 | 1.70 | compare | 128K | N/A | 28.1 | 28.4 | |
| DeepSeek V3.1 | SambaNova | 3.00 | 4.50 | compare | 33K | 33K | 28.1 | 28.4 | |
| DeepSeek V3.1 | Replicate | 0.672 | 2.02 | compare | 164K | 164K | 28.1 | 28.4 | |
| DeepSeek V3.1:671B Cloud | Ollama | N/A | N/A | compare | 164K | 164K | 28.1 | 28.4 | |
| DeepSeek V3.1 | Novita AI | 0.270 | 1.00 | compare | 131K | 33K | 28.1 | 28.4 | |
| DeepSeek V3p1 | Fireworks AI | 0.560 | 1.68 | compare | 128K | 8K | 28.1 | 28.4 | |
| DeepSeek V3.1 | DeepInfra | 0.270 | 1.00 | compare | 164K | 164K | 28.1 | 28.4 | |
| DeepSeek R1 | Vercel AI Gateway | 0.550 | 2.19 | compare | 128K | 8K | 27.1 | 24.0 | |
| Us.deepseek.r1 V1 | AWS Bedrock | 1.35 | 5.40 | compare | 128K | 4K | 27.1 | 24.0 | |
| DeepSeek R1 | Together AI | 3.00 | 7.00 | compare | 128K | 20K | 27.1 | 24.0 | |
| DeepSeek R1 |  Snowflake | N/A | N/A | compare | 33K | 8K | 27.1 | 24.0 | |
| DeepSeek R1 | SambaNova | 5.00 | 7.00 | compare | 33K | 33K | 27.1 | 24.0 | |
| DeepSeek R1 | Replicate | 3.75 | 10.00 | compare | 66K | 8K | 27.1 | 24.0 | |
| DeepSeek R1 | OpenRouter | 0.550 | 2.19 | compare | 65K | 8K | 27.1 | 24.0 | |
| Magistral Medium 2509 |  Mistral AI | 2.00 | 5.00 | compare | 40K | 40K | 27.1 | 21.7 | |
| DeepSeek R1 |  Hyperbolic | 0.400 | 0.400 | compare | 33K | 33K | 27.1 | 24.0 | |
| DeepSeek R1 | Fireworks AI | 3.00 | 8.00 | compare | 128K | 20K | 27.1 | 24.0 | |
| DeepSeek R1 | DeepSeek | 0.550 | 2.19 | compare | 66K | 8K | 27.1 | 24.0 | |
| DeepSeek R1 | DeepInfra | 0.700 | 2.40 | compare | 164K | 164K | 27.1 | 24.0 | |
| DeepSeek R1 | Azure AI | 1.35 | 5.40 | compare | 128K | 8K | 27.1 | 24.0 | |
| GPT-5 nano | Replicate | 0.050 | 0.400 | compare | N/A | N/A | 26.8 | 20.3 | |
| GPT-5 nano | OpenRouter | 0.050 | 0.400 | compare | 272K | 128K | 26.8 | 20.3 | |
| GPT-5 nano | OpenAI | 0.050 | 0.400 | compare | 272K | 128K | 26.8 | 20.3 | |
| Databricks GPT 5 Nano | Databricks | 0.050 | 0.400 | compare | 272K | 128K | 26.8 | 20.3 | |
| GPT-4.1 nano | Azure OpenAI | 0.100 | 0.400 | compare | 1.0M | 33K | 26.8 | 20.3 | |
| Qwen3 Next 80B A3b Thinking Maas |  Vertex AI (Qwen) | 0.150 | 1.20 | compare | 262K | 262K | 26.7 | 19.5 | |
| Qwen3 Next 80B A3B Thinking | Together AI | 0.150 | 1.50 | compare | 262K | N/A | 26.7 | 19.5 | |
| Qwen3 Next 80B A3b Thinking | Novita AI | 0.150 | 1.50 | compare | 131K | 33K | 26.7 | 19.5 | |
| Qwen3 Next 80B A3b Thinking | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | 26.7 | 19.5 | |
| Qwen3 Next 80B A3B Thinking | DeepInfra | 0.140 | 1.40 | compare | 262K | 262K | 26.7 | 19.5 | |
| Glm 4.5 | Z AI (Zhipu) | 0.600 | 2.20 | compare | 128K | 32K | 26.4 | 26.3 | |
| GLM 4.5 | Weights & Biases | 0.055 | 0.200 | compare | 131K | 131K | 26.4 | 26.3 | |
| Glm 4.5 | Vercel AI Gateway | 0.600 | 2.20 | compare | 131K | 131K | 26.4 | 26.3 | |
| Glm 4.5 | Novita AI | 0.600 | 2.20 | compare | 131K | 98K | 26.4 | 26.3 | |
| Glm 4p5 | Fireworks AI | 0.550 | 2.19 | compare | 128K | 96K | 26.4 | 26.3 | |
| GLM 4.5 | DeepInfra | 0.400 | 1.60 | compare | 131K | 131K | 26.4 | 26.3 | |
| Glm 4.5 Air | Z AI (Zhipu) | 0.200 | 1.10 | compare | 128K | 32K | 26.3 | 23.8 | |
| Kimi K2 Instruct | Weights & Biases | 0.600 | 2.50 | compare | 128K | 128K | 26.3 | 22.1 | |
| Glm 4.5 Air | Vercel AI Gateway | 0.200 | 1.10 | compare | 128K | 96K | 26.3 | 23.8 | |
| GPT-4.1 | Vercel AI Gateway | 2.00 | 8.00 | compare | 1.0M | 33K | 26.3 | 21.8 | |
| Kimi K2 | Vercel AI Gateway | 0.550 | 2.20 | compare | 131K | 16K | 26.3 | 22.1 | |
| GLM 4.5 Air FP8 | Together AI | 0.200 | 1.10 | compare | 128K | N/A | 26.3 | 23.8 | |
| Kimi K2 Instruct | Together AI | 1.00 | 3.00 | compare | N/A | N/A | 26.3 | 22.1 | |
| GPT-4.1 | Replicate | 2.00 | 8.00 | compare | N/A | N/A | 26.3 | 21.8 | |
| GPT-4.1 | OpenRouter | 2.00 | 8.00 | compare | 1.0M | 33K | 26.3 | 21.8 | |
| Glm 4.5 Air | Novita AI | 0.130 | 0.850 | compare | 131K | 98K | 26.3 | 23.8 | |
| Kimi K2 Instruct | Novita AI | 0.570 | 2.30 | compare | 131K | 131K | 26.3 | 22.1 | |
| Kimi K2 Instruct | Hyperbolic | 2.00 | 2.00 | compare | 131K | 131K | 26.3 | 22.1 | |
| GPT-4.1 | GitHub Copilot | N/A | N/A | compare | 128K | 16K | 26.3 | 21.8 | |
| Ft:gpt 4 0613 | OpenAI | 30.00 | 60.00 | compare | 8K | 4K | 26.3 | 21.8 | |
| Kimi K2 Instruct | Fireworks AI | 0.600 | 2.50 | compare | 131K | 16K | 26.3 | 22.1 | |
| Kimi K2 Instruct | DeepInfra | 0.500 | 2.00 | compare | 131K | 131K | 26.3 | 22.1 | |
| GPT-4.1 | Azure OpenAI | 2.20 | 8.80 | compare | 1.0M | 33K | 26.3 | 21.8 | |
| o3 mini | Vercel AI Gateway | 1.10 | 4.40 | compare | 200K | 100K | 25.9 | 17.9 | |
| o3 mini | OpenRouter | 1.10 | 4.40 | compare | 128K | 66K | 25.9 | 17.9 | |
| o3 mini | OpenAI | 1.10 | 4.40 | compare | 200K | 100K | 25.9 | 17.9 | |
| Openai O3 Mini | Gradient AI | 1.10 | 4.40 | compare | 100K | N/A | 25.9 | 17.9 | |
| o3 mini | Azure OpenAI | 1.10 | 4.40 | compare | 200K | 100K | 25.9 | 17.9 | |
| Grok 3 | xAI | 3.00 | 15.00 | compare | 131K | 131K | 25.2 | 19.8 | |
| Grok 3 | Vercel AI Gateway | 3.00 | 15.00 | compare | 131K | 131K | 25.2 | 19.8 | |
| Xai.grok 3 | Oracle Cloud (OCI) | 3.00 | 15.00 | compare | 131K | 131K | 25.2 | 19.8 | |
| Grok 3 | Azure AI | 3.00 | 15.00 | compare | 131K | 131K | 25.2 | 19.8 | |
| Qwen3 235B A22B Instruct 2507 | Weights & Biases | 0.010 | 0.010 | compare | 262K | 262K | 25.0 | 22.1 | |
| Qwen3 235B A22b Instruct 2507 Maas | Vertex AI (Qwen) | 0.250 | 1.00 | compare | 262K | 16K | 25.0 | 22.1 | |
| Qwen3 235B A22B Instruct 2507 Tput | Together AI | 0.200 | 6.00 | compare | 262K | N/A | 25.0 | 22.1 | |
| Qwen3 235B A22b 2507 V1 | AWS Bedrock | 0.220 | 0.880 | compare | 262K | 131K | 25.0 | 22.1 | |
| Qwen3 235B A22b 2507 | OpenRouter | 0.071 | 0.100 | compare | 262K | 262K | 25.0 | 22.1 | |
| Qwen3 235B A22b Instruct 2507 | Novita AI | 0.090 | 0.580 | compare | 131K | 16K | 25.0 | 22.1 | |
| Qwen3 235B A22b Instruct 2507 | Fireworks AI | 0.220 | 0.880 | compare | 262K | 262K | 25.0 | 22.1 | |
| Qwen3 235B A22B Instruct 2507 | DeepInfra | 0.090 | 0.600 | compare | 262K | 262K | 25.0 | 22.1 | |
| Qwen3 Coder 480B A35B Instruct | Weights & Biases | 0.100 | 0.150 | compare | 262K | 262K | 24.8 | 24.6 | |
| Qwen3 Coder 480B A35b Instruct Maas | Vertex AI (Qwen) | 1.00 | 4.00 | compare | 262K | 33K | 24.8 | 24.6 | |
| Qwen3 Coder 480B A35B Instruct FP8 | Together AI | 2.00 | 2.00 | compare | 256K | N/A | 24.8 | 24.6 | |
| Qwen3 Coder 480B A35b V1 | AWS Bedrock | 0.220 | 1.80 | compare | 262K | 66K | 24.8 | 24.6 | |
| Qwen3 Coder:480B Cloud | Ollama | N/A | N/A | compare | 262K | 262K | 24.8 | 24.6 | |
| Qwen3 Coder 480B A35b Instruct | Novita AI | 0.300 | 1.30 | compare | 262K | 66K | 24.8 | 24.6 | |
| Qwen3 Coder 480B A35b Instruct | Fireworks AI | 0.450 | 1.80 | compare | 262K | 262K | 24.8 | 24.6 | |
| Qwen3 Coder 480B A35B Instruct | DeepInfra | 0.400 | 1.60 | compare | 262K | 262K | 24.8 | 24.6 | |
| GPT-oss-20b | Weights & Biases | 0.0050 | 0.020 | compare | 131K | 131K | 24.5 | 18.5 | |
| GPT-oss-20b-maas | Vertex AI (OpenAI) | 0.075 | 0.300 | compare | 131K | 33K | 24.5 | 18.5 | |
| GPT-oss-20b | Together AI | 0.050 | 0.200 | compare | 128K | N/A | 24.5 | 18.5 | |
| GPT-oss-20b | Replicate | 0.090 | 0.360 | compare | N/A | N/A | 24.5 | 18.5 | |
| GPT-oss-20b | OVHcloud | 0.040 | 0.150 | compare | 131K | 131K | 24.5 | 18.5 | |
| GPT-oss-20b | OpenRouter | 0.020 | 0.100 | compare | 131K | 33K | 24.5 | 18.5 | |
| GPT-oss-20b-1 | AWS Bedrock | 0.070 | 0.300 | compare | 128K | 128K | 24.5 | 18.5 | |
| GPT-oss:20b-cloud | Ollama | N/A | N/A | compare | 131K | 131K | 24.5 | 18.5 | |
| GPT-oss-20b | Novita AI | 0.040 | 0.150 | compare | 131K | 33K | 24.5 | 18.5 | |
| GPT-oss-20b-mxfp4-GGUF | Lemonade (AMD) | N/A | N/A | compare | 131K | 33K | 24.5 | 18.5 | |
| GPT-oss-20b | Groq | 0.075 | 0.300 | compare | 131K | 33K | 24.5 | 18.5 | |
| GPT-oss-20b | Fireworks AI | 0.050 | 0.200 | compare | 131K | 131K | 24.5 | 18.5 | |
| GPT-oss-20b | DeepInfra | 0.040 | 0.150 | compare | 131K | 131K | 24.5 | 18.5 | |
| Databricks GPT OSS 20B | Databricks | 0.070 | 0.300 | compare | 131K | 131K | 24.5 | 18.5 | |
| Kimi K2 Thinking Maas |  Vertex AI (Moonshot) | 0.600 | 2.50 | compare | 256K | 256K | 24.1 | 15.5 | |
| Kimi K2 Thinking | Novita AI | 0.600 | 2.50 | compare | 262K | 262K | 24.1 | 15.5 | |
| Kimi K2 Thinking | Moonshot AI (Kimi) | 0.600 | 2.50 | compare | 262K | 262K | 24.1 | 15.5 | |
| Kimi K2 Thinking 251104 | Volcengine (ByteDance) | N/A | N/A | compare | 229K | 33K | 24.1 | 15.5 | |
| Kimi K2 Thinking | GMI Cloud | 0.800 | 1.20 | compare | 262K | 16K | 24.1 | 15.5 | |
| Kimi K2 Thinking | Fireworks AI | 0.600 | 2.50 | compare | 262K | 262K | 24.1 | 15.5 | |
| Moonshotai.kimi K2 Thinking | AWS Bedrock | 0.730 | 3.03 | compare | 262K | 262K | 24.1 | 15.5 | |
| Qwen3 Next 80B A3b Instruct Maas | Vertex AI (Qwen) | 0.150 | 1.20 | compare | 262K | 262K | 23.7 | 15.3 | |
| Qwen3 Next 80B A3B Instruct | Together AI | 0.150 | 1.50 | compare | 262K | N/A | 23.7 | 15.3 | |
| Qwen3 Next 80B A3b | AWS Bedrock | 0.150 | 1.20 | compare | 128K | 8K | 23.7 | 15.3 | |
| o1-preview | OpenAI | 15.00 | 60.00 | compare | 128K | 33K | 23.7 | 34.0 | |
| Qwen3 Next 80B A3b Instruct | Novita AI | 0.150 | 1.50 | compare | 131K | 33K | 23.7 | 15.3 | |
| Qwen3 Next 80B A3b Instruct | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | 23.7 | 15.3 | |
| Qwen3 Next 80B A3B Instruct | DeepInfra | 0.140 | 1.40 | compare | 262K | 262K | 23.7 | 15.3 | |
| o1-preview | Azure OpenAI | 15.00 | 60.00 | compare | 128K | 33K | 23.7 | 34.0 | |
| Claude Opus 4.1 | Anthropic (Vertex AI) | 15.00 | 75.00 | compare | 200K | 32K | 23.6 | N/A | |
| Claude Opus 4.1 | Vercel AI Gateway | 15.00 | 75.00 | compare | 200K | 32K | 23.6 | N/A | |
| Claude Opus 4.1 | OpenRouter | 15.00 | 75.00 | compare | 200K | 32K | 23.6 | N/A | |
| Claude Opus 41 | GitHub Copilot | N/A | N/A | compare | 80K | 16K | 23.6 | N/A | |
| Databricks Claude Opus 4 1 | Databricks | 15.00 | 75.00 | compare | 200K | 32K | 23.6 | N/A | |
| Claude Opus 4.1 | Anthropic | 15.00 | 75.00 | compare | 200K | 32K | 23.6 | N/A | |
| Claude Opus 4.1 | Azure AI | 15.00 | 75.00 | compare | 200K | 32K | 23.6 | N/A | |
| Claude Opus 4.1 | AWS Bedrock | 15.00 | 75.00 | compare | 200K | 32K | 23.6 | N/A | |
| Qwen3 Vl 235B A22b | AWS Bedrock | 0.530 | 2.66 | compare | 128K | 8K | 23.3 | 16.5 | |
| Qwen3 Vl 235B A22b Instruct | Novita AI | 0.300 | 1.50 | compare | 131K | 33K | 23.3 | 16.5 | |
| Qwen3 Vl 235B A22b Instruct | Fireworks AI | 0.220 | 0.880 | compare | 262K | 262K | 23.3 | 16.5 | |
| Grok 4 Fast Non Reasoning | xAI | 0.200 | 0.500 | compare | 2.0M | 2.0M | 23.1 | 19.0 | |
| Mistral Large 3 | Mistral AI | 0.500 | 1.50 | compare | 256K | 8K | 22.8 | 22.7 | |
| Mistral Large 3 675B Instruct | AWS Bedrock | 0.500 | 1.50 | compare | 128K | 8K | 22.8 | 22.7 | |
| Mistral Large 3 Fp8 | Fireworks AI | 1.20 | 1.20 | compare | 256K | 256K | 22.8 | 22.7 | |
| Mistral Large 3 | Azure AI | 0.500 | 1.50 | compare | 256K | 8K | 22.8 | 22.7 | |
| Magistral Small 2509 | AWS Bedrock | 0.500 | 1.50 | compare | 128K | 8K | 22.5 | 14.8 | |
| DeepSeek V3 0324 | Weights & Biases | 0.114 | 0.275 | compare | 161K | 161K | 22.3 | 22.0 | |
| DeepSeek V3 0324 | Novita AI | 0.270 | 1.12 | compare | 164K | 164K | 22.3 | 22.0 | |
| DeepSeek V3 0324 |  Lambda | 0.200 | 0.600 | compare | 131K | 131K | 22.3 | 22.0 | |
| DeepSeek V3 0324 | Hyperbolic | 0.400 | 0.400 | compare | 33K | 33K | 22.3 | 22.0 | |
| DeepSeek V3 0324 | GMI Cloud | 0.280 | 0.880 | compare | 164K | 16K | 22.3 | 22.0 | |
| DeepSeek V3 0324 | Fireworks AI | 0.900 | 0.900 | compare | 164K | 164K | 22.3 | 22.0 | |
| DeepSeek V3 0324 | DeepInfra | 0.250 | 0.880 | compare | 164K | 164K | 22.3 | 22.0 | |
| Claude Opus 4 | Anthropic (Vertex AI) | 15.00 | 75.00 | compare | 200K | 32K | 22.2 | N/A | |
| GPT-4.1 mini | Vercel AI Gateway | 0.400 | 1.60 | compare | 1.0M | 33K | 22.2 | 18.5 | |
| Claude 4 Opus | Vercel AI Gateway | 15.00 | 75.00 | compare | 200K | 32K | 22.2 | N/A | |
| GPT-4.1 mini | Replicate | 0.400 | 1.60 | compare | N/A | N/A | 22.2 | 18.5 | |
| GPT-4.1 mini | OpenRouter | 0.400 | 1.60 | compare | 1.0M | 33K | 22.2 | 18.5 | |
| Claude Opus 4 | OpenRouter | 15.00 | 75.00 | compare | 200K | 32K | 22.2 | N/A | |
| GPT-4.1 mini | OpenAI | 0.400 | 1.60 | compare | 1.0M | 33K | 22.2 | 18.5 | |
| Claude Opus 4 | GMI Cloud | 15.00 | 75.00 | compare | 410K | 32K | 22.2 | N/A | |
| Claude 4 Opus | DeepInfra | 16.50 | 82.50 | compare | 200K | 200K | 22.2 | N/A | |
| Databricks Claude Opus 4 | Databricks | 15.00 | 75.00 | compare | 200K | 32K | 22.2 | N/A | |
| Claude 4 Opus | Anthropic | 15.00 | 75.00 | compare | 200K | 32K | 22.2 | N/A | |
| GPT-4.1 mini | Azure OpenAI | 0.440 | 1.76 | compare | 1.0M | 33K | 22.2 | 18.5 | |
| Claude Opus 4.20250514 | AWS Bedrock | 15.00 | 75.00 | compare | 200K | 32K | 22.2 | N/A | |
| Nova 2 Pro Preview 20251202 V1 | AWS Bedrock | 2.19 | 17.50 | compare | 1.0M | 64K | 21.9 | 20.5 | |
| Claude Haiku 4.5 | Anthropic (Vertex AI) | 1.00 | 5.00 | compare | 200K | 8K | 21.8 | 29.6 | |
| Claude Haiku 4.5 | Vercel AI Gateway | 1.00 | 5.00 | compare | 200K | 64K | 21.8 | 29.6 | |
| Claude 4.5 Haiku | Replicate | 1.00 | 5.00 | compare | N/A | N/A | 21.8 | 29.6 | |
| Claude Haiku 4.5 | OpenRouter | 1.00 | 5.00 | compare | 200K | 200K | 21.8 | 29.6 | |
| Claude Haiku 4.5 | GitHub Copilot | N/A | N/A | compare | 128K | 16K | 21.8 | 29.6 | |
| Databricks Claude Haiku 4 5 | Databricks | 1.00 | 5.00 | compare | 200K | 64K | 21.8 | 29.6 | |
| Claude Haiku 4.5 | Anthropic | 1.00 | 5.00 | compare | 200K | 64K | 21.8 | 29.6 | |
| Claude Haiku 4.5 | Azure AI | 1.00 | 5.00 | compare | 200K | 64K | 21.8 | 29.6 | |
| Claude Haiku 4.5 | AWS Bedrock | 1.00 | 5.00 | compare | 200K | 64K | 21.8 | 29.6 | |
| Qwen3 Vl 32B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | 21.4 | 15.6 | |
| Gemini 2.5 Flash | Vercel AI Gateway | 0.300 | 2.50 | compare | 1.0M | 66K | 21.1 | 17.8 | |
| Gemini 2.5 Flash | Replicate | 2.50 | 2.50 | compare | N/A | N/A | 21.1 | 17.8 | |
| Gemini 2.5 Flash | OpenRouter | 0.300 | 2.50 | compare | 1.0M | 8K | 21.1 | 17.8 | |
| Gemini 2.5 Flash-native-audio | Google Gemini | 0.300 | 2.50 | compare | 1.0M | 8K | 21.1 | 17.8 | |
| Gemini 2.5 Flash | Google Vertex AI | 0.300 | 2.50 | compare | 1.0M | 66K | 21.1 | 17.8 | |
| Gemini 2.5 Flash | DeepInfra | 0.300 | 2.50 | compare | 1.0M | 1.0M | 21.1 | 17.8 | |
| Databricks Gemini 2 5 Flash | Databricks | 0.300 | 2.50 | compare | 1.0M | 66K | 21.1 | 17.8 | |
| Minimax M1 80K | Novita AI | 0.550 | 2.20 | compare | 1.0M | 40K | 20.9 | 14.1 | |
| Minimax M1 80K | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | 20.9 | 14.1 | |
| o1 mini | Replicate | 1.10 | 4.40 | compare | N/A | N/A | 20.4 | N/A | |
| o1 mini | OpenAI | 1.10 | 4.40 | compare | 128K | 66K | 20.4 | N/A | |
| o1 mini | Azure OpenAI | 1.21 | 4.84 | compare | 128K | 66K | 20.4 | N/A | |
| Qwen3 Vl 30B A3b Instruct | Novita AI | 0.200 | 0.700 | compare | 131K | 33K | 20.0 | 14.3 | |
| GPT-4.5 Preview | OpenAI | 75.00 | 150.00 | compare | 128K | 16K | 20.0 | N/A | |
| Qwen3 Vl 30B A3b Instruct | Fireworks AI | 0.150 | 0.600 | compare | 262K | 262K | 20.0 | 14.3 | |
| Grok 4 1 Fast Non Reasoning | xAI | 0.200 | 0.500 | compare | 2.0M | 2.0M | 19.9 | 19.5 | |
| QwQ 32B | SambaNova | 0.500 | 1.00 | compare | 16K | 16K | 19.7 | N/A | |
| QwQ 32B |  Nscale | 0.180 | 0.200 | compare | N/A | N/A | 19.7 | N/A | |
| QwQ 32B | Hyperbolic | 0.200 | 0.200 | compare | 131K | 131K | 19.7 | N/A | |
| Qwen Qwq 32B Preview | Fireworks AI | 0.900 | 0.900 | compare | 33K | 33K | 19.7 | N/A | |
| QwQ 32B | DeepInfra | 0.150 | 0.400 | compare | 131K | 131K | 19.7 | N/A | |
| Qwen3 30B A3b Instruct 2507 | Fireworks AI | 0.500 | 0.500 | compare | 262K | 262K | 19.3 | 14.2 | |
| Qwen3 30B A3b Thinking 2507 | Fireworks AI | 0.900 | 0.900 | compare | 262K | 262K | 19.1 | 11.0 | |
| Devstral | Mistral AI | 0.400 | 2.00 | compare | 256K | 256K | 19.0 | 23.7 | |
| Olmo 3 32B Think |  Public AI | N/A | N/A | compare | 33K | 4K | 18.9 | 10.5 | |
| Nvidia.nemotron Nano 9B V2 | AWS Bedrock | 0.060 | 0.230 | compare | 128K | 8K | 18.8 | 7.5 | |
| Nvidia Nemotron Nano 9B V2 | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | 18.8 | 7.5 | |
| NVIDIA Nemotron Nano 9B V2 | DeepInfra | 0.040 | 0.160 | compare | 131K | 131K | 18.8 | 7.5 | |
| Nova 2 Lite V1 | AWS Bedrock | 0.300 | 2.50 | compare | 1.0M | 64K | 18.6 | 12.5 | |
| Llama 4 Maverick | Vercel AI Gateway | 0.200 | 0.600 | compare | 131K | 8K | 18.4 | 15.6 | |
| Sonar Reasoning | Vercel AI Gateway | 1.00 | 5.00 | compare | 127K | 8K | 17.9 | N/A | |
| Sonar Reasoning |  Perplexity | 1.00 | 5.00 | compare | 128K | N/A | 17.9 | N/A | |
| Mistral Medium 3 |  Vertex AI (Mistral) | 0.400 | 2.00 | compare | 128K | 8K | 17.6 | 13.6 | |
| Gemini 2.0 Flash | Vercel AI Gateway | 0.150 | 0.600 | compare | 1.0M | 8K | 17.6 | 13.6 | |
| Gemini 2.0 Flash-001 | OpenRouter | 0.100 | 0.400 | compare | 1.0M | 8K | 17.6 | 13.6 | |
| Gemini 2.0 Flash-exp | Google Gemini | N/A | N/A | compare | 1.0M | 8K | 17.6 | 13.6 | |
| Gemini 2.0 Flash-exp | Google Vertex AI | 0.150 | 0.600 | compare | 1.0M | 8K | 17.6 | 13.6 | |
| Gemini 2.0 Flash-001 | DeepInfra | 0.100 | 0.400 | compare | 1.0M | 1.0M | 17.6 | 13.6 | |
| Qwen3 Coder 30B A3b V1 | AWS Bedrock | 0.150 | 0.600 | compare | 262K | 131K | 17.5 | 19.4 | |
| Qwen3 Coder 30B A3b Instruct | Novita AI | 0.070 | 0.270 | compare | 160K | 33K | 17.5 | 19.4 | |
| Qwen3 Coder 30B A3B Instruct GGUF | Lemonade (AMD) | N/A | N/A | compare | 262K | 33K | 17.5 | 19.4 | |
| Qwen3 Coder 30B A3b Instruct | Fireworks AI | 0.150 | 0.600 | compare | 262K | 262K | 17.5 | 19.4 | |
| Magistral Medium | Vercel AI Gateway | 2.00 | 5.00 | compare | 128K | 64K | 17.4 | 16.0 | |
| Magistral Medium | Mistral AI | 2.00 | 5.00 | compare | 40K | 40K | 17.4 | 16.0 | |
| ERNIE 4.5 300B A47b Paddle | Novita AI | 0.280 | 1.10 | compare | 123K | 12K | 17.3 | 14.5 | |
| ERNIE 4p5 300B A47b Pt | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | 17.3 | 14.5 | |
| DeepSeek R1 Distill Qwen 32B | Nscale | 0.150 | 0.150 | compare | N/A | N/A | 17.2 | N/A | |
| DeepSeek R1 Distill Qwen 32B | Novita AI | 0.300 | 0.300 | compare | 64K | 32K | 17.2 | N/A | |
| DeepSeek R1 Distill Qwen 32B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 17.2 | N/A | |
| DeepSeek R1 Distill Qwen 32B | DeepInfra | 0.270 | 0.270 | compare | 131K | 131K | 17.2 | N/A | |
| DeepSeek V3 | Vercel AI Gateway | 0.900 | 0.900 | compare | 128K | 8K | 17.1 | 16.4 | |
| DeepSeek V3 | Together AI | 1.25 | 1.25 | compare | 66K | 8K | 17.1 | 16.4 | |
| DeepSeek V3 0324 | SambaNova | 3.00 | 4.50 | compare | 33K | 33K | 17.1 | 16.4 | |
| DeepSeek V3 | Replicate | 1.45 | 1.45 | compare | 66K | 8K | 17.1 | 16.4 | |
| DeepSeek V3 Turbo | Novita AI | 0.400 | 1.30 | compare | 64K | 16K | 17.1 | 16.4 | |
| Hermes3 405B | Lambda | 0.800 | 0.800 | compare | 131K | 131K | 17.1 | 18.1 | |
| DeepSeek V3 | Hyperbolic | 0.200 | 0.200 | compare | 33K | 33K | 17.1 | 16.4 | |
| DeepSeek V3 | Fireworks AI | 0.900 | 0.900 | compare | 128K | 8K | 17.1 | 16.4 | |
| DeepSeek V3 | DeepSeek | 0.270 | 1.10 | compare | 66K | 8K | 17.1 | 16.4 | |
| V3 V1 | AWS Bedrock | 0.580 | 1.68 | compare | 164K | 82K | 17.1 | 16.4 | |
| Hermes 3 Llama 3.1 405B | DeepInfra | 1.00 | 1.00 | compare | 131K | 131K | 17.1 | 18.1 | |
| DeepSeek V3 | DeepInfra | 0.380 | 0.890 | compare | 164K | 164K | 17.1 | 16.4 | |
| DeepSeek V3 | Azure AI | 1.14 | 4.56 | compare | 128K | 8K | 17.1 | 16.4 | |
| Us.amazon.nova Premier V1 | AWS Bedrock | 2.50 | 12.50 | compare | 1.0M | 10K | 17.0 | 13.8 | |
| Nova Premier V1 |  Amazon Nova | 2.50 | 12.50 | compare | 1.0M | 10K | 17.0 | 13.8 | |
| Magistral Small | Vercel AI Gateway | 0.500 | 1.50 | compare | 128K | 64K | 16.8 | 11.1 | |
| Olmo 3 7B Think | Public AI | N/A | N/A | compare | 33K | 4K | 16.8 | 7.6 | |
| Magistral Small | Mistral AI | 0.500 | 1.50 | compare | 40K | 40K | 16.8 | 11.1 | |
| Qwen3 Vl 8B Instruct | Novita AI | 0.080 | 0.500 | compare | 131K | 33K | 16.7 | 9.8 | |
| DeepSeek R1 0528 Distill Qwen3 8B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | 16.4 | 7.8 | |
| Qwen Max | DashScope (Alibaba) | 1.60 | 6.40 | compare | 31K | 8K | 16.3 | N/A | |
| Ministral 14B 2512 | OpenRouter | 0.200 | 0.200 | compare | 262K | 262K | 16.2 | 10.9 | |
| Ministral 3 14B Instruct | AWS Bedrock | 0.200 | 0.200 | compare | 128K | 8K | 16.2 | 10.9 | |
| Glm 4.6v | Novita AI | 0.300 | 0.900 | compare | 131K | 33K | 16.1 | 11.1 | |
| Qwen3 4B Instruct 2507 GGUF | Lemonade (AMD) | N/A | N/A | compare | 262K | 33K | 16.1 | 9.1 | |
| Qwen3 4B Instruct 2507 | Fireworks AI | 0.200 | 0.200 | compare | 262K | 262K | 16.1 | 9.1 | |
| DeepSeek R1 Distill Llama 70B | Vercel AI Gateway | 0.750 | 0.990 | compare | 131K | 131K | 16.0 | 11.4 | |
| Qwen 3 235B | Vercel AI Gateway | 0.200 | 0.600 | compare | 41K | 16K | 16.0 | 14.0 | |
| Qwen3 235B A22B Fp8 Tput | Together AI | 0.200 | 0.600 | compare | 40K | N/A | 16.0 | 14.0 | |
| DeepSeek R1 Distill Llama 70B | SambaNova | 0.700 | 1.40 | compare | 131K | 131K | 16.0 | 11.4 | |
| Qwen3 235B A22b Instruct 2507 | Replicate | 0.264 | 1.06 | compare | N/A | N/A | 16.0 | 14.0 | |
| DeepSeek R1 Distill Llama 70B | OVHcloud | 0.670 | 0.670 | compare | 131K | 131K | 16.0 | 11.4 | |
| DeepSeek R1 Distill Llama 70B | Nscale | 0.375 | 0.375 | compare | N/A | N/A | 16.0 | 11.4 | |
| Qwen3 235B A22b Fp8 | Novita AI | 0.200 | 0.800 | compare | 41K | 20K | 16.0 | 14.0 | |
| DeepSeek R1 Distill Llama 70B | Novita AI | 0.800 | 0.800 | compare | 8K | 8K | 16.0 | 11.4 | |
| Qwen3 235B A22B | Hyperbolic | 2.00 | 2.00 | compare | 131K | 131K | 16.0 | 14.0 | |
| DeepSeek R1 Distill Llama 70B | Gradient AI | 0.990 | 0.990 | compare | 8K | N/A | 16.0 | 11.4 | |
| Qwen3 VL 235B A22B Instruct FP8 | GMI Cloud | 0.300 | 1.40 | compare | 262K | 16K | 16.0 | 14.0 | |
| Gemini 1.5 Pro | Google Gemini | 3.50 | 1.05 | compare | 1.0M | 8K | 16.0 | 23.6 | |
| Gemini flash-lite | Google Gemini | 0.100 | 0.400 | compare | 1.0M | 66K | 16.0 | 7.4 | |
| Gemini 2.5 Flash-Lite | Google Vertex AI | 0.100 | 0.400 | compare | 1.0M | 66K | 16.0 | 7.4 | |
| Gemini 1.5 Pro | Google Vertex AI | 1.25 | 5.00 | compare | 2.1M | 8K | 16.0 | 23.6 | |
| Qwen3 235B A22b | Fireworks AI | 0.220 | 0.880 | compare | 131K | 131K | 16.0 | 14.0 | |
| DeepSeek R1 Distill Llama 70B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 16.0 | 11.4 | |
| Qwen3 235B A22B | DeepInfra | 0.180 | 0.540 | compare | 41K | 41K | 16.0 | 14.0 | |
| DeepSeek R1 Distill Llama 70B | DeepInfra | 0.200 | 0.600 | compare | 131K | 131K | 16.0 | 11.4 | |
| Claude 3 5 Sonnet | Anthropic (Vertex AI) | 3.00 | 15.00 | compare | 200K | 8K | 15.9 | 30.2 | |
| Claude 3 5 Sonnet | Vercel AI Gateway | 3.00 | 15.00 | compare | 200K | 8K | 15.9 | 30.2 | |
| Claude 3 5 Sonnet | Snowflake | N/A | N/A | compare | 18K | 8K | 15.9 | 30.2 | |
| Claude 3.5 Sonnet | Replicate | 3.75 | 18.75 | compare | N/A | N/A | 15.9 | 30.2 | |
| Claude 3.5 Sonnet | OpenRouter | 3.00 | 15.00 | compare | 200K | 8K | 15.9 | 30.2 | |
| Claude 3 5 Sonnet | Heroku (Salesforce) | N/A | N/A | compare | 8K | N/A | 15.9 | 30.2 | |
| Anthropic Claude 3.5 Sonnet | Gradient AI | 3.00 | 15.00 | compare | 1K | N/A | 15.9 | 30.2 | |
| Claude 3 5 Sonnet | Anthropic | 3.00 | 15.00 | compare | 200K | 8K | 15.9 | 30.2 | |
| Claude 3 5 Sonnet 20240620 V1 | AWS Bedrock | 3.00 | 15.00 | compare | 1.0M | 4K | 15.9 | 30.2 | |
| DeepSeek R1 Distill Qwen 14B | Nscale | 0.070 | 0.070 | compare | N/A | N/A | 15.8 | N/A | |
| DeepSeek R1 Distill Qwen 14B | Novita AI | 0.150 | 0.150 | compare | 33K | 16K | 15.8 | N/A | |
| DeepSeek R1 Distill Qwen 14B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | 15.8 | N/A | |
| Qwen2.5 72B Instruct Turbo | Together AI | N/A | N/A | compare | N/A | N/A | 15.6 | 11.9 | |
| Qwen 2.5 72B Instruct | Novita AI | 0.380 | 0.400 | compare | 32K | 8K | 15.6 | 11.9 | |
| Qwen2.5 72B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 131K | 131K | 15.6 | 11.9 | |
| Qwen2p5 72B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 15.6 | 11.9 | |
| Qwen2.5 72B Instruct | DeepInfra | 0.120 | 0.390 | compare | 33K | 33K | 15.6 | 11.9 | |
| Sonar | Vercel AI Gateway | 1.00 | 1.00 | compare | 127K | 8K | 15.5 | N/A | |
| Sonar | Perplexity | 1.00 | 1.00 | compare | 128K | N/A | 15.5 | N/A | |
| Ministral 8B 2512 | OpenRouter | 0.150 | 0.150 | compare | 262K | 262K | 15.3 | 10.0 | |
| Ministral 3 8B Instruct | AWS Bedrock | 0.150 | 0.150 | compare | 128K | 8K | 15.3 | 10.0 | |
| Llama 3.1 405B Instruct Maas |  Vertex AI (Llama) | 5.00 | 16.00 | compare | 128K | 2K | 15.2 | 14.5 | |
| Sonar Reasoning Pro | Vercel AI Gateway | 2.00 | 8.00 | compare | 127K | 8K | 15.2 | N/A | |
| Meta Llama 3.1 405B Instruct Turbo | Together AI | 3.50 | 3.50 | compare | N/A | N/A | 15.2 | 14.5 | |
| Llama3.1 405B | Snowflake | N/A | N/A | compare | 128K | 8K | 15.2 | 14.5 | |
| Meta Llama 3.1 405B Instruct | SambaNova | 5.00 | 10.00 | compare | 16K | 16K | 15.2 | 14.5 | |
| Sonar Reasoning Pro | Perplexity | 2.00 | 8.00 | compare | 128K | N/A | 15.2 | N/A | |
| Llama 3.1 405B Instruct | Oracle Cloud (OCI) | 10.68 | 10.68 | compare | 128K | 4K | 15.2 | 14.5 | |
| Llama3 1 405B Instruct V1 | AWS Bedrock | 5.32 | 16.00 | compare | 128K | 4K | 15.2 | 14.5 | |
| Llama3.1 405B Instruct Fp8 | Lambda | 0.800 | 0.800 | compare | 131K | 131K | 15.2 | 14.5 | |
| Meta Llama 3.1 405B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 33K | 33K | 15.2 | 14.5 | |
| Llama V3p1 405B Instruct | Fireworks AI | 3.00 | 3.00 | compare | 128K | 16K | 15.2 | 14.5 | |
| Databricks Meta Llama 3 1 405B Instruct | Databricks | 5.00 | 15.00 | compare | 128K | 128K | 15.2 | 14.5 | |
| Meta Llama 3.1 405B Instruct | Azure AI | 5.33 | 16.00 | compare | 128K | 2K | 15.2 | 14.5 | |
| Mistral Small 3.2 24B Instruct 2506 | OVHcloud | 0.090 | 0.280 | compare | 128K | 128K | 15.1 | 13.3 | |
| Mistral Small 3.2 24B Instruct | OpenRouter | 0.100 | 0.300 | compare | 32K | N/A | 15.1 | 13.3 | |
| Devstral Medium | Mistral AI | 0.400 | 2.00 | compare | 256K | 256K | 15.1 | 15.9 | |
| Mistral Small 3.2 24B Instruct 2506 | DeepInfra | 0.075 | 0.200 | compare | 128K | 128K | 15.1 | 13.3 | |
| GPT-4.1 nano | Vercel AI Gateway | 0.100 | 0.400 | compare | 1.0M | 33K | 14.9 | 11.2 | |
| GPT-4.1 nano | Replicate | 0.100 | 0.400 | compare | N/A | N/A | 14.9 | 11.2 | |
| GPT-4.1 nano | OpenRouter | 0.100 | 0.400 | compare | 1.0M | 33K | 14.9 | 11.2 | |
| GPT-4.1 nano | OpenAI | 0.100 | 0.400 | compare | 1.0M | 33K | 14.9 | 11.2 | |
| GPT-4.1 nano | Azure OpenAI | 0.110 | 0.440 | compare | 1.0M | 33K | 14.9 | 11.2 | |
| GPT-4o | Vercel AI Gateway | 2.50 | 10.00 | compare | 128K | 16K | 14.8 | 16.7 | |
| Devstral Small | Vercel AI Gateway | 0.070 | 0.280 | compare | 128K | 128K | 14.8 | 12.1 | |
| GPT-4o | Replicate | 2.50 | 10.00 | compare | N/A | N/A | 14.8 | 16.7 | |
| GPT-4o | OpenRouter | 2.50 | 10.00 | compare | 128K | 4K | 14.8 | 16.7 | |
| Devstral Small | Mistral AI | 0.100 | 0.300 | compare | 256K | 256K | 14.8 | 12.1 | |
| Qwen3 Vl 8B | LlamaGate | 0.150 | 0.550 | compare | 33K | 8K | 14.8 | 7.3 | |
| Openai GPT 4o | Gradient AI | N/A | N/A | compare | 16K | N/A | 14.8 | 16.7 | |
| GPT-4o | GMI Cloud | 2.50 | 10.00 | compare | 131K | 16K | 14.8 | 16.7 | |
| GPT-4-o Preview | GitHub Copilot | N/A | N/A | compare | 64K | 4K | 14.8 | 16.7 | |
| Qwen3 Vl 8B Instruct | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | 14.8 | 7.3 | |
| Chatgpt 4o | OpenAI | 5.00 | 15.00 | compare | 128K | 4K | 14.8 | 16.7 | |
| GPT-4o | Azure OpenAI | 2.50 | 10.00 | compare | 128K | 16K | 14.8 | 16.7 | |
| Gemini 2.0 Flash-Lite | Vercel AI Gateway | 0.075 | 0.300 | compare | 1.0M | 8K | 14.7 | N/A | |
| Command A | Vercel AI Gateway | 2.50 | 10.00 | compare | 256K | 8K | 14.7 | 9.9 | |
| Mistral Large2 | Snowflake | N/A | N/A | compare | 128K | 8K | 14.7 | 13.8 | |
| Gemini 2.0 Flash-Lite | Google Gemini | 0.075 | 0.300 | compare | 1.0M | 8K | 14.7 | N/A | |
| Gemini 2.0 Flash-Lite | Google Vertex AI | 0.075 | 0.300 | compare | 1.0M | 8K | 14.7 | N/A | |
| Qwen 3 30B | Vercel AI Gateway | 0.100 | 0.300 | compare | 41K | 16K | 14.6 | 13.3 | |
| Qwen3 30B A3b Fp8 | Novita AI | 0.090 | 0.450 | compare | 41K | 20K | 14.6 | 13.3 | |
| Qwen3 30B A3b | Fireworks AI | 0.150 | 0.600 | compare | 131K | 131K | 14.6 | 13.3 | |
| Qwen3 30B A3B | DeepInfra | 0.080 | 0.290 | compare | 41K | 41K | 14.6 | 13.3 | |
| Llama 3.3 Nemotron Super 49B V1.5 | DeepInfra | 0.100 | 0.400 | compare | 131K | 131K | 14.6 | 10.5 | |
| Qwen3 30B A3b | DashScope (Alibaba) | N/A | N/A | compare | 129K | 16K | 14.6 | 13.3 | |
| Llama 3 3 70B Instruct | IBM watsonx | 0.710 | 0.710 | compare | 128K | 128K | 14.5 | 10.7 | |
| Llama 3.3 70B Instruct | Weights & Biases | 0.071 | 0.071 | compare | 128K | 128K | 14.5 | 10.7 | |
| Llama 3.3 70B | Vercel AI Gateway | 0.720 | 0.720 | compare | 128K | 8K | 14.5 | 10.7 | |
| Qwen 3 32B | Vercel AI Gateway | 0.100 | 0.300 | compare | 41K | 16K | 14.5 | N/A | |
| Llama 3.3 70B Instruct Turbo | Together AI | 0.880 | 0.880 | compare | N/A | N/A | 14.5 | 10.7 | |
| Llama3.3 70B | Snowflake | N/A | N/A | compare | 128K | 8K | 14.5 | 10.7 | |
| Qwen3 32B | SambaNova | 0.400 | 0.800 | compare | 8K | 8K | 14.5 | N/A | |
| Meta Llama 3.3 70B Instruct | SambaNova | 0.600 | 1.20 | compare | 131K | 131K | 14.5 | 10.7 | |
| Qwen3 32B V1 | AWS Bedrock | 0.150 | 0.600 | compare | 131K | 16K | 14.5 | N/A | |
| Qwen3 32B | OVHcloud | 0.080 | 0.230 | compare | 32K | 32K | 14.5 | N/A | |
| Meta Llama 3 3 70B Instruct | OVHcloud | 0.670 | 0.670 | compare | 131K | 131K | 14.5 | 10.7 | |
| Llama 3.3 70B Instruct | Oracle Cloud (OCI) | 0.720 | 0.720 | compare | 128K | 4K | 14.5 | 10.7 | |
| Llama 3.3 70B Instruct | Nscale | 0.200 | 0.200 | compare | N/A | N/A | 14.5 | 10.7 | |
| Qwen3 32B Fp8 | Novita AI | 0.100 | 0.450 | compare | 41K | 20K | 14.5 | N/A | |
| Llama 3.3 70B Instruct | Novita AI | 0.135 | 0.400 | compare | 131K | 120K | 14.5 | 10.7 | |
| Llama3 3 70B Instruct V1 | AWS Bedrock | 0.720 | 0.720 | compare | 128K | 4K | 14.5 | 10.7 | |
| Llama 3.3 70B Instruct |  Meta Llama | N/A | N/A | compare | 128K | 4K | 14.5 | 10.7 | |
| Qwen3 32B Fp8 | Lambda | 0.050 | 0.100 | compare | 131K | 131K | 14.5 | N/A | |
| DeepSeek Llama3.3 70B | Lambda | 0.200 | 0.600 | compare | 131K | 131K | 14.5 | 10.7 | |
| Llama 3.3 70B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 131K | 131K | 14.5 | 10.7 | |
| Qwen3 32B | Groq | 0.290 | 0.590 | compare | 131K | 131K | 14.5 | N/A | |
| Llama 3.3 70B Versatile | Groq | 0.590 | 0.790 | compare | 128K | 33K | 14.5 | 10.7 | |
| Llama3.3 70B Instruct | Gradient AI | 0.650 | 0.650 | compare | 2K | N/A | 14.5 | 10.7 | |
| Alibaba Qwen3 32B | Gradient AI | N/A | N/A | compare | 2K | N/A | 14.5 | N/A | |
| Qwen3 32B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 14.5 | N/A | |
| Llama V3p3 70B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 14.5 | 10.7 | |
| Qwen3 32B | DeepInfra | 0.100 | 0.280 | compare | 41K | 41K | 14.5 | N/A | |
| Llama 3.3 70B Instruct | DeepInfra | 0.230 | 0.400 | compare | 131K | 131K | 14.5 | 10.7 | |
| Databricks Meta Llama 3 3 70B Instruct | Databricks | 0.500 | 1.50 | compare | 128K | 128K | 14.5 | 10.7 | |
| Qwen 3 32B | Cerebras | 0.400 | 0.800 | compare | 128K | 128K | 14.5 | N/A | |
| Llama 3.3 70B | Cerebras | 0.850 | 1.20 | compare | 128K | 128K | 14.5 | 10.7 | |
| Llama 3.3 70B Instruct | Azure AI | 0.710 | 0.710 | compare | 128K | 2K | 14.5 | 10.7 | |
| Glm 4.5v | Z AI (Zhipu) | 0.600 | 1.80 | compare | 128K | 32K | 14.4 | 10.8 | |
| Glm 4.5v | Novita AI | 0.600 | 1.80 | compare | 66K | 16K | 14.4 | 10.8 | |
| Glm 4p5v | Fireworks AI | 1.20 | 1.20 | compare | 131K | 131K | 14.4 | 10.8 | |
| Nvidia.nemotron Nano 3 30B | AWS Bedrock | 0.060 | 0.240 | compare | 262K | 8K | 14.2 | 15.8 | |
| Nvidia.nemotron Nano 12B V2 | AWS Bedrock | 0.200 | 0.600 | compare | 128K | 8K | 14.2 | 5.9 | |
| Nemotron Nano V2 12B Vl | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | 14.2 | 5.9 | |
| Mistral Small 3 1 24B Instruct 2503 | IBM watsonx | 0.100 | 0.300 | compare | 32K | 32K | 14.0 | 13.9 | |
| Nova Pro | Vercel AI Gateway | 0.800 | 3.20 | compare | 300K | 8K | 14.0 | 11.0 | |
| Mistral Small 3.1 24B Instruct | OpenRouter | 0.100 | 0.300 | compare | 32K | N/A | 14.0 | 13.9 | |
| Pixtral Large 2411 | Mistral AI | 2.00 | 6.00 | compare | 128K | 128K | 14.0 | N/A | |
| Nova Pro V1 | AWS Bedrock | 0.800 | 3.20 | compare | 300K | 10K | 14.0 | 11.0 | |
| Nova Pro V1 | Amazon Nova | 0.800 | 3.20 | compare | 300K | 10K | 14.0 | 11.0 | |
| Grok 2 1212 | xAI | 2.00 | 10.00 | compare | 131K | 131K | 13.9 | N/A | |
| Gemini 1.5 Flash | Google Gemini | 0.075 | 0.300 | compare | 1.0M | 8K | 13.8 | N/A | |
| Gemini 1.5 Flash | Google Vertex AI | 0.075 | 0.300 | compare | 1.0M | 8K | 13.8 | N/A | |
| Llama 4 Scout | Vercel AI Gateway | 0.100 | 0.300 | compare | 131K | 8K | 13.5 | 6.7 | |
| Llama3.1 Nemotron 70B Instruct Fp8 | Lambda | 0.120 | 0.300 | compare | 131K | 131K | 13.5 | 10.8 | |
| Llama V3p1 Nemotron 70B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 13.5 | 10.8 | |
| Llama 3.1 Nemotron 70B Instruct | DeepInfra | 0.600 | 0.600 | compare | 131K | 131K | 13.5 | 10.8 | |
| Grok Beta | xAI | 5.00 | 15.00 | compare | 131K | 131K | 13.3 | N/A | |
| Granite 4 H Small | IBM watsonx | 0.060 | 0.250 | compare | 20K | 20K | 13.2 | 8.5 | |
| Qwen3 8B Fp8 | Novita AI | 0.035 | 0.138 | compare | 128K | 20K | 13.2 | 7.1 | |
| Qwen3 8B | LlamaGate | 0.040 | 0.140 | compare | 33K | 8K | 13.2 | 7.1 | |
| Qwen3 8B | Fireworks AI | 0.200 | 0.200 | compare | 41K | 41K | 13.2 | 7.1 | |
| Qwen2p5 32B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 13.2 | N/A | |
| Phi 4 | DeepInfra | 0.070 | 0.140 | compare | 16K | 16K | 13.2 | 11.2 | |
| Phi 4 | Azure AI | 0.125 | 0.500 | compare | 16K | 16K | 13.2 | 11.2 | |
| Llama 3.1 70B Instruct Maas | Vertex AI (Llama) | N/A | N/A | compare | 128K | 2K | 13.1 | 10.9 | |
| Llama 3.1 70B | Vercel AI Gateway | 0.720 | 0.720 | compare | 128K | 8K | 13.1 | 10.9 | |
| Meta Llama 3.1 70B Instruct Turbo | Together AI | 0.880 | 0.880 | compare | N/A | N/A | 13.1 | 10.9 | |
| Llama3.1 70B | Snowflake | N/A | N/A | compare | 128K | 8K | 13.1 | 10.9 | |
| Llama 3.1 70B Instruct | Perplexity | 1.00 | 1.00 | compare | 131K | 131K | 13.1 | 10.9 | |
| Meta Llama 3 1 70B Instruct | OVHcloud | 0.670 | 0.670 | compare | 131K | 131K | 13.1 | 10.9 | |
| Llama3 1 70B Instruct V1 | AWS Bedrock | 0.990 | 0.990 | compare | 128K | 2K | 13.1 | 10.9 | |
| Llama3.1 70B Instruct Fp8 | Lambda | 0.120 | 0.300 | compare | 131K | 131K | 13.1 | 10.9 | |
| Meta Llama 3.1 70B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 33K | 33K | 13.1 | 10.9 | |
| Meta Llama 3.1 70B Instruct |  FriendliAI | 0.600 | 0.600 | compare | 8K | 8K | 13.1 | 10.9 | |
| Qwen3 1p7b Fp8 Draft | Fireworks AI | 0.100 | 0.100 | compare | 262K | 262K | 13.1 | 1.4 | |
| Llama V3p1 70B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 13.1 | 10.9 | |
| Meta Llama 3.1 70B Instruct | DeepInfra | 0.400 | 0.400 | compare | 131K | 131K | 13.1 | 10.9 | |
| Llama3.1 70B | Cerebras | 0.600 | 0.600 | compare | 128K | 128K | 13.1 | 10.9 | |
| Meta Llama 3.1 70B Instruct | Azure AI | 2.68 | 3.54 | compare | 128K | 2K | 13.1 | 10.9 | |
| Mistral Large | Vertex AI (Mistral) | 2.00 | 6.00 | compare | 128K | 8K | 13.0 | N/A | |
| Olmo 3 7B Instruct | Public AI | N/A | N/A | compare | 33K | 4K | 13.0 | 3.4 | |
| Mistral Large Instruct 2407 | Ollama | N/A | N/A | compare | 66K | 8K | 13.0 | N/A | |
| Mistral Large 2407 | Mistral AI | 3.00 | 9.00 | compare | 128K | 128K | 13.0 | N/A | |
| Mistral Large 2407 V1 | AWS Bedrock | 3.00 | 9.00 | compare | 128K | 8K | 13.0 | N/A | |
| Mistral Large 2407 | Azure AI | 2.00 | 6.00 | compare | 128K | 4K | 13.0 | N/A | |
| Qwen2.5 Coder 32B Instruct | OVHcloud | 0.870 | 0.870 | compare | 32K | 32K | 12.9 | N/A | |
| Qwen 2.5 Coder 32B Instruct | OpenRouter | 0.180 | 0.180 | compare | 34K | 34K | 12.9 | N/A | |
| Ministral 3B 2512 | OpenRouter | 0.100 | 0.100 | compare | 131K | 131K | 12.9 | 4.8 | |
| Qwen2.5 Coder 32B Instruct | Nscale | 0.060 | 0.200 | compare | N/A | N/A | 12.9 | N/A | |
| Ministral 3 3B Instruct | AWS Bedrock | 0.100 | 0.100 | compare | 128K | 8K | 12.9 | 4.8 | |
| Qwen25 Coder 32B Instruct | Lambda | 0.050 | 0.100 | compare | 131K | 131K | 12.9 | N/A | |
| Qwen2.5 Coder 32B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 33K | 33K | 12.9 | N/A | |
| Qwen2p5 Coder 32B | Fireworks AI | 0.900 | 0.900 | compare | 33K | 33K | 12.9 | N/A | |
| GPT-4 Turbo | Vercel AI Gateway | 10.00 | 30.00 | compare | 128K | 4K | 12.8 | 13.1 | |
| Nova Lite | Vercel AI Gateway | 0.060 | 0.240 | compare | 300K | 8K | 12.8 | 5.1 | |
| GPT-4 | OpenRouter | 30.00 | 60.00 | compare | 8K | N/A | 12.8 | 13.1 | |
| GPT-4-32k | OpenAI | 60.00 | 120.00 | compare | 33K | 4K | 12.8 | 13.1 | |
| Nova Lite V1 | AWS Bedrock | 0.060 | 0.240 | compare | 300K | 10K | 12.8 | 5.1 | |
| Nova Lite V1 | Amazon Nova | 0.060 | 0.240 | compare | 300K | 10K | 12.8 | 5.1 | |
| GPT-4o mini | Vercel AI Gateway | 0.150 | 0.600 | compare | 128K | 16K | 12.6 | N/A | |
| GPT-4o mini | Replicate | 0.150 | 0.600 | compare | N/A | N/A | 12.6 | N/A | |
| Openai GPT 4o Mini | Gradient AI | N/A | N/A | compare | 16K | N/A | 12.6 | N/A | |
| GPT-4o mini | OpenAI | 0.150 | 0.600 | compare | 128K | 16K | 12.6 | N/A | |
| GPT-4o mini | GMI Cloud | 0.150 | 0.600 | compare | 131K | 16K | 12.6 | N/A | |
| GPT-4o mini | GitHub Copilot | N/A | N/A | compare | 64K | 4K | 12.6 | N/A | |
| GPT-4o mini | Azure OpenAI | 0.150 | 0.600 | compare | 128K | 16K | 12.6 | N/A | |
| Claude 3 Opus | Anthropic (Vertex AI) | 15.00 | 75.00 | compare | 200K | 4K | 12.5 | 19.5 | |
| Claude 3 Opus | Vercel AI Gateway | 15.00 | 75.00 | compare | 200K | 4K | 12.5 | 19.5 | |
| Qwen3 4B Fp8 | Novita AI | 0.030 | 0.030 | compare | 128K | 20K | 12.5 | N/A | |
| Jamba Large 1.7 |  AI21 Labs | 2.00 | 8.00 | compare | 256K | 256K | 12.5 | 7.8 | |
| Anthropic Claude 3 Opus | Gradient AI | 15.00 | 75.00 | compare | 1K | N/A | 12.5 | 19.5 | |
| Qwen3 4B | Fireworks AI | 0.200 | 0.200 | compare | 41K | 41K | 12.5 | N/A | |
| DeepSeek V2p5 | Fireworks AI | 1.20 | 1.20 | compare | 33K | 33K | 12.5 | N/A | |
| Claude 3 Opus | Anthropic | 15.00 | 75.00 | compare | 200K | 4K | 12.5 | 19.5 | |
| Claude 3 Opus 20240229 V1 | AWS Bedrock | 15.00 | 75.00 | compare | 200K | 4K | 12.5 | 19.5 | |
| Gemma 3 12B It | Novita AI | 0.050 | 0.100 | compare | 131K | 8K | 12.4 | 6.3 | |
| Gemma 3 12B It | AWS Bedrock | 0.090 | 0.290 | compare | 128K | 8K | 12.4 | 6.3 | |
| Gemma 3 12B It | DeepInfra | 0.050 | 0.100 | compare | 131K | 131K | 12.4 | 6.3 | |
| Databricks Gemma 3 12B | Databricks | 0.150 | 0.500 | compare | 128K | 32K | 12.4 | 6.3 | |
| Claude 3 5 Haiku | Anthropic (Vertex AI) | 1.00 | 5.00 | compare | 200K | 8K | 12.3 | 10.7 | |
| Claude 3.5 Haiku | Vercel AI Gateway | 0.800 | 4.00 | compare | 200K | 8K | 12.3 | 10.7 | |
| Claude 3.5 Haiku | Replicate | 1.00 | 5.00 | compare | N/A | N/A | 12.3 | 10.7 | |
| Claude 3 5 Haiku | Heroku (Salesforce) | N/A | N/A | compare | 4K | N/A | 12.3 | 10.7 | |
| Anthropic Claude 3.5 Haiku | Gradient AI | 0.800 | 4.00 | compare | 1K | N/A | 12.3 | 10.7 | |
| Gemini 2.0 Flash-thinking-exp | Google Gemini | N/A | N/A | compare | 1.0M | 66K | 12.3 | N/A | |
| Gemini 2.0 Flash-thinking-exp | Google Vertex AI | N/A | N/A | compare | 1.0M | 8K | 12.3 | N/A | |
| Eu.anthropic.claude 3 5 Haiku 20241022 V1 | AWS Bedrock | 0.250 | 1.25 | compare | 200K | 8K | 12.3 | 10.7 | |
| Claude 3 5 Haiku | Anthropic | 1.00 | 5.00 | compare | 200K | 8K | 12.3 | 10.7 | |
| Mistral Saba 24B | Vercel AI Gateway | 0.790 | 0.790 | compare | 33K | 33K | 12.1 | N/A | |
| DeepSeek R1 Distill Llama 8B | Nscale | 0.025 | 0.025 | compare | N/A | N/A | 12.1 | N/A | |
| Devstral Small 2505 | Mistral AI | 0.100 | 0.300 | compare | 128K | 128K | 12.1 | 12.2 | |
| Devstral Small 2505 | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 12.1 | 12.2 | |
| DeepSeek R1 Distill Llama 8B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | 12.1 | N/A | |
| Reka Flash | Snowflake | N/A | N/A | compare | 100K | 8K | 12.0 | N/A | |
| Qwen Turbo | DashScope (Alibaba) | 0.050 | 0.200 | compare | 1.0M | 16K | 12.0 | N/A | |
| Llama 3 2 90B Vision Instruct | IBM watsonx | 2.00 | 2.00 | compare | 128K | 128K | 11.9 | N/A | |
| Llama 3.2 90B Vision Instruct Maas | Vertex AI (Llama) | N/A | N/A | compare | 128K | 2K | 11.9 | N/A | |
| Llama 3.2 90B | Vercel AI Gateway | 0.720 | 0.720 | compare | 128K | 8K | 11.9 | N/A | |
| Llama 3.2 90B Vision Instruct | Oracle Cloud (OCI) | 2.00 | 2.00 | compare | 128K | 4K | 11.9 | N/A | |
| Llama3 2 90B Instruct V1 | AWS Bedrock | 2.00 | 2.00 | compare | 128K | 4K | 11.9 | N/A | |
| Llama V3p2 90B Vision Instruct | Fireworks AI | 0.900 | 0.900 | compare | 16K | 16K | 11.9 | N/A | |
| Llama 3.2 90B Vision Instruct | Azure AI | 2.04 | 2.04 | compare | 128K | 2K | 11.9 | N/A | |
| Nova Micro | Vercel AI Gateway | 0.035 | 0.140 | compare | 128K | 8K | 11.6 | 4.1 | |
| Nova Micro V1 | AWS Bedrock | 0.035 | 0.140 | compare | 128K | 10K | 11.6 | 4.1 | |
| Nova Micro V1 | Amazon Nova | 0.035 | 0.140 | compare | 128K | 10K | 11.6 | 4.1 | |
| Llama 3.1 8B Instruct | Weights & Biases | 0.022 | 0.022 | compare | 128K | 128K | 11.3 | 4.9 | |
| Llama 3.1 8B Instruct Maas | Vertex AI (Llama) | N/A | N/A | compare | 128K | 2K | 11.3 | 4.9 | |
| Llama 3.1 8B | Vercel AI Gateway | 0.050 | 0.080 | compare | 131K | 131K | 11.3 | 4.9 | |
| Meta Llama 3.1 8B Instruct Turbo | Together AI | 0.180 | 0.180 | compare | N/A | N/A | 11.3 | 4.9 | |
| Llama3.1 8B | Snowflake | N/A | N/A | compare | 128K | 8K | 11.3 | 4.9 | |
| Meta Llama 3.1 8B Instruct | SambaNova | 0.100 | 0.200 | compare | 16K | 16K | 11.3 | 4.9 | |
| Llama 3.1 8B Instruct | Perplexity | 0.200 | 0.200 | compare | 131K | 131K | 11.3 | 4.9 | |
| Llama 3.1 8B Instruct | OVHcloud | 0.100 | 0.100 | compare | 131K | 131K | 11.3 | 4.9 | |
| Llama3.1 | Ollama | N/A | N/A | compare | 8K | 8K | 11.3 | 4.9 | |
| Llama 3.1 8B Instruct | Nscale | 0.030 | 0.030 | compare | N/A | N/A | 11.3 | 4.9 | |
| Llama 3.1 8B Instruct | Novita AI | 0.020 | 0.050 | compare | 16K | 16K | 11.3 | 4.9 | |
| Llama3 1 8B Instruct V1 | AWS Bedrock | 0.220 | 0.220 | compare | 128K | 2K | 11.3 | 4.9 | |
| Llama 3.1 8B | LlamaGate | 0.030 | 0.050 | compare | 131K | 8K | 11.3 | 4.9 | |
| Llama3.1 8B Instruct | Lambda | 0.025 | 0.040 | compare | 131K | 131K | 11.3 | 4.9 | |
| Meta Llama 3.1 8B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 33K | 33K | 11.3 | 4.9 | |
| Llama 3.1 8B Instant | Groq | 0.050 | 0.080 | compare | 128K | 8K | 11.3 | 4.9 | |
| Meta Llama 3.1 8B Instruct | FriendliAI | 0.100 | 0.100 | compare | 8K | 8K | 11.3 | 4.9 | |
| Llama V3p1 8B Instruct | Fireworks AI | 0.100 | 0.100 | compare | 16K | 16K | 11.3 | 4.9 | |
| Meta Llama 3.1 8B Instruct | DeepInfra | 0.030 | 0.050 | compare | 131K | 131K | 11.3 | 4.9 | |
| Databricks Meta Llama 3 1 8B Instruct | Databricks | 0.150 | 0.450 | compare | 200K | 128K | 11.3 | 4.9 | |
| Llama3.1 8B | Cerebras | 0.100 | 0.100 | compare | 128K | 128K | 11.3 | 4.9 | |
| Meta Llama 3.1 8B Instruct | Azure AI | 0.300 | 0.610 | compare | 128K | 2K | 11.3 | 4.9 | |
| Llama 3 2 11B Vision Instruct | IBM watsonx | 0.350 | 0.350 | compare | 128K | 128K | 10.9 | 4.3 | |
| Phi 4 Mini Instruct | Weights & Biases | 0.0080 | 0.035 | compare | 128K | 128K | 10.9 | 3.6 | |
| Llama 3.2 11B | Vercel AI Gateway | 0.160 | 0.160 | compare | 128K | 8K | 10.9 | 4.3 | |
| Llama3 2 11B Instruct V1 | AWS Bedrock | 0.350 | 0.350 | compare | 128K | 4K | 10.9 | 4.3 | |
| Llama3.2 11B Vision Instruct | Lambda | 0.015 | 0.025 | compare | 131K | 131K | 10.9 | 4.3 | |
| Llama V3p2 11B Vision Instruct | Fireworks AI | 0.200 | 0.200 | compare | 16K | 16K | 10.9 | 4.3 | |
| Llama 3.2 11B Vision Instruct | DeepInfra | 0.049 | 0.049 | compare | 131K | 131K | 10.9 | 4.3 | |
| Phi 4 Mini Instruct | Azure AI | 0.075 | 0.300 | compare | 131K | 4K | 10.9 | 3.6 | |
| Llama 3.2 11B Vision Instruct | Azure AI | 0.370 | 0.370 | compare | 128K | 2K | 10.9 | 4.3 | |
| Granite 3 3 8B Instruct | IBM watsonx | 0.200 | 0.200 | compare | 8K | 8K | 10.8 | 3.4 | |
| Granite 3.3 8B Instruct | Replicate | 0.030 | 0.250 | compare | N/A | N/A | 10.8 | 3.4 | |
| Jamba 1.5 Large |  Vertex AI (AI21) | 2.00 | 8.00 | compare | 256K | 256K | 10.7 | N/A | |
| Jamba 1.5 Large | Snowflake | N/A | N/A | compare | 256K | 8K | 10.7 | N/A | |
| Gemma3 4B | LlamaGate | 0.030 | 0.080 | compare | 128K | 8K | 10.7 | 2.9 | |
| Gemma 3 4B It GGUF | Lemonade (AMD) | N/A | N/A | compare | 128K | 8K | 10.7 | 2.9 | |
| Jamba Mini 1.7 | AI21 Labs | 0.200 | 0.400 | compare | 256K | 256K | 10.7 | 3.1 | |
| Jamba 1.5 Large | AI21 Labs | 2.00 | 8.00 | compare | 256K | 256K | 10.7 | N/A | |
| Gemma 3 4B It | AWS Bedrock | 0.040 | 0.080 | compare | 128K | 8K | 10.7 | 2.9 | |
| Gemma 3 4B It | DeepInfra | 0.040 | 0.080 | compare | 131K | 131K | 10.7 | 2.9 | |
| Jamba 1 5 Large V1 | AWS Bedrock | 2.00 | 8.00 | compare | 256K | 256K | 10.7 | N/A | |
| DeepSeek Coder V2 Base | Ollama | N/A | N/A | compare | 8K | 8K | 10.6 | N/A | |
| Hermes3 70B | Lambda | 0.120 | 0.300 | compare | 131K | 131K | 10.6 | N/A | |
| Jamba Large 1.6 | AI21 Labs | 2.00 | 8.00 | compare | 256K | 256K | 10.6 | N/A | |
| Hermes 3 Llama 3.1 70B | Hyperbolic | 0.120 | 0.300 | compare | 33K | 33K | 10.6 | N/A | |
| Qwen3 1p7b | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | 10.6 | 2.3 | |
| DeepSeek Coder V2 Instruct | Fireworks AI | 1.20 | 1.20 | compare | 66K | 66K | 10.6 | N/A | |
| Hermes 3 Llama 3.1 70B | DeepInfra | 0.300 | 0.300 | compare | 131K | 131K | 10.6 | N/A | |
| Claude 3 Sonnet | Anthropic (Vertex AI) | 3.00 | 15.00 | compare | 200K | 4K | 10.3 | N/A | |
| Gemma 3 27B It | Novita AI | 0.119 | 0.200 | compare | 98K | 16K | 10.3 | 9.6 | |
| Gemma 3 27B It | AWS Bedrock | 0.230 | 0.380 | compare | 128K | 8K | 10.3 | 9.6 | |
| Gemma 3 27B It | Google Gemini | N/A | N/A | compare | 131K | 8K | 10.3 | 9.6 | |
| Gemma 3 27B It | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | 10.3 | 9.6 | |
| Gemma 3 27B It | DeepInfra | 0.090 | 0.160 | compare | 131K | 131K | 10.3 | 9.6 | |
| Claude 3 Sonnet 20240229 V1 | AWS Bedrock | 3.00 | 15.00 | compare | 200K | 4K | 10.3 | N/A | |
| Llama3 70B Instruct Maas | Vertex AI (Llama) | N/A | N/A | compare | 32K | 32K | 10.2 | 6.8 | |
| Mistral Small | Vercel AI Gateway | 0.100 | 0.300 | compare | 32K | 4K | 10.2 | N/A | |
| Llama 3 70B | Vercel AI Gateway | 0.590 | 0.790 | compare | 8K | 8K | 10.2 | 6.8 | |
| Llama3 70B | Snowflake | N/A | N/A | compare | 8K | 8K | 10.2 | 6.8 | |
| Llama 3 70B | Replicate | 0.650 | 2.75 | compare | 8K | 8K | 10.2 | 6.8 | |
| Llama 3 70B Instruct | OpenRouter | 0.590 | 0.790 | compare | 8K | N/A | 10.2 | 6.8 | |
| Llama3:70B | Ollama | N/A | N/A | compare | 8K | 8K | 10.2 | 6.8 | |
| Llama 3 70B Instruct | Novita AI | 0.510 | 0.740 | compare | 8K | 8K | 10.2 | 6.8 | |
| Mistral Small | Mistral AI | 0.100 | 0.300 | compare | 32K | 8K | 10.2 | N/A | |
| Meta Llama 3 70B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 131K | 131K | 10.2 | 6.8 | |
| Llama V3 70B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 8K | 8K | 10.2 | 6.8 | |
| Databricks Meta Llama 3 70B Instruct | Databricks | 1.00 | 3.00 | compare | 128K | 128K | 10.2 | 6.8 | |
| Llama3 70B Instruct V1 | AWS Bedrock | 2.65 | 3.50 | compare | 8K | 8K | 10.2 | 6.8 | |
| Mistral Small | Azure AI | 1.00 | 3.00 | compare | 32K | 8K | 10.2 | N/A | |
| Meta Llama 3 70B Instruct | Azure AI | 1.10 | 0.370 | compare | 8K | 2K | 10.2 | 6.8 | |
| Meta Llama 3 70B Instruct |  Anyscale | 1.00 | 1.00 | compare | 8K | 8K | 10.2 | 6.8 | |
| Gemini 1.0 Ultra | Google Vertex AI | 0.500 | 1.50 | compare | 8K | 2K | 10.1 | 17.6 | |
| Phi 3 Mini 128K Instruct | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | 10.1 | 3.0 | |
| Phi 3 Mini 128K Instruct | Azure AI | 0.130 | 0.520 | compare | 128K | 4K | 10.1 | 3.0 | |
| Qwen2.5 Coder 7B Instruct | Nscale | 0.010 | 0.030 | compare | N/A | N/A | 10.0 | N/A | |
| Qwen2.5 Coder 7B | LlamaGate | 0.060 | 0.120 | compare | 33K | 8K | 10.0 | N/A | |
| Qwen2p5 Coder 7B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | 10.0 | N/A | |
| Phi 4 Multimodal Instruct | Azure AI | 0.080 | 0.320 | compare | 131K | 4K | 10.0 | N/A | |
| Mistral Large | IBM watsonx | 3.00 | 10.00 | compare | 131K | 16K | 9.9 | N/A | |
| Mistral Large@latest | Vertex AI (Mistral) | 2.00 | 6.00 | compare | 128K | 8K | 9.9 | N/A | |
| Mistral Large | Vercel AI Gateway | 2.00 | 6.00 | compare | 32K | 4K | 9.9 | N/A | |
| Mistral Large | Snowflake | N/A | N/A | compare | 32K | 8K | 9.9 | N/A | |
| Mistral Large | OpenRouter | 8.00 | 24.00 | compare | 32K | N/A | 9.9 | N/A | |
| Mistral Large | Mistral AI | 2.00 | 6.00 | compare | 128K | 128K | 9.9 | N/A | |
| Mistral Large | Azure OpenAI | 8.00 | 24.00 | compare | 32K | N/A | 9.9 | N/A | |
| Mistral Large | Azure AI | 2.00 | 6.00 | compare | 128K | 4K | 9.9 | N/A | |
| Mixtral 8x22B Instruct | Vercel AI Gateway | 1.20 | 1.20 | compare | 66K | 2K | 9.8 | N/A | |
| Mixtral 8x22B Instruct | OpenRouter | 0.650 | 0.650 | compare | 66K | N/A | 9.8 | N/A | |
| Open Mixtral 8x22B | Mistral AI | 2.00 | 6.00 | compare | 65K | 8K | 9.8 | N/A | |
| Mixtral 8x22B | Fireworks AI | 1.20 | 1.20 | compare | 66K | 66K | 9.8 | N/A | |
| Llama 3 2 3B Instruct | IBM watsonx | 0.150 | 0.150 | compare | 128K | 128K | 9.7 | N/A | |
| Llama 3.2 3B | Vercel AI Gateway | 0.150 | 0.150 | compare | 128K | 8K | 9.7 | N/A | |
| Llama 3.2 3B Instruct Turbo | Together AI | N/A | N/A | compare | N/A | N/A | 9.7 | N/A | |
| Llama3.2 3B | Snowflake | N/A | N/A | compare | 128K | 8K | 9.7 | N/A | |
| Meta Llama 3.2 3B Instruct | SambaNova | 0.080 | 0.160 | compare | 4K | 4K | 9.7 | N/A | |
| Meta Textgeneration Llama 2 7B |  AWS SageMaker | N/A | N/A | compare | 4K | 4K | 9.7 | N/A | |
| Llama 2 7B | Replicate | 0.050 | 0.250 | compare | 4K | 4K | 9.7 | N/A | |
| Llama2:7B | Ollama | N/A | N/A | compare | 4K | 4K | 9.7 | N/A | |
| Llama 3.2 3B Instruct | Novita AI | 0.030 | 0.050 | compare | 33K | 32K | 9.7 | N/A | |
| Llama3 2 3B Instruct V1 | AWS Bedrock | 0.150 | 0.150 | compare | 128K | 4K | 9.7 | N/A | |
| Llama 3.2 3B | LlamaGate | 0.040 | 0.080 | compare | 131K | 8K | 9.7 | N/A | |
| Llama3.2 3B Instruct | Lambda | 0.015 | 0.025 | compare | 131K | 131K | 9.7 | N/A | |
| Llama 3.2 3B Instruct | Hyperbolic | 0.120 | 0.300 | compare | 33K | 33K | 9.7 | N/A | |
| Qwen3 0p6b | Fireworks AI | 0.100 | 0.100 | compare | 41K | 41K | 9.7 | 1.4 | |
| Llama V3p2 3B | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | 9.7 | N/A | |
| Llama V2 7B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | 9.7 | N/A | |
| Llama 3.2 3B Instruct | DeepInfra | 0.020 | 0.020 | compare | 131K | 131K | 9.7 | N/A | |
| Llama 2 7B Chat Fp16 |  Cloudflare Workers AI | 1.92 | 1.92 | compare | 3K | 3K | 9.7 | N/A | |
| Llama 2 7B Chat Hf | Anyscale | 0.150 | 0.150 | compare | 4K | 4K | 9.7 | N/A | |
| Claude 3 Haiku | Anthropic (Vertex AI) | 0.250 | 1.25 | compare | 200K | 4K | 9.3 | 6.7 | |
| Claude 3 Haiku | Vercel AI Gateway | 0.250 | 1.25 | compare | 200K | 4K | 9.3 | 6.7 | |
| Claude 3 Haiku | OpenRouter | 0.250 | 1.25 | compare | 200K | N/A | 9.3 | 6.7 | |
| Claude 3 Haiku | Anthropic | 0.250 | 1.25 | compare | 200K | 4K | 9.3 | 6.7 | |
| Claude V2 | AWS Bedrock | 8.00 | 24.00 | compare | 100K | 8K | 9.3 | 14.0 | |
| Claude 3 Haiku 20240307 V1 | AWS Bedrock | 0.250 | 1.25 | compare | 200K | 4K | 9.3 | 6.7 | |
| Llama 3 2 1B Instruct | IBM watsonx | 0.100 | 0.100 | compare | 128K | 128K | 9.1 | 0.6 | |
| Llama 3.2 1B | Vercel AI Gateway | 0.100 | 0.100 | compare | 128K | 8K | 9.1 | 0.6 | |
| Llama3.2 1B | Snowflake | N/A | N/A | compare | 128K | 8K | 9.1 | 0.6 | |
| Meta Llama 3.2 1B Instruct | SambaNova | 0.040 | 0.080 | compare | 16K | 16K | 9.1 | 0.6 | |
| DeepSeek R1 Distill Qwen 1.5B | Nscale | 0.090 | 0.090 | compare | N/A | N/A | 9.1 | N/A | |
| Llama3 2 1B Instruct V1 | AWS Bedrock | 0.100 | 0.100 | compare | 128K | 4K | 9.1 | 0.6 | |
| Llama V3p2 1B | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | 9.1 | 0.6 | |
| DeepSeek R1 Distill Qwen 1p5b | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | 9.1 | N/A | |
| GPT-3.5 Turbo | Vercel AI Gateway | 0.500 | 1.50 | compare | 16K | 4K | 9.0 | 10.7 | |
| GPT-3.5 Turbo | OpenRouter | 1.50 | 2.00 | compare | 4K | N/A | 9.0 | 10.7 | |
| Mistral Medium | Mistral AI | 0.400 | 2.00 | compare | 131K | 8K | 9.0 | N/A | |
| Mistral Small 2402 V1 | AWS Bedrock | 1.00 | 3.00 | compare | 32K | 8K | 9.0 | N/A | |
| GPT-3.5 Turbo | GitHub Copilot | N/A | N/A | compare | 16K | 4K | 9.0 | 10.7 | |
| Ft:gpt 3.5 Turbo | OpenAI | 3.00 | 6.00 | compare | 16K | 4K | 9.0 | 10.7 | |
| GPT-3.5-turbo-instruct-0914 |  Microsoft Azure | 1.50 | 2.00 | compare | 4K | N/A | 9.0 | 10.7 | |
| GPT-3.5 Turbo | Azure OpenAI | 0.500 | 1.50 | compare | 4K | 4K | 9.0 | 10.7 | |
| Snowflake Arctic | Snowflake | N/A | N/A | compare | 4K | 8K | 8.8 | N/A | |
| Lfm 40B | Lambda | 0.100 | 0.200 | compare | 131K | 131K | 8.8 | N/A | |
| Qwen2 72B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 33K | 33K | 8.8 | N/A | |
| Llama3 8B Instruct Maas | Vertex AI (Llama) | N/A | N/A | compare | 32K | 32K | 8.7 | 4.0 | |
| Llama 3 8B | Vercel AI Gateway | 0.050 | 0.080 | compare | 8K | 8K | 8.7 | 4.0 | |
| Llama3 8B | Snowflake | N/A | N/A | compare | 8K | 8K | 8.7 | 4.0 | |
| Llama 3 8B | Replicate | 0.050 | 0.250 | compare | 8K | 8K | 8.7 | 4.0 | |
| Llama3 | Ollama | N/A | N/A | compare | 8K | 8K | 8.7 | 4.0 | |
| Llama 3 8B Instruct | Novita AI | 0.040 | 0.040 | compare | 8K | 8K | 8.7 | 4.0 | |
| Llama3 8B Instruct | Gradient AI | 0.200 | 0.200 | compare | 512 | N/A | 8.7 | 4.0 | |
| Llama V3 8B | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | 8.7 | 4.0 | |
| Meta Llama 3 8B Instruct | DeepInfra | 0.030 | 0.060 | compare | 8K | 8K | 8.7 | 4.0 | |
| Llama3 8B Instruct V1 | AWS Bedrock | 0.300 | 0.600 | compare | 8K | 8K | 8.7 | 4.0 | |
| Meta Llama 3 8B Instruct | Anyscale | 0.150 | 0.150 | compare | 8K | 8K | 8.7 | 4.0 | |
| DeepSeek Coder V2 Lite Base | Ollama | N/A | N/A | compare | 8K | 8K | 8.5 | N/A | |
| Gemini pro | Google Gemini | 0.350 | 1.05 | compare | 33K | 8K | 8.5 | N/A | |
| Gemini 1.0 Pro | Google Vertex AI | 0.500 | 1.50 | compare | 33K | 8K | 8.5 | N/A | |
| DeepSeek Coder V2 Lite Base | Fireworks AI | 0.500 | 0.500 | compare | 164K | 164K | 8.5 | N/A | |
| Llama2 70B Chat | Snowflake | N/A | N/A | compare | 4K | 8K | 8.4 | N/A | |
| Meta Textgeneration Llama 2 70B | AWS SageMaker | N/A | N/A | compare | 4K | 4K | 8.4 | N/A | |
| Meta Textgeneration Llama 2 13B | AWS SageMaker | N/A | N/A | compare | 4K | 4K | 8.4 | N/A | |
| Llama 2 70B | Replicate | 0.650 | 2.75 | compare | 4K | 4K | 8.4 | N/A | |
| Llama 2 13B | Replicate | 0.100 | 0.500 | compare | 4K | 4K | 8.4 | N/A | |
| Llama 2 70B Chat | Perplexity | 0.700 | 2.80 | compare | 4K | 4K | 8.4 | N/A | |
| Llama2:70B | Ollama | N/A | N/A | compare | 4K | 4K | 8.4 | N/A | |
| Llama2:13B | Ollama | N/A | N/A | compare | 4K | 4K | 8.4 | N/A | |
| Llama2 70B Chat V1 | AWS Bedrock | 1.95 | 2.56 | compare | 4K | 4K | 8.4 | N/A | |
| Llama2 13B Chat V1 | AWS Bedrock | 0.750 | 1.00 | compare | 4K | 4K | 8.4 | N/A | |
| Llama V2 70B | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | 8.4 | N/A | |
| Llama V2 13B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | 8.4 | N/A | |
| Databricks Llama 2 70B Chat | Databricks | 0.500 | 1.50 | compare | 4K | 4K | 8.4 | N/A | |
| Llama 2 70B Chat Hf | Anyscale | 1.00 | 1.00 | compare | 4K | 4K | 8.4 | N/A | |
| Llama 2 13B Chat Hf | Anyscale | 0.250 | 0.250 | compare | 4K | 4K | 8.4 | N/A | |
| Command R+ | Vercel AI Gateway | 2.50 | 10.00 | compare | 128K | 4K | 8.3 | N/A | |
| Command Plus | Oracle Cloud (OCI) | 1.56 | 1.56 | compare | 128K | 4K | 8.3 | N/A | |
| Openchat 3p5 0106 7B | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | 8.3 | N/A | |
| Dbrx Instruct | Fireworks AI | 1.20 | 1.20 | compare | 33K | 33K | 8.3 | N/A | |
| Command R+ |  Cohere | 2.50 | 10.00 | compare | 128K | 4K | 8.3 | N/A | |
| Command R Plus V1 | AWS Bedrock | 3.00 | 15.00 | compare | 128K | 4K | 8.3 | N/A | |
| Command R+ | Azure OpenAI | 3.00 | 15.00 | compare | 128K | 4K | 8.3 | N/A | |
| Jamba 1.5 Mini | Vertex AI (AI21) | 0.200 | 0.400 | compare | 256K | 256K | 8.0 | N/A | |
| Jamba 1.5 Mini | Snowflake | N/A | N/A | compare | 256K | 8K | 8.0 | N/A | |
| Jamba 1.5 Mini | AI21 Labs | 0.200 | 0.400 | compare | 256K | 256K | 8.0 | N/A | |
| Jamba 1 5 Mini V1 | AWS Bedrock | 0.200 | 0.400 | compare | 256K | 256K | 8.0 | N/A | |
| Jamba Mini 1.6 | AI21 Labs | 0.200 | 0.400 | compare | 256K | 256K | 7.9 | N/A | |
| Mixtral 8x7B | Snowflake | N/A | N/A | compare | 32K | 8K | 7.7 | N/A | |
| Mixtral 8x7B Instruct | Perplexity | 0.070 | 0.280 | compare | 4K | 4K | 7.7 | N/A | |
| Open Mixtral 8x7B | Mistral AI | 0.700 | 0.700 | compare | 32K | 8K | 7.7 | N/A | |
| Mixtral 8x7B | Fireworks AI | 0.500 | 0.500 | compare | 33K | 33K | 7.7 | N/A | |
| Command R | Vercel AI Gateway | 0.150 | 0.600 | compare | 128K | 4K | 7.4 | N/A | |
| Qwen 3 14B | Vercel AI Gateway | 0.080 | 0.240 | compare | 41K | 16K | 7.4 | N/A | |
| Mistral 7B | Snowflake | N/A | N/A | compare | 32K | 8K | 7.4 | N/A | |
| Mistral 7B Instruct | Perplexity | 0.070 | 0.280 | compare | 4K | 4K | 7.4 | N/A | |
| Mistral 7B Instruct | OpenRouter | 0.130 | 0.130 | compare | 8K | N/A | 7.4 | N/A | |
| Mistral | Ollama | N/A | N/A | compare | 8K | 8K | 7.4 | N/A | |
| Open Mistral 7B | Mistral AI | 0.250 | 0.250 | compare | 32K | 8K | 7.4 | N/A | |
| Qwen3 14B | Fireworks AI | 0.200 | 0.200 | compare | 41K | 41K | 7.4 | N/A | |
| Mistral 7B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | 7.4 | N/A | |
| Qwen3 14B | DeepInfra | 0.060 | 0.240 | compare | 41K | 41K | 7.4 | N/A | |
| Command R | Cohere | 0.150 | 0.600 | compare | 128K | 4K | 7.4 | N/A | |
| Command R V1 | AWS Bedrock | 0.500 | 1.50 | compare | 128K | 4K | 7.4 | N/A | |
| Claude Instant V1 | AWS Bedrock | 0.800 | 2.40 | compare | 100K | 8K | 7.4 | 7.8 | |
| Glm 4.5 X | Z AI (Zhipu) | 2.20 | 8.90 | compare | 128K | 32K | N/A | N/A | |
| Glm 4.5 Flash | Z AI (Zhipu) | N/A | N/A | compare | 128K | 32K | N/A | N/A | |
| Glm 4.5 Airx | Z AI (Zhipu) | 1.10 | 4.50 | compare | 128K | 32K | N/A | N/A | |
| Glm 4 32B 0414 128K | Z AI (Zhipu) | 0.100 | 0.100 | compare | 128K | 32K | N/A | N/A | |
| Grok Vision Beta | xAI | 5.00 | 15.00 | compare | 8K | 8K | N/A | N/A | |
| Grok Code Fast 1 0825 | xAI | 0.200 | 1.50 | compare | 256K | 256K | N/A | N/A | |
| Grok Code Fast | xAI | 0.200 | 1.50 | compare | 256K | 256K | N/A | N/A | |
| Grok 4 0709 | xAI | 3.00 | 15.00 | compare | 256K | 256K | N/A | N/A | |
| Grok 3 Mini Fast | xAI | 0.600 | 4.00 | compare | 131K | 131K | N/A | N/A | |
| Grok 3 Fast | xAI | 5.00 | 25.00 | compare | 131K | 131K | N/A | N/A | |
| Grok 2 Vision | xAI | 2.00 | 10.00 | compare | 33K | 33K | N/A | N/A | |
| Grok 2 | xAI | 2.00 | 10.00 | compare | 131K | 131K | N/A | N/A | |
| Allam 1 13B Instruct | IBM watsonx | 1.80 | 1.80 | compare | 8K | 8K | N/A | N/A | |
| Pixtral 12B 2409 | IBM watsonx | 0.350 | 0.350 | compare | 128K | 128K | N/A | N/A | |
| Mistral Small 2503 | IBM watsonx | 0.100 | 0.300 | compare | 32K | 32K | N/A | N/A | |
| Mistral Medium 2505 | IBM watsonx | 3.00 | 10.00 | compare | 128K | 128K | N/A | N/A | |
| Llama Guard 3 11B Vision | IBM watsonx | 0.350 | 0.350 | compare | 128K | 128K | N/A | N/A | |
| Llama 4 Maverick 17B | IBM watsonx | 0.350 | 1.40 | compare | 128K | 128K | N/A | N/A | |
| Granite Vision 3 2 2B | IBM watsonx | 0.100 | 0.100 | compare | 8K | 8K | N/A | N/A | |
| Granite Ttm 512 96 R2 | IBM watsonx | 0.380 | 0.380 | compare | 512 | 512 | N/A | N/A | |
| Granite Ttm 1536 96 R2 | IBM watsonx | 0.380 | 0.380 | compare | 512 | 512 | N/A | N/A | |
| Granite Ttm 1024 96 R2 | IBM watsonx | 0.380 | 0.380 | compare | 512 | 512 | N/A | N/A | |
| Granite Guardian 3 3 8B | IBM watsonx | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Granite Guardian 3 2 2B | IBM watsonx | 0.100 | 0.100 | compare | 8K | 8K | N/A | N/A | |
| Granite 13B Chat V2 | IBM watsonx | 0.600 | 0.600 | compare | 8K | 8K | N/A | N/A | |
| Flan T5 Xl 3B | IBM watsonx | 0.600 | 0.600 | compare | 8K | 8K | N/A | N/A | |
| JAIS 13B Chat | IBM watsonx | 500.00 | 0.0020 | compare | 8K | 8K | N/A | N/A | |
| Mt0 Xxl 13B | IBM watsonx | 500.00 | 0.0020 | compare | 8K | 8K | N/A | N/A | |
| Qwen3 235B A22B Thinking 2507 | Weights & Biases | 0.010 | 0.010 | compare | 262K | 262K | N/A | N/A | |
| Llama 4 Scout 17B 16E Instruct | Weights & Biases | 0.017 | 0.066 | compare | 64K | 64K | N/A | N/A | |
| DeepSeek R1 0528 | Weights & Biases | 0.135 | 0.540 | compare | 161K | 161K | N/A | N/A | |
| Glm 5 Maas | Vertex AI (Z AI) | 1.00 | 3.20 | compare | 200K | 128K | N/A | 44.2 | |
| Mistral Small 2503 | Vertex AI (Mistral) | 1.00 | 3.00 | compare | 128K | 128K | N/A | N/A | |
| Mistral Nemo@latest | Vertex AI (Mistral) | 0.150 | 0.150 | compare | 128K | 128K | N/A | N/A | |
| Mistral Nemo | Vertex AI (Mistral) | 3.00 | 3.00 | compare | 128K | 128K | N/A | N/A | |
| Mistral Large 2411 | Vertex AI (Mistral) | 2.00 | 6.00 | compare | 128K | 8K | N/A | N/A | |
| Llama3 405B Instruct Maas | Vertex AI (Llama) | N/A | N/A | compare | 32K | 32K | N/A | N/A | |
| Llama 4 Scout 17B 16e Instruct Maas | Vertex AI (Llama) | 0.250 | 0.700 | compare | 10.0M | 10.0M | N/A | N/A | |
| Llama 4 Scout 17B 128e Instruct Maas | Vertex AI (Llama) | 0.250 | 0.700 | compare | 10.0M | 10.0M | N/A | N/A | |
| Llama 4 Maverick 17B 16e Instruct Maas | Vertex AI (Llama) | 0.350 | 1.15 | compare | 1.0M | 1.0M | N/A | N/A | |
| Llama 4 Maverick 17B 128e Instruct Maas | Vertex AI (Llama) | 0.350 | 1.15 | compare | 1.0M | 1.0M | N/A | N/A | |
| Jamba 1.5 | Vertex AI (AI21) | 0.200 | 0.400 | compare | 256K | 256K | N/A | N/A | |
| Gemini 3.1 Pro Preview | Google Vertex AI | 2.00 | 12.00 | compare | 1.0M | 66K | N/A | 55.5 | |
| DeepSeek R1 0528 Maas | Vertex AI (DeepSeek) | 1.35 | 5.40 | compare | 65K | 8K | N/A | N/A | |
| Codestral @latest | Vertex AI (Mistral) | 0.200 | 0.600 | compare | 128K | 128K | N/A | N/A | |
| Codestral | Vertex AI (Mistral) | 0.200 | 0.600 | compare | 128K | 128K | N/A | N/A | |
| Codestral 2501 | Vertex AI (Mistral) | 0.200 | 0.600 | compare | 128K | 128K | N/A | N/A | |
| Codestral 2 | Vertex AI (Mistral) | 0.300 | 0.900 | compare | 128K | 128K | N/A | N/A | |
| Claude Sonnet 4.6 | Anthropic (Vertex AI) | 3.00 | 15.00 | compare | 200K | 64K | N/A | 46.4 | |
| Claude Opus 4.6 | Anthropic (Vertex AI) | 5.00 | 25.00 | compare | 1.0M | 128K | N/A | 47.6 | |
| Grok 3 Mini Fast | Vercel AI Gateway | 0.600 | 4.00 | compare | 131K | 131K | N/A | N/A | |
| Grok 3 Mini | Vercel AI Gateway | 0.300 | 0.500 | compare | 131K | 131K | N/A | N/A | |
| Grok 3 Fast | Vercel AI Gateway | 5.00 | 25.00 | compare | 131K | 131K | N/A | N/A | |
| Grok 2 Vision | Vercel AI Gateway | 2.00 | 10.00 | compare | 33K | 33K | N/A | N/A | |
| Grok 2 | Vercel AI Gateway | 2.00 | 10.00 | compare | 131K | 4K | N/A | N/A | |
| V0 1.5 Md | Vercel AI Gateway | 3.00 | 15.00 | compare | 128K | 33K | N/A | N/A | |
| V0 1.0 Md | Vercel AI Gateway | 3.00 | 15.00 | compare | 128K | 32K | N/A | N/A | |
| Morph V3 Large | Vercel AI Gateway | 0.900 | 1.90 | compare | 33K | 16K | N/A | N/A | |
| Morph V3 Fast | Vercel AI Gateway | 0.800 | 1.20 | compare | 33K | 16K | N/A | N/A | |
| Pixtral Large | Vercel AI Gateway | 2.00 | 6.00 | compare | 128K | 4K | N/A | N/A | |
| Pixtral 12B | Vercel AI Gateway | 0.150 | 0.150 | compare | 128K | 4K | N/A | N/A | |
| Mistral Embed | Vercel AI Gateway | 0.100 | N/A | compare | N/A | N/A | N/A | N/A | |
| Ministral 8B | Vercel AI Gateway | 0.100 | 0.100 | compare | 128K | 4K | N/A | N/A | |
| Ministral 3B | Vercel AI Gateway | 0.040 | 0.040 | compare | 128K | 4K | N/A | N/A | |
| Codestral Embed | Vercel AI Gateway | 0.150 | N/A | compare | N/A | N/A | N/A | N/A | |
| Codestral | Vercel AI Gateway | 0.300 | 0.900 | compare | 256K | 4K | N/A | N/A | |
| Mercury Coder Small | Vercel AI Gateway | 0.250 | 1.00 | compare | 32K | 16K | N/A | N/A | |
| Gemma 2 9B | Vercel AI Gateway | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Embed V4.0 | Vercel AI Gateway | 0.120 | N/A | compare | N/A | N/A | N/A | N/A | |
| Claude Opus 4.6 | Vercel AI Gateway | 5.00 | 25.00 | compare | 200K | 64K | N/A | 47.6 | |
| Titan Embed Text V2 | Vercel AI Gateway | 0.020 | N/A | compare | N/A | N/A | N/A | N/A | |
| Qwen3 Coder | Vercel AI Gateway | 0.400 | 1.60 | compare | 262K | 67K | N/A | N/A | |
| V0 1.5 Md |  v0 (Vercel) | 3.00 | 15.00 | compare | 128K | 128K | N/A | N/A | |
| V0 1.5 Lg | v0 (Vercel) | 15.00 | 75.00 | compare | 512K | 512K | N/A | N/A | |
| V0 1.0 Md | v0 (Vercel) | 3.00 | 15.00 | compare | 128K | 128K | N/A | N/A | |
| Us.writer.palmyra X5 V1 | AWS Bedrock | 0.600 | 6.00 | compare | 1.0M | 8K | N/A | N/A | |
| Us.writer.palmyra X4 V1 | AWS Bedrock | 2.50 | 10.00 | compare | 128K | 8K | N/A | N/A | |
| Together Ai Up To 4B | Together AI | 0.100 | 0.100 | compare | N/A | N/A | N/A | N/A | |
| Together Ai 81.1B 110B | Together AI | 1.80 | 1.80 | compare | N/A | N/A | N/A | N/A | |
| Together Ai 8.1B 21B | Together AI | 0.300 | 0.300 | compare | 1K | N/A | N/A | N/A | |
| Together Ai 41.1B 80B | Together AI | 0.900 | 0.900 | compare | N/A | N/A | N/A | N/A | |
| Together Ai 4.1B 8B | Together AI | 0.200 | 0.200 | compare | N/A | N/A | N/A | N/A | |
| Together Ai 21.1B 41B | Together AI | 0.800 | 0.800 | compare | N/A | N/A | N/A | N/A | |
| CodeLlama 34B Instruct | Together AI | N/A | N/A | compare | N/A | N/A | N/A | N/A | |
| Qwen3 235B A22B Thinking 2507 | Together AI | 0.650 | 3.00 | compare | 256K | N/A | N/A | N/A | |
| Qwen2.5 7B Instruct Turbo | Together AI | N/A | N/A | compare | N/A | N/A | N/A | N/A | |
| Mixtral 8x7B Instruct V0.1 | Together AI | 0.600 | 0.600 | compare | N/A | N/A | N/A | N/A | |
| Mistral Small 24B Instruct 2501 | Together AI | N/A | N/A | compare | N/A | N/A | N/A | N/A | |
| Mistral 7B Instruct V0.1 | Together AI | N/A | N/A | compare | N/A | N/A | N/A | N/A | |
| Llama 4 Scout 17B 16E Instruct | Together AI | 0.180 | 0.590 | compare | N/A | N/A | N/A | N/A | |
| Llama 4 Maverick 17B 128E Instruct FP8 | Together AI | 0.270 | 0.850 | compare | N/A | N/A | N/A | N/A | |
| DeepSeek R1 0528 Tput | Together AI | 0.550 | 2.19 | compare | 128K | N/A | N/A | N/A | |
| Text Unicorn |  Google Vertex AI | 10.00 | 28.00 | compare | 8K | 1K | N/A | N/A | |
| Text Unicorn | Google Vertex AI | 10.00 | 28.00 | compare | 8K | 1K | N/A | N/A | |
| Text Bison32k | Google Vertex AI | 0.125 | 0.125 | compare | 8K | 1K | N/A | N/A | |
| Text Bison32k | Google Vertex AI | 0.125 | 0.125 | compare | 8K | 1K | N/A | N/A | |
| Text Bison | Google Vertex AI | N/A | N/A | compare | 8K | 1K | N/A | N/A | |
| Text Bison | Google Vertex AI | N/A | N/A | compare | 8K | 1K | N/A | N/A | |
| Text Bison | Google Vertex AI | N/A | N/A | compare | 8K | 2K | N/A | N/A | |
| Reka Core | Snowflake | N/A | N/A | compare | 32K | 8K | N/A | N/A | |
| Jamba Instruct | Snowflake | N/A | N/A | compare | 256K | 8K | N/A | N/A | |
| Gemma 7B | Snowflake | N/A | N/A | compare | 8K | 8K | N/A | N/A | |
| Sarvam M |  Sarvam AI | N/A | N/A | compare | 8K | 32K | N/A | N/A | |
| Qwen2 Audio 7B Instruct | SambaNova | 0.500 | 100.00 | compare | 4K | 4K | N/A | N/A | |
| Meta Llama Guard 3 8B | SambaNova | 0.300 | 0.300 | compare | 16K | 16K | N/A | N/A | |
| Llama 4 Scout 17B 16E Instruct | SambaNova | 0.400 | 0.700 | compare | 8K | 8K | N/A | N/A | |
| Llama 4 Maverick 17B 128E Instruct | SambaNova | 0.630 | 1.80 | compare | 131K | 131K | N/A | N/A | |
| Mixtral 8x7B Instruct V0.1 | Replicate | 0.300 | 1.00 | compare | 4K | 4K | N/A | N/A | |
| Mistral 7B V0.1 | Replicate | 0.050 | 0.250 | compare | 4K | 4K | N/A | N/A | |
| Mistral 7B Instruct V0.2 | Replicate | 0.050 | 0.250 | compare | 4K | 4K | N/A | N/A | |
| Apertus 8B Instruct | Public AI | N/A | N/A | compare | 8K | 4K | N/A | N/A | |
| Apertus 70B Instruct | Public AI | N/A | N/A | compare | 8K | 4K | N/A | N/A | |
| Salamandra 7B Instruct Tools 16K | Public AI | N/A | N/A | compare | 16K | 4K | N/A | N/A | |
| ALIA 40B Instruct Q8 0 | Public AI | N/A | N/A | compare | 8K | 4K | N/A | N/A | |
| Qwen SEA LION V4 32B IT | Public AI | N/A | N/A | compare | 33K | 4K | N/A | N/A | |
| Gemma SEA LION V4 27B IT | Public AI | N/A | N/A | compare | 8K | 4K | N/A | N/A | |
| Sonar Small Chat | Perplexity | 0.070 | 0.280 | compare | 16K | 16K | N/A | N/A | |
| Sonar Medium Chat | Perplexity | 0.600 | 1.80 | compare | 16K | 16K | N/A | N/A | |
| Sonar Deep Research | Perplexity | 2.00 | 8.00 | compare | 128K | N/A | N/A | N/A | |
| Pplx 7B Chat | Perplexity | 0.070 | 0.280 | compare | 8K | 8K | N/A | N/A | |
| Pplx 70B Chat | Perplexity | 0.700 | 2.80 | compare | 4K | 4K | N/A | N/A | |
| Llama 3.1 Sonar Small 128K Chat | Perplexity | 0.200 | 0.200 | compare | 131K | 131K | N/A | N/A | |
| Llama 3.1 Sonar Large 128K Chat | Perplexity | 1.00 | 1.00 | compare | 131K | 131K | N/A | N/A | |
| Llama 3.1 Sonar Huge 128K Online | Perplexity | 5.00 | 5.00 | compare | 127K | 127K | N/A | N/A | |
| Codellama 70B Instruct | Perplexity | 0.700 | 2.80 | compare | 16K | 16K | N/A | N/A | |
| Codellama 34B Instruct | Perplexity | 0.350 | 1.40 | compare | 16K | 16K | N/A | N/A | |
| Text Bison 001 |  Google PaLM | 0.125 | 0.125 | compare | 8K | 1K | N/A | N/A | |
| Text Bison | Google PaLM | 0.125 | 0.125 | compare | 8K | 1K | N/A | N/A | |
| Chat Bison 001 | Google PaLM | 0.125 | 0.125 | compare | 8K | 4K | N/A | N/A | |
| Chat Bison | Google PaLM | 0.125 | 0.125 | compare | 8K | 4K | N/A | N/A | |
| Qwen2.5 VL 72B Instruct | OVHcloud | 0.910 | 0.910 | compare | 32K | 32K | N/A | N/A | |
| Mixtral 8x7B Instruct V0.1 | OVHcloud | 0.630 | 0.630 | compare | 32K | 32K | N/A | N/A | |
| Mistral Nemo Instruct 2407 | OVHcloud | 0.130 | 0.130 | compare | 118K | 118K | N/A | N/A | |
| Mistral 7B Instruct V0.3 | OVHcloud | 0.100 | 0.100 | compare | 127K | 127K | N/A | N/A | |
| Mamba Codestral 7B V0.1 | OVHcloud | 0.190 | 0.190 | compare | 256K | 256K | N/A | N/A | |
| Llava V1.6 Mistral 7B Hf | OVHcloud | 0.290 | 0.290 | compare | 32K | 32K | N/A | N/A | |
| Remm Slerp L2 13B | OpenRouter | 1.88 | 1.88 | compare | 6K | N/A | N/A | N/A | |
| Router | OpenRouter | 0.850 | 3.40 | compare | 131K | 131K | N/A | N/A | |
| Qwen3 Coder | OpenRouter | 0.220 | 0.950 | compare | 262K | 262K | N/A | N/A | |
| Qwen3 235B A22b Thinking 2507 | OpenRouter | 0.110 | 0.600 | compare | 262K | 262K | N/A | N/A | |
| Qwen Vl Plus | OpenRouter | 0.210 | 0.630 | compare | 8K | 2K | N/A | N/A | |
| GPT-5.2-pro | OpenRouter | 21.00 | 168.00 | compare | 272K | 128K | N/A | N/A | |
| GPT-5.2-codex | OpenRouter | 1.75 | 14.00 | compare | 272K | 128K | N/A | 43.0 | |
| Mistral Large 2512 | OpenRouter | 0.500 | 1.50 | compare | 262K | 262K | N/A | N/A | |
| Devstral 2512 | OpenRouter | 0.150 | 0.600 | compare | 262K | 66K | N/A | N/A | |
| Minimax M2.1 | OpenRouter | 0.270 | 1.20 | compare | 204K | 64K | N/A | N/A | |
| Weaver | OpenRouter | 5.63 | 5.63 | compare | 8K | N/A | N/A | N/A | |
| Mythomax L2 13B | OpenRouter | 1.88 | 1.88 | compare | 8K | N/A | N/A | N/A | |
| DeepSeek R1 0528 | OpenRouter | 0.500 | 2.15 | compare | 65K | 8K | N/A | N/A | |
| DeepSeek Chat V3.1 | OpenRouter | 0.200 | 0.800 | compare | 164K | 164K | N/A | N/A | |
| DeepSeek Chat V3 0324 | OpenRouter | 0.140 | 0.280 | compare | 66K | 8K | N/A | N/A | |
| DeepSeek Chat | OpenRouter | 0.140 | 0.280 | compare | 66K | 8K | N/A | N/A | |
| Ui Tars 1.5 7B | OpenRouter | 0.100 | 0.200 | compare | 131K | 2K | N/A | N/A | |
| Container | OpenAI | N/A | N/A | compare | N/A | N/A | N/A | N/A | |
| GPT-oss-safeguard-20b | AWS Bedrock | 0.070 | 0.200 | compare | 128K | 8K | N/A | N/A | |
| GPT-oss-safeguard-120b | AWS Bedrock | 0.150 | 0.600 | compare | 128K | 8K | N/A | N/A | |
| Vicuna | Ollama | N/A | N/A | compare | 2K | 2K | N/A | N/A | |
| Orca Mini | Ollama | N/A | N/A | compare | 4K | 4K | N/A | N/A | |
| Mixtral 8x7B Instruct V0.1 | Ollama | N/A | N/A | compare | 33K | 33K | N/A | N/A | |
| Mixtral 8x22B Instruct V0.1 | Ollama | N/A | N/A | compare | 66K | 66K | N/A | N/A | |
| Mistral 7B Instruct V0.2 | Ollama | N/A | N/A | compare | 33K | 33K | N/A | N/A | |
| Mistral 7B Instruct V0.1 | Ollama | N/A | N/A | compare | 8K | 8K | N/A | N/A | |
| Llama2 | Ollama | N/A | N/A | compare | 4K | 4K | N/A | N/A | |
| Internlm2 5 20B Chat | Ollama | N/A | N/A | compare | 33K | 8K | N/A | N/A | |
| Codellama | Ollama | N/A | N/A | compare | 4K | 4K | N/A | N/A | |
| Codegemma | Ollama | N/A | N/A | compare | 8K | 8K | N/A | N/A | |
| Codegeex4 | Ollama | N/A | N/A | compare | 33K | 8K | N/A | N/A | |
| Xai.grok 3 Mini Fast | Oracle Cloud (OCI) | 0.600 | 4.00 | compare | 131K | 131K | N/A | N/A | |
| Xai.grok 3 Mini | Oracle Cloud (OCI) | 0.300 | 0.500 | compare | 131K | 131K | N/A | N/A | |
| Xai.grok 3 Fast | Oracle Cloud (OCI) | 5.00 | 25.00 | compare | 131K | 131K | N/A | N/A | |
| Llama 4 Scout 17B 16e Instruct | Oracle Cloud (OCI) | 0.720 | 0.720 | compare | 192K | 4K | N/A | N/A | |
| Llama 4 Maverick 17B 128e Instruct Fp8 | Oracle Cloud (OCI) | 0.720 | 0.720 | compare | 512K | 4K | N/A | N/A | |
| Command | Oracle Cloud (OCI) | 1.56 | 1.56 | compare | 128K | 4K | N/A | N/A | |
| Command A | Oracle Cloud (OCI) | 1.56 | 1.56 | compare | 256K | 4K | N/A | N/A | |
| Qwen2.5 Coder 3B Instruct | Nscale | 0.010 | 0.030 | compare | N/A | N/A | N/A | N/A | |
| Mixtral 8x22B Instruct V0.1 | Nscale | 0.600 | 0.600 | compare | N/A | N/A | N/A | N/A | |
| Llama 4 Scout 17B 16E Instruct | Nscale | 0.090 | 0.290 | compare | N/A | N/A | N/A | N/A | |
| DeepSeek R1 Distill Qwen 7B | Nscale | 0.200 | 0.200 | compare | N/A | N/A | N/A | N/A | |
| Autoglm Phone 9B Multilingual | Novita AI | 0.035 | 0.138 | compare | 66K | 66K | N/A | N/A | |
| R1v4 Lite | Novita AI | 0.200 | 0.600 | compare | 262K | 66K | N/A | N/A | |
| L31 70B Euryale V2.2 | Novita AI | 1.48 | 1.48 | compare | 8K | 8K | N/A | N/A | |
| L3 8B Stheno V3.2 | Novita AI | 0.050 | 0.050 | compare | 8K | 32K | N/A | N/A | |
| L3 8B Lunaris | Novita AI | 0.050 | 0.050 | compare | 8K | 8K | N/A | N/A | |
| L3 70B Euryale V2.1 | Novita AI | 1.48 | 1.48 | compare | 8K | 8K | N/A | N/A | |
| Qwen2.5 Vl 72B Instruct | Novita AI | 0.800 | 0.800 | compare | 33K | 33K | N/A | N/A | |
| Qwen2.5 7B Instruct | Novita AI | 0.070 | 0.070 | compare | 32K | 32K | N/A | N/A | |
| Qwen Mt Plus | Novita AI | 0.250 | 0.750 | compare | 16K | 8K | N/A | N/A | |
| Paddleocr Vl | Novita AI | 0.020 | 0.020 | compare | 16K | 16K | N/A | N/A | |
| Hermes 2 Pro Llama 3 8B | Novita AI | 0.140 | 0.140 | compare | 8K | 8K | N/A | N/A | |
| Mistral Nemo | Novita AI | 0.040 | 0.170 | compare | 60K | 16K | N/A | N/A | |
| Minimax M2.1 | Novita AI | 0.300 | 1.20 | compare | 205K | 131K | N/A | N/A | |
| Wizardlm 2 8x22B | Novita AI | 0.620 | 0.620 | compare | 66K | 8K | N/A | N/A | |
| Llama 4 Scout 17B 16e Instruct | Novita AI | 0.180 | 0.590 | compare | 131K | 131K | N/A | N/A | |
| Llama 4 Maverick 17B 128e Instruct Fp8 | Novita AI | 0.270 | 0.850 | compare | 1.0M | 8K | N/A | N/A | |
| Mythomax L2 13B | Novita AI | 0.090 | 0.090 | compare | 4K | 3K | N/A | N/A | |
| DeepSeek R1 Turbo | Novita AI | 0.700 | 2.50 | compare | 64K | 16K | N/A | N/A | |
| DeepSeek R1 0528 | Novita AI | 0.700 | 2.50 | compare | 164K | 33K | N/A | N/A | |
| DeepSeek Prover V2 671B | Novita AI | 0.700 | 2.50 | compare | 160K | 160K | N/A | N/A | |
| DeepSeek OCR | Novita AI | 0.030 | 0.030 | compare | 8K | 8K | N/A | N/A | |
| ERNIE 4.5 Vl 424B A47b | Novita AI | 0.420 | 1.25 | compare | 123K | 16K | N/A | N/A | |
| ERNIE 4.5 Vl 28B A3b | Novita AI | 0.140 | 0.560 | compare | 30K | 8K | N/A | N/A | |
| ERNIE 4.5 21B A3b | Novita AI | 0.070 | 0.280 | compare | 120K | 8K | N/A | N/A | |
| Baichuan M2 32B | Novita AI | 0.070 | 0.070 | compare | 131K | 131K | N/A | N/A | |
| Morph V3 Large |  Morph | 0.900 | 1.90 | compare | 16K | 16K | N/A | N/A | |
| Morph V3 Fast | Morph | 0.800 | 1.20 | compare | 16K | 16K | N/A | N/A | |
| Moonshot V1 Auto | Moonshot AI (Kimi) | 2.00 | 5.00 | compare | 131K | 131K | N/A | N/A | |
| Moonshot V1 8K Vision Preview | Moonshot AI (Kimi) | 0.200 | 2.00 | compare | 8K | 8K | N/A | N/A | |
| Moonshot V1 8K 0430 | Moonshot AI (Kimi) | 0.200 | 2.00 | compare | 8K | 8K | N/A | N/A | |
| Moonshot V1 8K | Moonshot AI (Kimi) | 0.200 | 2.00 | compare | 8K | 8K | N/A | N/A | |
| Moonshot V1 32K Vision Preview | Moonshot AI (Kimi) | 1.00 | 3.00 | compare | 33K | 33K | N/A | N/A | |
| Moonshot V1 32K 0430 | Moonshot AI (Kimi) | 1.00 | 3.00 | compare | 33K | 33K | N/A | N/A | |
| Moonshot V1 32K | Moonshot AI (Kimi) | 1.00 | 3.00 | compare | 33K | 33K | N/A | N/A | |
| Moonshot V1 128K Vision Preview | Moonshot AI (Kimi) | 2.00 | 5.00 | compare | 131K | 131K | N/A | N/A | |
| Moonshot V1 128K 0430 | Moonshot AI (Kimi) | 2.00 | 5.00 | compare | 131K | 131K | N/A | N/A | |
| Moonshot V1 128K | Moonshot AI (Kimi) | 2.00 | 5.00 | compare | 131K | 131K | N/A | N/A | |
| Kimi Thinking Preview | Moonshot AI (Kimi) | 0.600 | 2.50 | compare | 131K | 131K | N/A | N/A | |
| Kimi Latest 8K | Moonshot AI (Kimi) | 0.200 | 2.00 | compare | 8K | 8K | N/A | N/A | |
| Kimi Latest 32K | Moonshot AI (Kimi) | 1.00 | 3.00 | compare | 33K | 33K | N/A | N/A | |
| Kimi Latest 128K | Moonshot AI (Kimi) | 2.00 | 5.00 | compare | 131K | 131K | N/A | N/A | |
| Kimi | Moonshot AI (Kimi) | 2.00 | 5.00 | compare | 131K | 131K | N/A | N/A | |
| Kimi K2 Turbo Preview | Moonshot AI (Kimi) | 1.15 | 8.00 | compare | 262K | 262K | N/A | N/A | |
| Kimi K2 Thinking Turbo | Moonshot AI (Kimi) | 1.15 | 8.00 | compare | 262K | 262K | N/A | N/A | |
| Kimi K2 0711 Preview | Moonshot AI (Kimi) | 0.600 | 2.50 | compare | 131K | 131K | N/A | N/A | |
| Pixtral Large | Mistral AI | 2.00 | 6.00 | compare | 128K | 128K | N/A | N/A | |
| Pixtral 12B 2409 | Mistral AI | 0.150 | 0.150 | compare | 128K | 128K | N/A | N/A | |
| Open Mistral Nemo 2407 | Mistral AI | 0.300 | 0.300 | compare | 128K | 128K | N/A | N/A | |
| Open Mistral Nemo | Mistral AI | 0.300 | 0.300 | compare | 128K | 128K | N/A | N/A | |
| Mistral Tiny | Mistral AI | 0.250 | 0.250 | compare | 32K | 8K | N/A | N/A | |
| Mistral Medium 2505 | Mistral AI | 0.400 | 2.00 | compare | 131K | 8K | N/A | N/A | |
| Mistral Medium 2312 | Mistral AI | 2.70 | 8.10 | compare | 32K | 8K | N/A | N/A | |
| Mistral Large 2411 | Mistral AI | 2.00 | 6.00 | compare | 128K | 128K | N/A | N/A | |
| Mistral Large 2402 | Mistral AI | 4.00 | 12.00 | compare | 32K | 8K | N/A | N/A | |
| Magistral Small 2506 | Mistral AI | 0.500 | 1.50 | compare | 40K | 40K | N/A | N/A | |
| Magistral Medium 2506 | Mistral AI | 2.00 | 5.00 | compare | 40K | 40K | N/A | N/A | |
| Labs Devstral Small 2512 | Mistral AI | 0.100 | 0.300 | compare | 256K | 256K | N/A | N/A | |
| Devstral Small 2507 | Mistral AI | 0.100 | 0.300 | compare | 128K | 128K | N/A | N/A | |
| Devstral Medium 2507 | Mistral AI | 0.400 | 2.00 | compare | 128K | 128K | N/A | N/A | |
| Devstral 2512 | Mistral AI | 0.400 | 2.00 | compare | 256K | 256K | N/A | N/A | |
| Codestral Mamba | Mistral AI | 0.250 | 0.250 | compare | 256K | 256K | N/A | N/A | |
| Codestral | Mistral AI | 1.00 | 3.00 | compare | 32K | 8K | N/A | N/A | |
| Codestral 2508 | Mistral AI | 0.300 | 0.900 | compare | 256K | 256K | N/A | N/A | |
| Codestral 2405 | Mistral AI | 1.00 | 3.00 | compare | 32K | 8K | N/A | N/A | |
| Voxtral Small 24B 2507 | AWS Bedrock | 0.100 | 0.300 | compare | 128K | 8K | N/A | N/A | |
| Voxtral Mini 3B 2507 | AWS Bedrock | 0.040 | 0.040 | compare | 128K | 8K | N/A | N/A | |
| MiniMax M2.5 Lightning | MiniMax | 0.300 | 2.40 | compare | 1.0M | 8K | N/A | N/A | |
| MiniMax M2.1 Lightning | MiniMax | 0.300 | 2.40 | compare | 1.0M | 8K | N/A | N/A | |
| MiniMax M2.1 | MiniMax | 0.300 | 1.20 | compare | 1.0M | 8K | N/A | N/A | |
| Llama4 Scout 17B Instruct V1 | AWS Bedrock | 0.170 | 0.660 | compare | 128K | 4K | N/A | N/A | |
| Llama4 Maverick 17B Instruct V1 | AWS Bedrock | 0.240 | 0.970 | compare | 128K | 4K | N/A | N/A | |
| Llama 4 Scout 17B 16E Instruct FP8 | Meta Llama | N/A | N/A | compare | 10.0M | 4K | N/A | N/A | |
| Llama 4 Maverick 17B 128E Instruct FP8 | Meta Llama | N/A | N/A | compare | 1.0M | 4K | N/A | N/A | |
| Llama 3.3 8B Instruct | Meta Llama | N/A | N/A | compare | 128K | 4K | N/A | N/A | |
| Medlm Medium | Google Vertex AI | N/A | N/A | compare | 33K | 8K | N/A | N/A | |
| Medlm Large | Google Vertex AI | N/A | N/A | compare | 8K | 1K | N/A | N/A | |
| Luminous Supreme Control |  Aleph Alpha | 218.75 | 240.63 | compare | 2K | N/A | N/A | N/A | |
| Luminous Supreme | Aleph Alpha | 175.00 | 192.50 | compare | 2K | N/A | N/A | N/A | |
| Luminous Extended Control | Aleph Alpha | 56.25 | 61.88 | compare | 2K | N/A | N/A | N/A | |
| Luminous Extended | Aleph Alpha | 45.00 | 49.50 | compare | 2K | N/A | N/A | N/A | |
| Luminous Base Control | Aleph Alpha | 37.50 | 41.25 | compare | 2K | N/A | N/A | N/A | |
| Luminous Base | Aleph Alpha | 30.00 | 33.00 | compare | 2K | N/A | N/A | N/A | |
| Openthinker 7B | LlamaGate | 0.080 | 0.150 | compare | 33K | 8K | N/A | N/A | |
| Mistral 7B V0.3 | LlamaGate | 0.100 | 0.150 | compare | 33K | 8K | N/A | N/A | |
| Llava 7B | LlamaGate | 0.100 | 0.200 | compare | 4K | 2K | N/A | N/A | |
| Dolphin3 8B | LlamaGate | 0.080 | 0.150 | compare | 128K | 8K | N/A | N/A | |
| DeepSeek R1 8B | LlamaGate | 0.100 | 0.200 | compare | 66K | 16K | N/A | N/A | |
| DeepSeek R1 7B Qwen | LlamaGate | 0.080 | 0.150 | compare | 131K | 16K | N/A | N/A | |
| DeepSeek Coder 6.7B | LlamaGate | 0.060 | 0.120 | compare | 16K | 4K | N/A | N/A | |
| Codellama 7B | LlamaGate | 0.060 | 0.120 | compare | 16K | 4K | N/A | N/A | |
| Llama 4 Scout 17B 16e Instruct | Lambda | 0.050 | 0.100 | compare | 16K | 8K | N/A | N/A | |
| Llama 4 Maverick 17B 128e Instruct Fp8 | Lambda | 0.050 | 0.100 | compare | 131K | 8K | N/A | N/A | |
| Lfm 7B | Lambda | 0.025 | 0.040 | compare | 131K | 131K | N/A | N/A | |
| Hermes3 8B | Lambda | 0.025 | 0.040 | compare | 131K | 131K | N/A | N/A | |
| DeepSeek R1 671B | Lambda | 0.800 | 0.800 | compare | 131K | 131K | N/A | N/A | |
| DeepSeek R1 0528 | Lambda | 0.200 | 0.600 | compare | 131K | 131K | N/A | N/A | |
| Jamba 1.5 | AI21 Labs | 0.200 | 0.400 | compare | 256K | 256K | N/A | N/A | |
| J2 Ultra | AI21 Labs | 15.00 | 15.00 | compare | 8K | 8K | N/A | N/A | |
| J2 Mid | AI21 Labs | 10.00 | 10.00 | compare | 8K | 8K | N/A | N/A | |
| J2 Light | AI21 Labs | 3.00 | 3.00 | compare | 8K | 8K | N/A | N/A | |
| DeepSeek R1 0528 | Hyperbolic | 0.250 | 0.250 | compare | 131K | 131K | N/A | N/A | |
| GPT-oss-safeguard-20b | Groq | 0.075 | 0.300 | compare | 131K | 66K | N/A | N/A | |
| Llama Guard 4 12B | Groq | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Llama 4 Scout 17B 16e Instruct | Groq | 0.110 | 0.340 | compare | 131K | 8K | N/A | N/A | |
| Llama 4 Maverick 17B 128e Instruct | Groq | 0.200 | 0.600 | compare | 131K | 8K | N/A | N/A | |
| Gemma 7B It | Groq | 0.050 | 0.080 | compare | 8K | 8K | N/A | N/A | |
| Mistral Nemo Instruct 2407 | Gradient AI | 0.300 | 0.300 | compare | 512 | N/A | N/A | N/A | |
| GPT-realtime mini | OpenAI | 0.600 | 2.40 | compare | 128K | 4K | N/A | N/A | |
| GPT-realtime | OpenAI | 4.00 | 16.00 | compare | 32K | 4K | N/A | N/A | |
| GPT-audio mini | OpenAI | 0.600 | 2.40 | compare | 128K | 16K | N/A | N/A | |
| GPT-audio | OpenAI | 2.50 | 10.00 | compare | 128K | 16K | N/A | N/A | |
| GPT-5-search-api | OpenAI | 1.25 | 10.00 | compare | 272K | 128K | N/A | N/A | |
| GPT-4o-realtime Preview | OpenAI | 5.00 | 20.00 | compare | 128K | 4K | N/A | N/A | |
| GPT-4o-mini-search Preview | OpenAI | 0.150 | 0.600 | compare | 128K | 16K | N/A | N/A | |
| GPT-4o-mini-realtime Preview | OpenAI | 0.600 | 2.40 | compare | 128K | 4K | N/A | N/A | |
| GPT-4o-mini-audio Preview | OpenAI | 0.150 | 0.600 | compare | 128K | 16K | N/A | N/A | |
| GPT-4o-audio Preview | OpenAI | 2.50 | 10.00 | compare | 128K | 16K | N/A | N/A | |
| GPT-4-32k-0613 | OpenAI | 60.00 | 120.00 | compare | 33K | 4K | N/A | N/A | |
| GPT-4-32k-0314 | OpenAI | 60.00 | 120.00 | compare | 33K | 4K | N/A | N/A | |
| GPT-4-1106 Preview | OpenAI | 10.00 | 30.00 | compare | 128K | 4K | N/A | N/A | |
| GPT-4 | OpenAI | 30.00 | 60.00 | compare | 8K | 4K | N/A | N/A | |
| MiniMax M2.1 | GMI Cloud | 0.300 | 1.20 | compare | 197K | 16K | N/A | N/A | |
| GPT-4 | GitHub Copilot | N/A | N/A | compare | 33K | 4K | N/A | N/A | |
| Claude Opus 4.6 | GitHub Copilot | N/A | N/A | compare | 128K | 16K | N/A | 47.6 | |
| GigaChat 2 Pro |  GigaChat (Sber) | N/A | N/A | compare | 128K | 8K | N/A | N/A | |
| GigaChat 2 Max | GigaChat (Sber) | N/A | N/A | compare | 128K | 8K | N/A | N/A | |
| GigaChat 2 Lite | GigaChat (Sber) | N/A | N/A | compare | 128K | 8K | N/A | N/A | |
| Learnlm 1.5 Pro Experimental | Google Gemini | N/A | N/A | compare | 33K | 8K | N/A | N/A | |
| Gemini robotics-er-1.5 Preview | Google Gemini | 0.300 | 2.50 | compare | 1.0M | 66K | N/A | N/A | |
| Gemini gemma-2-9b-it | Google Gemini | 0.350 | 1.05 | compare | 8K | 8K | N/A | N/A | |
| Gemini gemma-2-27b-it | Google Gemini | 0.350 | 1.05 | compare | 8K | 8K | N/A | N/A | |
| Gemini Experimental 1114 | Google Gemini | N/A | N/A | compare | 1.0M | 8K | N/A | N/A | |
| Gemini 3.1 Pro Preview | Google Gemini | 2.00 | 12.00 | compare | 1.0M | 66K | N/A | 55.5 | |
| Gemini 2.0 Pro-exp-02-05 | Google Gemini | N/A | N/A | compare | 2.1M | 8K | N/A | N/A | |
| Gemini robotics-er-1.5 Preview | Google Vertex AI | 0.300 | 2.50 | compare | 1.0M | 66K | N/A | N/A | |
| Gemini Experimental 1206 | Google Gemini | 0.300 | 2.50 | compare | 1.0M | 66K | N/A | N/A | |
| Gemini 2.0 Pro-exp-02-05 | Google Vertex AI | 1.25 | 10.00 | compare | 2.1M | 8K | N/A | N/A | |
| Ft:davinci 002 |  OpenAI | 12.00 | 12.00 | compare | 16K | 4K | N/A | N/A | |
| Ft:babbage 002 | OpenAI | 1.60 | 1.60 | compare | 16K | 4K | N/A | N/A | |
| Zephyr 7B Beta | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Yi Large | Fireworks AI | 3.00 | 3.00 | compare | 33K | 33K | N/A | N/A | |
| Yi 6B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| Yi 34B 200K Capybara | Fireworks AI | 0.900 | 0.900 | compare | 200K | 200K | N/A | N/A | |
| Yi 34B | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | N/A | N/A | |
| Toppy M 7B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Starcoder2 7B | Fireworks AI | 0.200 | 0.200 | compare | 16K | 16K | N/A | N/A | |
| Starcoder2 3B | Fireworks AI | 0.100 | 0.100 | compare | 16K | 16K | N/A | N/A | |
| Starcoder2 15B | Fireworks AI | 0.200 | 0.200 | compare | 16K | 16K | N/A | N/A | |
| Starcoder 7B | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Starcoder 16B | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Stablecode 3B | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | N/A | N/A | |
| Snorkel Mistral 7B Pairrm Dpo | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Rolm OCR | Fireworks AI | 0.200 | 0.200 | compare | 128K | 128K | N/A | N/A | |
| Qwen3 1p7b Fp8 Draft 40960 | Fireworks AI | 0.100 | 0.100 | compare | 41K | 41K | N/A | N/A | |
| Qwen3 1p7b Fp8 Draft 131072 | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | N/A | N/A | |
| Qwen2p5 Vl 7B Instruct | Fireworks AI | 0.200 | 0.200 | compare | 128K | 128K | N/A | N/A | |
| Qwen2p5 Vl 72B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 128K | 128K | N/A | N/A | |
| Qwen2p5 Vl 3B Instruct | Fireworks AI | 0.200 | 0.200 | compare | 128K | 128K | N/A | N/A | |
| Qwen2p5 Vl 32B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 128K | 128K | N/A | N/A | |
| Qwen2p5 Math 72B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | N/A | N/A | |
| Qwen2p5 Coder 3B | Fireworks AI | 0.100 | 0.100 | compare | 33K | 33K | N/A | N/A | |
| Qwen2p5 Coder 1p5b | Fireworks AI | 0.100 | 0.100 | compare | 33K | 33K | N/A | N/A | |
| Qwen2p5 Coder 14B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Qwen2p5 Coder 0p5b | Fireworks AI | 0.100 | 0.100 | compare | 33K | 33K | N/A | N/A | |
| Qwen2p5 1p5b Instruct | Fireworks AI | 0.100 | 0.100 | compare | 33K | 33K | N/A | N/A | |
| Qwen2p5 0p5b Instruct | Fireworks AI | 0.100 | 0.100 | compare | 33K | 33K | N/A | N/A | |
| Qwen2 Vl 7B Instruct | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Qwen2 Vl 72B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 33K | 33K | N/A | N/A | |
| Qwen2 Vl 2B Instruct | Fireworks AI | 0.100 | 0.100 | compare | 33K | 33K | N/A | N/A | |
| Qwen2 7B Instruct | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Qwen1p5 72B Chat | Fireworks AI | 0.900 | 0.900 | compare | 33K | 33K | N/A | N/A | |
| Qwen V2p5 7B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | N/A | N/A | |
| Qwen V2p5 14B Instruct | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Pythia 12B | Fireworks AI | 0.200 | 0.200 | compare | 2K | 2K | N/A | N/A | |
| Phind Code Llama 34B V2 | Fireworks AI | 0.900 | 0.900 | compare | 16K | 16K | N/A | N/A | |
| Phind Code Llama 34B Python V1 | Fireworks AI | 0.900 | 0.900 | compare | 16K | 16K | N/A | N/A | |
| Phi 3 Vision 128K Instruct | Fireworks AI | 0.200 | 0.200 | compare | 32K | 32K | N/A | N/A | |
| Phi 2 3B | Fireworks AI | 0.100 | 0.100 | compare | 2K | 2K | N/A | N/A | |
| Openorca 7B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Openhermes 2p5 Mistral 7B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Openhermes 2 Mistral 7B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Nous Hermes Llama2 7B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| Nous Hermes Llama2 70B | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | N/A | N/A | |
| Nous Hermes Llama2 13B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| Nous Hermes 2 Yi 34B | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | N/A | N/A | |
| Nous Hermes 2 Mixtral 8x7B Dpo | Fireworks AI | 0.500 | 0.500 | compare | 33K | 33K | N/A | N/A | |
| Nous Capybara 7B V1p9 | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Mythomax L2 13B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| Mixtral 8x22B Instruct Hf | Fireworks AI | 1.20 | 1.20 | compare | 66K | 66K | N/A | N/A | |
| Mistral Small 24B Instruct 2501 | Fireworks AI | 0.900 | 0.900 | compare | 33K | 33K | N/A | N/A | |
| Mistral Nemo Base 2407 | Fireworks AI | 0.200 | 0.200 | compare | 128K | 128K | N/A | N/A | |
| Mistral 7B Instruct V0p2 | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| Ministral 3 8B Instruct 2512 | Fireworks AI | 0.200 | 0.200 | compare | 256K | 256K | N/A | N/A | |
| Ministral 3 3B Instruct 2512 | Fireworks AI | 0.100 | 0.100 | compare | 256K | 256K | N/A | N/A | |
| Ministral 3 14B Instruct 2512 | Fireworks AI | 0.200 | 0.200 | compare | 256K | 256K | N/A | N/A | |
| Minimax M2p1 | Fireworks AI | 0.300 | 1.20 | compare | 205K | 205K | N/A | N/A | |
| Llava Yi 34B | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | N/A | N/A | |
| Llamaguard 7B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| Llama4 Scout Instruct Basic | Fireworks AI | 0.150 | 0.600 | compare | 131K | 131K | N/A | N/A | |
| Llama4 Maverick Instruct Basic | Fireworks AI | 0.220 | 0.880 | compare | 131K | 131K | N/A | N/A | |
| Llama Guard 3 8B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | N/A | N/A | |
| Llama Guard 3 1B | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | N/A | N/A | |
| Llama Guard 2 8B | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Kat Dev 72B Exp | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | N/A | N/A | |
| Kat Dev 32B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | N/A | N/A | |
| Kat Coder | Fireworks AI | 0.900 | 0.900 | compare | 262K | 262K | N/A | N/A | |
| Internvl3 8B | Fireworks AI | 0.200 | 0.200 | compare | 16K | 16K | N/A | N/A | |
| Internvl3 78B | Fireworks AI | 0.900 | 0.900 | compare | 16K | 16K | N/A | N/A | |
| Internvl3 38B | Fireworks AI | 0.900 | 0.900 | compare | 16K | 16K | N/A | N/A | |
| Hermes 2 Pro Mistral 7B | Fireworks AI | 0.200 | 0.200 | compare | 33K | 33K | N/A | N/A | |
| GPT-oss-safeguard-20b | Fireworks AI | 0.500 | 0.500 | compare | 131K | 131K | N/A | N/A | |
| GPT-oss-safeguard-120b | Fireworks AI | 1.20 | 1.20 | compare | 131K | 131K | N/A | N/A | |
| Glm 4p5 Air | Fireworks AI | 0.220 | 0.880 | compare | 128K | 96K | N/A | N/A | |
| Gemma2 9B It | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Gemma 7B | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Gemma 2B It | Fireworks AI | 0.100 | 0.100 | compare | 8K | 8K | N/A | N/A | |
| Flux 1 Schnell | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | N/A | N/A | |
| Flux 1 Dev Controlnet Union | Fireworks AI | 0.0010 | 0.0010 | compare | 4K | 4K | N/A | N/A | |
| Flux 1 Dev | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | N/A | N/A | |
| Firesearch OCR V6 | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Firellava 13B | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| Firefunction V2 | Fireworks AI | 0.900 | 0.900 | compare | 8K | 8K | N/A | N/A | |
| Firefunction V1 | Fireworks AI | 0.500 | 0.500 | compare | 33K | 33K | N/A | N/A | |
| Fare 20B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | N/A | N/A | |
| ERNIE 4p5 21B A3b Pt | Fireworks AI | 0.100 | 0.100 | compare | 4K | 4K | N/A | N/A | |
| Dolphin 2p6 Mixtral 8x7B | Fireworks AI | 0.500 | 0.500 | compare | 33K | 33K | N/A | N/A | |
| Dolphin 2 9 2 Qwen2 72B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | N/A | N/A | |
| Dobby Unhinged Llama 3 3 70B New | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | N/A | N/A | |
| Dobby Mini Unhinged Plus Llama 3 1 8B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | N/A | N/A | |
| DeepSeek V2 Lite Chat | Fireworks AI | 0.500 | 0.500 | compare | 164K | 164K | N/A | N/A | |
| DeepSeek R1 Distill Qwen 7B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | N/A | N/A | |
| DeepSeek R1 Basic | Fireworks AI | 0.550 | 2.19 | compare | 128K | 20K | N/A | N/A | |
| DeepSeek R1 0528 | Fireworks AI | 3.00 | 8.00 | compare | 160K | 160K | N/A | N/A | |
| DeepSeek Prover V2 | Fireworks AI | 1.20 | 1.20 | compare | 164K | 164K | N/A | N/A | |
| DeepSeek Coder 7B Base V1p5 | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| DeepSeek Coder 7B Base | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| DeepSeek Coder 33B Instruct | Fireworks AI | 0.900 | 0.900 | compare | 16K | 16K | N/A | N/A | |
| DeepSeek Coder 1B Base | Fireworks AI | 0.100 | 0.100 | compare | 16K | 16K | N/A | N/A | |
| Cogito V1 Preview Qwen 32B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | N/A | N/A | |
| Cogito V1 Preview Qwen 14B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | N/A | N/A | |
| Cogito V1 Preview Llama 8B | Fireworks AI | 0.200 | 0.200 | compare | 131K | 131K | N/A | N/A | |
| Cogito V1 Preview Llama 70B | Fireworks AI | 0.900 | 0.900 | compare | 131K | 131K | N/A | N/A | |
| Cogito V1 Preview Llama 3B | Fireworks AI | 0.100 | 0.100 | compare | 131K | 131K | N/A | N/A | |
| Cogito 671B V2 P1 | Fireworks AI | 1.20 | 1.20 | compare | 164K | 164K | N/A | N/A | |
| Codegemma 7B | Fireworks AI | 0.200 | 0.200 | compare | 8K | 8K | N/A | N/A | |
| Codegemma 2B | Fireworks AI | 0.100 | 0.100 | compare | 8K | 8K | N/A | N/A | |
| Code Qwen 1p5 7B | Fireworks AI | 0.200 | 0.200 | compare | 66K | 66K | N/A | N/A | |
| Code Llama 7B | Fireworks AI | 0.200 | 0.200 | compare | 16K | 16K | N/A | N/A | |
| Code Llama 70B | Fireworks AI | 0.900 | 0.900 | compare | 4K | 4K | N/A | N/A | |
| Code Llama 34B | Fireworks AI | 0.900 | 0.900 | compare | 16K | 16K | N/A | N/A | |
| Code Llama 13B | Fireworks AI | 0.200 | 0.200 | compare | 16K | 16K | N/A | N/A | |
| Chronos Hermes 13B V2 | Fireworks AI | 0.200 | 0.200 | compare | 4K | 4K | N/A | N/A | |
| Qwerky QwQ 32B |  Featherless AI | N/A | N/A | compare | 33K | 4K | N/A | N/A | |
| Qwerky 72B | Featherless AI | N/A | N/A | compare | 33K | 4K | N/A | N/A | |
| Eu.twelvelabs.pegasus 1 2 V1 | AWS Bedrock | N/A | 7.50 | compare | N/A | N/A | N/A | N/A | |
| Eu.mistral.pixtral Large 2502 V1 | AWS Bedrock | 2.00 | 6.00 | compare | 128K | 4K | N/A | N/A | |
| Dolphin |  NLP Cloud | 0.500 | 0.500 | compare | 16K | 16K | N/A | N/A | |
| DeepSeek Coder | DeepSeek | 0.140 | 0.280 | compare | 128K | 4K | N/A | N/A | |
| DeepSeek Chat | DeepSeek | 0.280 | 0.420 | compare | 131K | 8K | N/A | N/A | |
| L3.3 70B Euryale V2.3 | DeepInfra | 0.650 | 0.750 | compare | 131K | 131K | N/A | N/A | |
| L3.1 70B Euryale V2.2 | DeepInfra | 0.650 | 0.750 | compare | 131K | 131K | N/A | N/A | |
| L3 8B Lunaris V1 Turbo | DeepInfra | 0.040 | 0.050 | compare | 8K | 8K | N/A | N/A | |
| Qwen3 Coder 480B A35B Instruct Turbo | DeepInfra | 0.290 | 1.20 | compare | 262K | 262K | N/A | N/A | |
| Qwen3 235B A22B Thinking 2507 | DeepInfra | 0.300 | 2.90 | compare | 262K | 262K | N/A | N/A | |
| Qwen2.5 VL 32B Instruct | DeepInfra | 0.200 | 0.600 | compare | 128K | 128K | N/A | N/A | |
| Qwen2.5 7B Instruct | DeepInfra | 0.040 | 0.100 | compare | 33K | 33K | N/A | N/A | |
| Mixtral 8x7B Instruct V0.1 | DeepInfra | 0.400 | 0.400 | compare | 33K | 33K | N/A | N/A | |
| Mistral Small 24B Instruct 2501 | DeepInfra | 0.050 | 0.080 | compare | 33K | 33K | N/A | N/A | |
| Mistral Nemo Instruct 2407 | DeepInfra | 0.020 | 0.040 | compare | 131K | 131K | N/A | N/A | |
| WizardLM 2 8x22B | DeepInfra | 0.480 | 0.480 | compare | 66K | 66K | N/A | N/A | |
| Llama Guard 4 12B | DeepInfra | 0.180 | 0.180 | compare | 164K | 164K | N/A | N/A | |
| Llama Guard 3 8B | DeepInfra | 0.055 | 0.055 | compare | 131K | 131K | N/A | N/A | |
| Llama 4 Scout 17B 16E Instruct | DeepInfra | 0.080 | 0.300 | compare | 328K | 328K | N/A | N/A | |
| Llama 4 Maverick 17B 128E Instruct FP8 | DeepInfra | 0.150 | 0.600 | compare | 1.0M | 1.0M | N/A | N/A | |
| MythoMax L2 13B | DeepInfra | 0.080 | 0.090 | compare | 4K | 4K | N/A | N/A | |
| DeepSeek R1 Turbo | DeepInfra | 1.00 | 3.00 | compare | 41K | 41K | N/A | N/A | |
| DeepSeek R1 0528 Turbo | DeepInfra | 1.00 | 3.00 | compare | 33K | 33K | N/A | N/A | |
| DeepSeek R1 0528 | DeepInfra | 0.500 | 2.15 | compare | 164K | 164K | N/A | N/A | |
| OlmOCR 7B 0725 FP8 | DeepInfra | 0.270 | 1.50 | compare | 16K | 16K | N/A | N/A | |
| Databricks Mpt 7B Instruct | Databricks | 0.500 | N/A | compare | 8K | 8K | N/A | N/A | |
| Databricks Mpt 30B Instruct | Databricks | 1.00 | 1.00 | compare | 8K | 8K | N/A | N/A | |
| Databricks Mixtral 8x7B Instruct | Databricks | 0.500 | 1.00 | compare | 4K | 4K | N/A | N/A | |
| Databricks Llama 4 Maverick | Databricks | 0.500 | 1.50 | compare | 128K | 128K | N/A | N/A | |
| Databricks Claude Sonnet 4 1 | Databricks | 3.00 | 15.00 | compare | 200K | 64K | N/A | N/A | |
| Qwq Plus | DashScope (Alibaba) | 0.800 | 2.40 | compare | 98K | 8K | N/A | N/A | |
| Qwen3 Coder Plus | DashScope (Alibaba) | N/A | N/A | compare | 998K | 66K | N/A | N/A | |
| Qwen3 Coder Plus | DashScope (Alibaba) | N/A | N/A | compare | 998K | 66K | N/A | N/A | |
| Qwen3 Coder Flash | DashScope (Alibaba) | N/A | N/A | compare | 998K | 66K | N/A | N/A | |
| Qwen3 Coder Flash | DashScope (Alibaba) | N/A | N/A | compare | 998K | 66K | N/A | N/A | |
| Qwen Turbo | DashScope (Alibaba) | 0.050 | 0.200 | compare | 1.0M | 16K | N/A | N/A | |
| Qwen Turbo | DashScope (Alibaba) | 0.050 | 0.200 | compare | 1.0M | 8K | N/A | N/A | |
| Qwen Plus | DashScope (Alibaba) | N/A | N/A | compare | 998K | 33K | N/A | N/A | |
| Qwen Plus | DashScope (Alibaba) | N/A | N/A | compare | 998K | 33K | N/A | N/A | |
| Qwen Plus | DashScope (Alibaba) | N/A | N/A | compare | 998K | 33K | N/A | N/A | |
| Qwen Plus | DashScope (Alibaba) | 0.400 | 1.20 | compare | 129K | 16K | N/A | N/A | |
| Qwen Plus | DashScope (Alibaba) | 0.400 | 1.20 | compare | 129K | 16K | N/A | N/A | |
| Qwen Plus | DashScope (Alibaba) | 0.400 | 1.20 | compare | 129K | 8K | N/A | N/A | |
| Qwen Flash | DashScope (Alibaba) | N/A | N/A | compare | 998K | 33K | N/A | N/A | |
| Qwen Flash | DashScope (Alibaba) | N/A | N/A | compare | 998K | 33K | N/A | N/A | |
| Qwen Coder | DashScope (Alibaba) | 0.300 | 1.50 | compare | 1.0M | 16K | N/A | N/A | |
| Command R7b | Cohere | 0.150 | 0.037 | compare | 128K | 4K | N/A | N/A | |
| Command Nightly |  Cohere | 1.00 | 2.00 | compare | 4K | 4K | N/A | N/A | |
| Command Light | Cohere | 0.300 | 0.600 | compare | 4K | 4K | N/A | N/A | |
| Command A | Cohere | 2.50 | 10.00 | compare | 256K | 8K | N/A | N/A | |
| Command | Cohere | 1.00 | 2.00 | compare | 4K | 4K | N/A | N/A | |
| Codestral |  Mistral Codestral | N/A | N/A | compare | 32K | 8K | N/A | N/A | |
| Codestral 2405 | Mistral Codestral | N/A | N/A | compare | 32K | 8K | N/A | N/A | |
| Codechat Bison |  Vertex AI (Code Chat) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Codechat Bison | Vertex AI (Code Chat) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Codechat Bison 32K | Vertex AI (Code Chat) | 0.125 | 0.125 | compare | 32K | 8K | N/A | N/A | |
| Codechat Bison 32K | Vertex AI (Code Chat) | 0.125 | 0.125 | compare | 32K | 8K | N/A | N/A | |
| Codechat Bison | Vertex AI (Code Chat) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Code Gecko |  Vertex AI (Code Text) | 0.125 | 0.125 | compare | 2K | 64 | N/A | N/A | |
| Code Gecko | Vertex AI (Code Text) | 0.125 | 0.125 | compare | 2K | 64 | N/A | N/A | |
| Code Gecko | Vertex AI (Code Text) | 0.125 | 0.125 | compare | 2K | 64 | N/A | N/A | |
| Code Bison32k | Vertex AI (Code Text) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Code Bison | Vertex AI (Code Text) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Code Bison | Vertex AI (Code Text) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Code Bison 32K | Vertex AI (Code Text) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Code Bison | Vertex AI (Code Text) | 0.125 | 0.125 | compare | 6K | 1K | N/A | N/A | |
| Codellama 7B Instruct Awq | Cloudflare Workers AI | 1.92 | 1.92 | compare | 4K | 4K | N/A | N/A | |
| Mistral 7B Instruct V0.1 | Cloudflare Workers AI | 1.92 | 1.92 | compare | 8K | 8K | N/A | N/A | |
| Claude Sonnet 4.6 | Anthropic | 3.00 | 15.00 | compare | 200K | 64K | N/A | 46.4 | |
| Claude Opus 4.6 | Anthropic | 5.00 | 25.00 | compare | 1.0M | 128K | N/A | 47.6 | |
| Chatdolphin | NLP Cloud | 0.500 | 0.500 | compare | 16K | 16K | N/A | N/A | |
| Chat Bison |  Vertex AI (Chat) | 0.125 | 0.125 | compare | 8K | 4K | N/A | N/A | |
| Chat Bison | Vertex AI (Chat) | 0.125 | 0.125 | compare | 8K | 4K | N/A | N/A | |
| Chat Bison 32K | Vertex AI (Chat) | 0.125 | 0.125 | compare | 32K | 8K | N/A | N/A | |
| Chat Bison 32K | Vertex AI (Chat) | 0.125 | 0.125 | compare | 32K | 8K | N/A | N/A | |
| Chat Bison | Vertex AI (Chat) | 0.125 | 0.125 | compare | 8K | 4K | N/A | N/A | |
| Zai Glm 4.7 | Cerebras | 2.25 | 2.75 | compare | 128K | 128K | N/A | N/A | |
| Zai Glm 4.6 | Cerebras | 2.25 | 2.75 | compare | 128K | 128K | N/A | N/A | |
| Mixtral 8x7B Instruct V0 | AWS Bedrock | 0.450 | 0.700 | compare | 32K | 8K | N/A | N/A | |
| Mistral Large 2402 V1 | AWS Bedrock | 8.00 | 24.00 | compare | 32K | 8K | N/A | N/A | |
| Mistral 7B Instruct V0 | AWS Bedrock | 0.150 | 0.200 | compare | 32K | 8K | N/A | N/A | |
| Qwen3 Coder Next | AWS Bedrock | 0.600 | 1.44 | compare | 262K | 8K | N/A | N/A | |
| Moonshotai.kimi K2.5 | AWS Bedrock | 0.720 | 3.60 | compare | 262K | 262K | N/A | N/A | |
| Minimax.minimax M2.1 | AWS Bedrock | 0.360 | 1.44 | compare | 196K | 8K | N/A | N/A | |
| Command Text V14 | AWS Bedrock | N/A | N/A | compare | 4K | 4K | N/A | N/A | |
| Command Light Text V14 | AWS Bedrock | N/A | N/A | compare | 4K | 4K | N/A | N/A | |
| Babbage 002 | OpenAI | 0.400 | 0.400 | compare | 16K | 4K | N/A | N/A | |
| Mistral Large 2402 | Azure OpenAI | 8.00 | 24.00 | compare | 32K | N/A | N/A | N/A | |
| GPT-realtime mini | Azure OpenAI | 0.600 | 2.40 | compare | 32K | 4K | N/A | N/A | |
| GPT-realtime | Azure OpenAI | 4.00 | 16.00 | compare | 32K | 4K | N/A | N/A | |
| GPT-realtime-1.5 | Azure OpenAI | 4.00 | 16.00 | compare | 32K | 4K | N/A | N/A | |
| GPT-audio mini | Azure OpenAI | 0.600 | 2.40 | compare | 128K | 16K | N/A | N/A | |
| GPT-audio | Azure OpenAI | 2.50 | 10.00 | compare | 128K | 16K | N/A | N/A | |
| GPT-audio-1.5 | Azure OpenAI | 2.50 | 10.00 | compare | 128K | 16K | N/A | N/A | |
| GPT-4o-realtime Preview | Azure OpenAI | 5.00 | 20.00 | compare | 128K | 4K | N/A | N/A | |
| GPT-4o-mini-realtime Preview | Azure OpenAI | 0.600 | 2.40 | compare | 128K | 4K | N/A | N/A | |
| GPT-4.1 mini | Azure OpenAI | 0.400 | 1.60 | compare | 1.0M | 33K | N/A | N/A | |
| Container | Azure OpenAI | N/A | N/A | compare | N/A | N/A | N/A | N/A | |
| Computer Use Preview | Azure OpenAI | 3.00 | 12.00 | compare | 8K | 1K | N/A | N/A | |
| Phi 4 Reasoning | Azure AI | 0.125 | 0.500 | compare | 33K | 4K | N/A | N/A | |
| Phi 4 Mini Reasoning | Azure AI | 0.080 | 0.320 | compare | 131K | 4K | N/A | N/A | |
| Phi 3.5 Vision Instruct | Azure AI | 0.130 | 0.520 | compare | 128K | 4K | N/A | N/A | |
| Phi 3.5 MoE Instruct | Azure AI | 0.160 | 0.640 | compare | 128K | 4K | N/A | N/A | |
| Phi 3.5 Mini Instruct | Azure AI | 0.130 | 0.520 | compare | 128K | 4K | N/A | N/A | |
| Phi 3 Small 128K Instruct | Azure AI | 0.150 | 0.600 | compare | 128K | 4K | N/A | N/A | |
| Phi 3 Medium 128K Instruct | Azure AI | 0.170 | 0.680 | compare | 128K | 4K | N/A | N/A | |
| Model Router | Azure AI | 0.140 | N/A | compare | N/A | N/A | N/A | N/A | |
| Mistral Small 2503 | Azure AI | 0.100 | 0.300 | compare | 128K | 128K | N/A | N/A | |
| Mistral Nemo | Azure AI | 0.150 | 0.150 | compare | 131K | 4K | N/A | N/A | |
| Mistral Medium 2505 | Azure AI | 0.400 | 2.00 | compare | 131K | 8K | N/A | N/A | |
| Ministral 3B | Azure AI | 0.040 | 0.040 | compare | 128K | 4K | N/A | N/A | |
| MAI DS R1 | Azure AI | 1.35 | 5.40 | compare | 128K | 8K | N/A | N/A | |
| Llama 4 Scout 17B 16E Instruct | Azure AI | 0.200 | 0.780 | compare | 10.0M | 16K | N/A | N/A | |
| Llama 4 Maverick 17B 128E Instruct FP8 | Azure AI | 1.41 | 0.350 | compare | 1.0M | 16K | N/A | N/A | |
| Kimi K2.5 | Azure AI | 0.600 | 3.00 | compare | 262K | 262K | N/A | N/A | |
| Jamba Instruct | Azure AI | 0.500 | 0.700 | compare | 70K | 4K | N/A | N/A | |
| JAIS 30B Chat | Azure AI | 0.0032 | 0.0097 | compare | 8K | 8K | N/A | N/A | |
| Grok 4 Fast Non Reasoning | Azure AI | 0.200 | 0.500 | compare | 131K | 131K | N/A | N/A | |
| Grok 3 Mini | Azure AI | 0.250 | 1.27 | compare | 131K | 131K | N/A | N/A | |
| Claude Sonnet 4.6 | Azure AI | 3.00 | 15.00 | compare | 200K | 64K | N/A | 46.4 | |
| Claude Opus 4.6 | Azure AI | 5.00 | 25.00 | compare | 200K | 128K | N/A | 47.6 | |
| Mixtral 8x7B Instruct V0.1 | Anyscale | 0.150 | 0.150 | compare | 16K | 16K | N/A | N/A | |
| Mixtral 8x22B Instruct V0.1 | Anyscale | 0.900 | 0.900 | compare | 66K | 66K | N/A | N/A | |
| Mistral 7B Instruct V0.1 | Anyscale | 0.150 | 0.150 | compare | 16K | 16K | N/A | N/A | |
| Zephyr 7B Beta | Anyscale | 0.150 | 0.150 | compare | 16K | 16K | N/A | N/A | |
| Gemma 7B It | Anyscale | 0.150 | 0.150 | compare | 8K | 8K | N/A | N/A | |
| CodeLlama 70B Instruct Hf | Anyscale | 1.00 | 1.00 | compare | 4K | 4K | N/A | N/A | |
| CodeLlama 34B Instruct Hf | Anyscale | 1.00 | 1.00 | compare | 4K | 4K | N/A | N/A | |
| Claude V1 | AWS Bedrock | 8.00 | 24.00 | compare | 100K | 8K | N/A | N/A | |
| Claude Sonnet 4.6 | AWS Bedrock | 3.00 | 15.00 | compare | 200K | 64K | N/A | 46.4 | |
| Claude Opus 4.6 | AWS Bedrock | 5.00 | 25.00 | compare | 1.0M | 128K | N/A | 47.6 | |
| Titan Text Premier V1 | AWS Bedrock | 0.500 | 1.50 | compare | 42K | 32K | N/A | N/A | |
| Titan Text Lite V1 | AWS Bedrock | 0.300 | 0.400 | compare | 42K | 4K | N/A | N/A | |
| Titan Text Express V1 | AWS Bedrock | 1.30 | 1.70 | compare | 42K | 8K | N/A | N/A | |
| Jamba Instruct V1 | AWS Bedrock | 0.500 | 0.700 | compare | 70K | 4K | N/A | N/A | |
| J2 Ultra V1 | AWS Bedrock | 18.80 | 18.80 | compare | 8K | 8K | N/A | N/A | |
| J2 Mid V1 | AWS Bedrock | 12.50 | 12.50 | compare | 8K | 8K | N/A | N/A |