What is the cheapest AI model for chat?

The cheapest AI chat models are typically smaller models like GPT-3.5-turbo, Claude Instant, or open-source models on platforms like Together AI and Groq. Prices can be as low as $0.10-0.25 per million tokens. However, cheaper models may have reduced capabilities compared to flagship models like GPT-4 or Claude 3 Opus. Use CloudPrice to compare current prices across all providers.

How much does GPT-4 cost?

GPT-4 pricing varies by version. GPT-4 Turbo costs approximately $10 per million input tokens and $30 per million output tokens. GPT-4o is more affordable at around $5/$15 per million tokens. OpenAI also offers GPT-4o-mini at significantly lower prices. Pricing may change, so check CloudPrice for current rates.

What is the difference between input and output tokens?

Input tokens are the text you send to the AI model (your prompts, context, and conversation history). Output tokens are what the model generates in response. Most AI providers charge differently for input and output tokens, with output tokens typically being 2-4x more expensive because they require more computation to generate.

Which AI model has the largest context window?

Google's Gemini 1.5 Pro currently offers one of the largest context windows at 1 million tokens. Anthropic's Claude 3 models support 200K tokens, while OpenAI's GPT-4 Turbo supports 128K tokens. Larger context windows allow processing more text in a single request but may cost more.

What does 'supports vision' mean for AI models?

AI models with vision support can process and understand images in addition to text. You can send images as part of your prompt and the model can describe, analyze, or answer questions about them. Examples include GPT-4 Vision, Claude 3, and Gemini Pro Vision. Vision capabilities typically cost extra per image processed.

AI Models Pricing & Benchmarks Comparison - 1900+ LLM Models

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 1,909 models across 103 providers.

The data is based on LiteLLM, maintained by the open-source community, and benchmark data from Artificial Analysis. The latest update occurred on April 15, 2026 at 12:00 AM UTC

Model	Provider	Input Price, $	Output Price, $	Price Compare	Context	Max Output	Intelligence	Coding
Gemini 3.1 Pro Preview	OpenRouter	2.00	12.00	compare	1.0M	66K	57.2#1	55.5#2
GPT-5.2	OpenRouter	1.75	14.00	compare	272K	128K	51.3#4	48.7#5
Glm 5	OpenRouter	0.800	2.56	compare	203K	128K	49.8#5	44.2#11
GPT-5.2-codex	OpenRouter	1.75	14.00	compare	272K	128K	49.0#7	43.0#13
Gemini 3 Pro Preview	OpenRouter	2.00	12.00	compare	1.0M	66K	48.4#9	46.5#8
Kimi K2.5	OpenRouter	0.600	3.00	compare	262K	262K	46.8#11	39.5#18
Claude Opus 4.6	OpenRouter	5.00	25.00	compare	1.0M	128K	46.5#12	47.6#6
Qwen3.5 397B A17b	OpenRouter	0.600	3.60	compare	262K	66K	45.0#13	41.3#15
GPT-5-codex	OpenRouter	1.25	10.00	compare	272K	128K	44.6#14	38.9#20
GPT-5	OpenRouter	1.25	10.00	compare	272K	128K	44.6#14	36.0#29
Claude Sonnet 4.6	OpenRouter	3.00	15.00	compare	1.0M	128K	44.4#16	46.4#9
Claude Opus 4.5	OpenRouter	5.00	25.00	compare	200K	32K	43.1#18	42.9#14
Glm 4.7	OpenRouter	0.400	1.50	compare	203K	64K	42.1#20	36.3#28
Qwen3.5 27B	OpenRouter	0.300	2.40	compare	262K	66K	42.1#20	34.9#31
Minimax M2.5	OpenRouter	0.300	1.10	compare	197K	66K	41.9#22	37.4#24
Qwen3.5 122B A10b	OpenRouter	0.400	2.00	compare	262K	66K	41.6#24	34.7#32
Grok 4	OpenRouter	3.00	15.00	compare	256K	256K	41.5#25	40.5#16
GPT-5 mini	OpenRouter	0.250	2.00	compare	272K	128K	41.2#26	35.3#30
Qwen3 235B A22b Thinking 2507	OpenRouter	0.110	0.600	compare	262K	262K	39.9#29	30.5#38
Qwen3.5 35B A3b	OpenRouter	0.250	2.00	compare	262K	66K	37.1#32	30.3#39
Claude Sonnet 4.5	OpenRouter	3.00	15.00	compare	1.0M	1.0M	37.1#32	33.5#35
Minimax M2	OpenRouter	0.255	1.02	compare	205K	205K	36.1#34	29.2#44
Claude Opus 4.1	OpenRouter	15.00	75.00	compare	200K	32K	36.0#35	N/A
Gemini 3 Flash Preview	OpenRouter	0.500	3.00	compare	1.0M	66K	35.0#37	37.8#23
GPT-oss-120b	OpenRouter	0.180	0.800	compare	131K	33K	33.3#39	28.6#45
Claude Sonnet 4	OpenRouter	3.00	15.00	compare	1.0M	64K	33.0#41	30.6#37
Claude Opus 4	OpenRouter	15.00	75.00	compare	200K	32K	33.0#41	N/A
DeepSeek V3.2	OpenRouter	0.280	0.400	compare	164K	164K	32.1#43	34.6#33
Claude Haiku 4.5	OpenRouter	1.00	5.00	compare	200K	200K	31.1#46	29.6#43
o1	OpenRouter	15.00	60.00	compare	200K	100K	30.8#48	20.5#71
Claude 3.7 Sonnet	OpenRouter	3.00	15.00	compare	200K	128K	30.8#48	26.7#47
Mimo V2 Flash	OpenRouter	0.090	0.290	compare	262K	16K	30.4#50	25.8#52
Gemini 2.5 Pro	OpenRouter	1.25	10.00	compare	1.0M	8K	30.3#51	46.7#7
Glm 4.6	OpenRouter	0.400	1.75	compare	203K	131K	30.2#52	30.2#40
Glm 4.7 Flash	OpenRouter	0.070	0.400	compare	200K	32K	30.1#53	25.9#50
DeepSeek R1	OpenRouter	0.550	2.19	compare	65K	8K	27.1#60	24.0#57
GPT-5 nano	OpenRouter	0.050	0.400	compare	272K	128K	26.8#62	20.3#73
GPT-4.1	OpenRouter	2.00	8.00	compare	1.0M	33K	26.3#65	21.8#68
o3 mini	OpenRouter	1.10	4.40	compare	128K	66K	25.9#67	17.9#85
Qwen3 235B A22b 2507	OpenRouter	0.071	0.100	compare	262K	262K	25.0#70	22.1#65
GPT-oss-20b	OpenRouter	0.020	0.100	compare	131K	33K	24.5#72	18.5#80
GPT-4.1 mini	OpenRouter	0.400	1.60	compare	1.0M	33K	22.9#80	18.5#80
Gemini 2.5 Flash	OpenRouter	0.300	2.50	compare	1.0M	8K	20.6#88	17.8#86
Gemini 2.0 Flash-001	OpenRouter	0.100	0.400	compare	1.0M	8K	18.5#100	13.6#110
GPT-4o	OpenRouter	2.50	10.00	compare	128K	4K	17.3#109	16.7#88
Ministral 14B 2512	OpenRouter	0.200	0.200	compare	262K	262K	16.0#120	10.9#127
Claude 3.5 Sonnet	OpenRouter	3.00	15.00	compare	200K	8K	15.9#123	30.2#40
Mistral Small 3.2 24B Instruct	OpenRouter	0.100	0.300	compare	32K	N/A	15.1#129	13.3#112
Ministral 8B 2512	OpenRouter	0.150	0.150	compare	262K	262K	14.8#134	10.0#136
Mistral Small 3.1 24B Instruct	OpenRouter	0.100	0.300	compare	32K	N/A	14.5#137	13.9#107
GPT-4.1 nano	OpenRouter	0.100	0.400	compare	1.0M	33K	13.0#153	11.2#122
Qwen 2.5 Coder 32B Instruct	OpenRouter	0.180	0.180	compare	34K	34K	12.9#155	N/A
GPT-4	OpenRouter	30.00	60.00	compare	8K	N/A	12.8#157	13.1#114
Claude 3 Haiku	OpenRouter	0.250	1.25	compare	200K	N/A	12.3#167	6.7#152
Ministral 3B 2512	OpenRouter	0.100	0.100	compare	131K	131K	11.2#176	4.8#158
Mistral Large	OpenRouter	8.00	24.00	compare	32K	N/A	9.9#194	N/A
Mixtral 8x22B Instruct	OpenRouter	0.650	0.650	compare	66K	N/A	9.8#195	N/A
GPT-3.5 Turbo	OpenRouter	1.50	2.00	compare	4K	N/A	9.0#201	10.7#131
Llama 3 70B Instruct	OpenRouter	0.590	0.790	compare	8K	N/A	8.9#204	6.8#151
Mistral 7B Instruct	OpenRouter	0.130	0.130	compare	8K	N/A	7.4#227	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
Qwen3.5 Plus 02 15	OpenRouter	0.400	2.40	compare	1.0M	66K	N/A	N/A
Qwen3.5 Flash 02 23	OpenRouter	0.100	0.400	compare	1.0M	66K	N/A	N/A
Qwen3 Coder Plus	OpenRouter	1.00	5.00	compare	998K	66K	N/A	N/A
Qwen3 Coder	OpenRouter	0.220	0.950	compare	262K	262K	N/A	N/A
Qwen Vl Plus	OpenRouter	0.210	0.630	compare	8K	2K	N/A	N/A
Free	OpenRouter	N/A	N/A	compare	200K	N/A	N/A	N/A
Bodybuilder	OpenRouter	N/A	N/A	compare	128K	N/A	N/A	N/A
Auto	OpenRouter	N/A	N/A	compare	2.0M	N/A	N/A	N/A
GPT-5.2-pro	OpenRouter	21.00	168.00	compare	272K	128K	N/A	N/A
GPT-5.1-codex-max	OpenRouter	1.25	10.00	compare	400K	128K	N/A	N/A
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

AI Models Comparison