Replicate
Run open-source machine learning models with a cloud API. Inference platform · Community · Image Generation · Open Source · Video Generation
Intelligence vs Price
Best value among Replicate models on this chart: Gemini 3 Pro · GPT-5 · GPT-5 Mini (and 4 more on the dashed frontier). Prices use each model's lowest available Replicate price across regions. Hover any dot for full pricing, or click a creator in the legend to isolate.
Replicate models
40 models in Global, 40 with pricing| Select | Model | Creator | Input Price, $ | Output Price, $ | Context | Max Output | Inference Providers | Intelligence | Coding |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Pro |  Google | 2.00 | 12.00 | 1.0M | 66K | #1 | N/A | ||
| Claude Sonnet 4.5 |  Anthropic | 3.00 | 15.00 | 1.0M | 64K | #2 | #1 | ||
| GPT-5 |  OpenAI | 1.25 | 10.00 | 410K | 128K | #3 | #4 | ||
| Grok 4 |  xAI | 7.20 | 36.00 | 256K | N/A | #4 | N/A | ||
| GPT-5 Mini | OpenAI | 0.25 | 2.00 | 1.0M | 128K | #5 | #14 | ||
| Claude Haiku 4.5 | Anthropic | 1.00 | 5.00 | 200K | 64K | #6 | #2 | ||
| Claude Sonnet 4 | Anthropic | 3.00 | 15.00 | 1.0M | 64K | #7 | #5 | ||
| o4 Mini | OpenAI | 1.00 | 4.00 | 200K | 100K | #8 | N/A | ||
| GPT OSS 120B | OpenAI | 0.18 | 0.72 | 131K | 131K | #9 | #6 | ||
| o1 | OpenAI | 15.00 | 60.00 | 200K | 100K | #11 | #3 | ||
| Claude Sonnet 3.7 | Anthropic | 3.00 | 15.00 | 200K | 128K | #10 | N/A | ||
| DeepSeek V3.1 |  DeepSeek | 0.672 | 2.02 | 164K | 128K | #12 | N/A | ||
| DeepSeek R1 | DeepSeek | 3.75 | 10.00 | 164K | 66K | #13 | #8 | ||
| Gemini 2.5 Flash | Google | 2.50 | 2.50 | 1.0M | 66K | #14 | N/A | ||
| GPT-5 Nano | OpenAI | 0.05 | 0.4 | 5.0M | 128K | #15 | N/A | ||
| GPT-4.1 | OpenAI | 2.00 | 8.00 | 1.0M | 33K | #16 | N/A | ||
| Qwen3 235B A22B Instruct |  Alibaba | 0.264 | 1.06 | 262K | 16K | #17 | N/A | ||
| GPT OSS 20B | OpenAI | 0.09 | 0.36 | 131K | 131K | #18 | #11 | ||
| GPT-4.1 Mini | OpenAI | 0.4 | 1.60 | 1.0M | 33K | #19 | #12 | ||
| DeepSeek V3 | DeepSeek | 1.45 | 1.45 | 164K | 82K | #20 | #10 | ||
| o1 Mini | OpenAI | 1.10 | 4.40 | 128K | 66K | #21 | N/A | ||
| Claude Haiku 3.5 | Anthropic | 1.00 | 5.00 | 200K | 8K | #22 | #13 | ||
| GPT-4o | OpenAI | 2.50 | 10.00 | 131K | 16K | #23 | #9 | ||
| Claude Sonnet 3.5 | Anthropic | 3.75 | 18.75 | 1.0M | 16K | #24 | #7 | ||
| GPT-4.1 Nano | OpenAI | 0.1 | 0.4 | 1.0M | 33K | #25 | #16 | ||
| GPT-4o mini | OpenAI | 0.15 | 0.6 | 131K | 16K | #26 | #15 | ||
| Llama 2 7B Chat |  Meta | 0.05 | 0.25 | 4K | 4K | #27 | N/A | ||
| Llama 3 70B Instruct | Meta | 0.65 | 2.75 | 131K | 8K | #28 | N/A | ||
| Llama 2 70B Chat | Meta | 0.65 | 2.75 | 4K | 4K | #30 | N/A | ||
| Llama 2 13B Chat | Meta | 0.1 | 0.5 | 4K | 4K | #29 | N/A | ||
| Mixtral 8x7B Instruct |  Mistral AI | 0.3 | 1.00 | 33K | 16K | #31 | N/A | ||
| Mistral 7B Instruct | Mistral AI | 0.05 | 0.25 | 127K | 16K | #32 | N/A | ||
| Granite 3.3 8B Instruct |  IBM | 0.03 | 0.25 | 8K | 8K | #33 | N/A | ||
| Llama 3 8B Instruct | Meta | 0.05 | 0.25 | 32K | 8K | #34 | N/A | ||
| Llama 2 13B | Meta | 0.1 | 0.5 | 4K | 4K | N/A | N/A | ||
| Llama 2 70B | Meta | 0.65 | 2.75 | 4K | 4K | N/A | N/A | ||
| Llama 2 7B | Meta | 0.05 | 0.25 | 4K | 4K | N/A | N/A | ||
| Llama 3 70B | Meta | 0.65 | 2.75 | 8K | 8K | N/A | N/A | ||
| Llama 3 8B | Meta | 0.05 | 0.25 | 8K | 8K | N/A | N/A | ||
| Mistral 7B | Mistral AI | 0.05 | 0.25 | 33K | 8K | N/A | N/A |