Every AI model price, per 1M tokens.
1,557 priced chat models and 1,657 endpoints total, from 32 providers. Compare cost per 1M tokens, prompt-cache rates and context windows — then estimate your own monthly bill in the cost calculator.
From the editor
I read the price diff this pipeline produces every six hours, open the provider page for anything that moves more than a few percent, and write up the part that matters. The arithmetic on this site is generated; the checking and the guides are mine. Start with the analysis or take the whole dataset as CSV — free, CC BY 4.0. — Mohammad Ghonchegi
Largest move in the last diff
Gemini Flash Lite rose 525% to $2.5 per 1M output tokens in the 2026-10-28 refresh.
Priced chat models
1,557
across 32 providers
Cheapest input
$0.01
Qwen2.5 Coder 7B · Nebius
Median input price
$0.6
half of all priced chat models are cheaper
Largest context
2.1M
Gemini Exp 1206
Search the index
Filter by provider, sort by what your workload actually pays for.
| Model | Provider | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| Gemini Exp 1114 | Google Gemini | free | free | 1.0M |
| Gemini Exp 1206 | Google Gemini | free | free | 2.1M |
| Gemma 3 27b It | Google Gemini | free | free | 131K |
| Gemma 4 26b A4b It | Google Gemini | free | free | 262K |
| Gemma 4 31b It | Google Gemini | free | free | 262K |
| Learnlm 1.5 Pro Experimental | Google Gemini | free | free | 33K |
| Labs Leanstral 1 5 | Mistral AI | free | free | 262K |
| Labs Leanstral 1 5 1 | Mistral AI | free | free | 262K |
| Pplx 70b Online | Perplexity | free | $2.8 | 4K |
| Pplx 7b Online | Perplexity | free | $0.28 | 4K |
| Sonar Medium Online | Perplexity | free | $1.8 | 12K |
| Sonar Small Online | Perplexity | free | $0.28 | 12K |
| Gemma 2b It Lora | Cloudflare Workers AI | free | free | 8K |
| Mistral 7b Instruct V0.2 Lora | Cloudflare Workers AI | free | free | 15K |
| Llama 2 7b Chat Hf Lora | Cloudflare Workers AI | free | free | 8K |
| Gemma 7b It Lora | Cloudflare Workers AI | free | free | 4K |
| Codegeex4 | Ollama | free | free | 33K |
| Codegemma | Ollama | free | free | 8K |
| Codellama | Ollama | free | free | 4K |
| Deepseek Coder V2 Base | Ollama | free | free | 8K |
| Deepseek Coder V2 Instruct | Ollama | free | free | 33K |
| Deepseek Coder V2 Lite Base | Ollama | free | free | 8K |
| Deepseek Coder V2 Lite Instruct | Ollama | free | free | 33K |
| Deepseek V3.1:671b Cloud | Ollama | free | free | 164K |
| GPT Oss:120b Cloud | Ollama | free | free | 131K |
| GPT Oss:20b Cloud | Ollama | free | free | 131K |
| Internlm2 5 20b Chat | Ollama | free | free | 33K |
| Llama2 | Ollama | free | free | 4K |
| Llama2 Uncensored | Ollama | free | free | 4K |
| Llama2:13b | Ollama | free | free | 4K |
| Llama2:70b | Ollama | free | free | 4K |
| Llama2:7b | Ollama | free | free | 4K |
| Llama3 | Ollama | free | free | 8K |
| Llama3.1 | Ollama | free | free | 8K |
| Llama3:70b | Ollama | free | free | 8K |
| Llama3:8b | Ollama | free | free | 8K |
| Mistral | Ollama | free | free | 8K |
| Mistral 7B Instruct V0.1 | Ollama | free | free | 8K |
| Mistral 7B Instruct V0.2 | Ollama | free | free | 33K |
| Mistral Large Instruct 2407 | Ollama | free | free | 66K |
| Mixtral 8x22B Instruct V0.1 | Ollama | free | free | 66K |
| Mixtral 8x7B Instruct V0.1 | Ollama | free | free | 33K |
| Orca Mini | Ollama | free | free | 4K |
| Qwen3 Coder:480b Cloud | Ollama | free | free | 262K |
| Vicuna | Ollama | free | free | 2K |
| Ternary Bonsai 27B | Together AI | free | free | 262K |
| Qwen2.5 Coder 7B | Nebius | $0.01 | $0.03 | 33K |
| Qwen2.5 Coder 3B Instruct | Nscale | $0.01 | $0.03 | — |
| Qwen2.5 Coder 7B Instruct | Nscale | $0.01 | $0.03 | — |
| Nemotron 3.5 Lightning 30b A3b | Perplexity | $0.011 | $0.17 | — |
| Granite 4.0 H Micro | Cloudflare Workers AI | $0.017 | $0.112 | 131K |
| Mistral Nemo Instruct 2407 | DeepInfra | $0.019 | $0.03 | 131K |
| Llama 3.2 3B Instruct | DeepInfra | $0.02 | $0.02 | 131K |
| Meta Llama 3.1 8B Instruct Turbo | DeepInfra | $0.02 | $0.04 | 131K |
| Gemma 4 E4B It | DeepInfra | $0.02 | $0.1 | 131K |
| Llama Guard 3 8B | Nebius | $0.02 | $0.06 | 128K |
| Meta Llama 3.1 8B Instruct | Nebius | $0.02 | $0.06 | 128K |
| Qwen2 VL 7B Instruct | Nebius | $0.02 | $0.06 | 131K |
| Paddleocr Vl | Novita AI | $0.02 | $0.02 | 16K |
| Llama 3.1 8b Instruct | Novita AI | $0.02 | $0.05 | 16K |
| Llama 3.2 1b Instruct | Novita AI | $0.02 | $0.02 | 131K |
| Qwen2 1.5B Instruct | Together AI | $0.02 | $0.02 | 33K |
| DeepSeek R1 Distill Llama 8B | Nscale | $0.025 | $0.025 | — |
| Llama 3.2 1b Instruct | Cloudflare Workers AI | $0.027 | $0.201 | 60K |
| Meta Llama 3 8B Instruct | DeepInfra | $0.03 | $0.06 | 8K |
| Meta Llama 3.1 8B Instruct | DeepInfra | $0.03 | $0.05 | 131K |
| GPT Oss 20b | DeepInfra | $0.03 | $0.14 | 131K |
| Llama Prompt Guard 2 22m | Groq | $0.03 | $0.03 | 512 |
| Deepseek Ocr | Novita AI | $0.03 | $0.03 | 8K |
| Qwen3 4b Fp8 | Novita AI | $0.03 | $0.03 | 128K |
| Llama 3.2 3b Instruct | Novita AI | $0.03 | $0.05 | 33K |
| Deepseek Ocr 2 | Novita AI | $0.03 | $0.03 | 8K |
| Llama 3.1 8B Instruct | Nscale | $0.03 | $0.03 | — |
| Granite 3.3 8b Instruct | Replicate | $0.03 | $0.25 | — |
| Autoglm Phone 9b Multilingual | Novita AI | $0.035 | $0.138 | 66K |
| Qwen3 8b Fp8 | Novita AI | $0.035 | $0.138 | 128K |
| GPT Oss 120b | DeepInfra | $0.037 | $0.17 | 131K |
| Qwen2.5 7B Instruct | DeepInfra | $0.04 | $0.1 | 33K |
| L3 8B Lunaris V1 Turbo | DeepInfra | $0.04 | $0.05 | 8K |
| NVIDIA Nemotron Nano 9B V2 | DeepInfra | $0.04 | $0.16 | 131K |
| Llama Prompt Guard 2 86m | Groq | $0.04 | $0.04 | 512 |
| Mistral Nemo Instruct 2407 | Nebius | $0.04 | $0.12 | 128K |
| GPT Oss 20b | Novita AI | $0.04 | $0.15 | 131K |
| Mistral Nemo | Novita AI | $0.04 | $0.17 | 60K |
| Llama 3 8b Instruct | Novita AI | $0.04 | $0.04 | 8K |
| Amazon.nova Micro V1:0 | Amazon Bedrock | $0.042 | $0.168 | 128K |
| Tev1 4B Experimental | Together AI | $0.042 | free | 33K |
| Trinity Mini | Together AI | $0.045 | $0.15 | 128K |
| Llama 3.2 11b Vision Instruct | Cloudflare Workers AI | $0.049 | $0.676 | 128K |
| Llama 3.2 11B Vision Instruct | DeepInfra | $0.049 | $0.049 | 131K |
| Databricks GPT 5 Nano | Databricks | $0.05 | $0.4 | 272K |
| Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | 129K |
| Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | 1M |
| Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | 1M |
| Qwen Turbo | Alibaba DashScope | $0.05 | $0.2 | 1M |
| GPT 5 Nano | OpenAI | $0.05 | $0.4 | 272K |
| GPT 5 Nano | OpenAI | $0.05 | $0.4 | 272K |
| GPT 5 Nano | Perplexity | $0.05 | $0.4 | — |
| GPT 5 Nano | Azure OpenAI | $0.05 | $0.4 | 272K |
| Gemma 3 12b It | DeepInfra | $0.05 | $0.15 | 131K |
| Gemma 3 4b It | DeepInfra | $0.05 | $0.1 | 131K |
| Mistral Small 24B Instruct 2501 | DeepInfra | $0.05 | $0.08 | 33K |
| Nemotron 3 Nano 30B A3B | DeepInfra | $0.05 | $0.2 | 262K |
| Nemotron Lightning 3p5 30b A3b | Fireworks AI | $0.05 | $0.2 | 262K |
| GPT Oss 120b | Novita AI | $0.05 | $0.25 | 131K |
| Gemma 3 12b It | Novita AI | $0.05 | $0.1 | 131K |
| L3 8b Lunaris | Novita AI | $0.05 | $0.05 | 8K |
| L3 8B Stheno V3.2 | Novita AI | $0.05 | $0.05 | 8K |
| Nemotron 3 Nano 30b A3b | Novita AI | $0.05 | $0.2 | 262K |
| Llama 2 7b | Replicate | $0.05 | $0.25 | 4K |
| Llama 2 7b Chat | Replicate | $0.05 | $0.25 | 4K |
| Llama 3 8b | Replicate | $0.05 | $0.25 | 8K |
| Llama 3 8b Instruct | Replicate | $0.05 | $0.25 | 8K |
| Mistral 7b Instruct V0.2 | Replicate | $0.05 | $0.25 | 4K |
| Mistral 7b V0.1 | Replicate | $0.05 | $0.25 | 4K |
| GPT 5 Nano | Replicate | $0.05 | $0.4 | — |
| GPT Oss 20b | Together AI | $0.05 | $0.2 | 131K |
| Llama 3.2 3b Instruct | Cloudflare Workers AI | $0.051 | $0.335 | 80K |
| Qwen3 30b A3b Fp8 | Cloudflare Workers AI | $0.051 | $0.335 | 33K |
| GPT 5 Nano | Azure OpenAI | $0.055 | $0.44 | 272K |
| Llama Guard 3 8B | DeepInfra | $0.055 | $0.055 | 131K |
| GLM 4.7 Flash | DeepInfra | $0.06 | $0.4 | 203K |
| Ling 3.0 Flash | DeepInfra | $0.06 | $0.18 | 131K |
| Qwen2.5 32B Instruct | Nebius | $0.06 | $0.2 | 128K |
| NVIDIA Nemotron 3 Nano 30B A3B | Nebius | $0.06 | $0.24 | 262K |
| Nemotron 3 Nano Omni | Nebius | $0.06 | $0.24 | 262K |
| Nemotron 3 5 Lightning | Nebius | $0.06 | $0.24 | 1.0M |
| Deepseek R1 0528 Qwen3 8b | Novita AI | $0.06 | $0.09 | 128K |
| Ling 3.0 Flash Fast | Novita AI | $0.06 | $0.18 | 262K |
| Ling 3.0 Flash | Novita AI | $0.06 | $0.18 | 262K |
| Qwen2.5 Coder 32B Instruct | Nscale | $0.06 | $0.2 | — |
| NVIDIA Nemotron Nano 9B V2 | Together AI | $0.06 | $0.25 | 131K |
| Llama 3.2 1B Instruct | Together AI | $0.06 | $0.06 | 131K |
| Llama 3.2 3B Instruct | Together AI | $0.06 | $0.06 | 131K |
| Glm 4.7 Flash | Cloudflare Workers AI | $0.06 | $0.4 | 131K |
| Mistral 7b Instruct | Perplexity | $0.07 | $0.28 | 4K |
| Mixtral 8x7b Instruct | Perplexity | $0.07 | $0.28 | 4K |
| Pplx 7b Chat | Perplexity | $0.07 | $0.28 | 8K |
| Sonar Small Chat | Perplexity | $0.07 | $0.28 | 16K |
| Databricks GPT Oss 20b | Databricks | $0.07 | $0.3 | 131K |
| Phi 4 | DeepInfra | $0.07 | $0.14 | 16K |
| Gemma 4 26B A4B It | DeepInfra | $0.07 | $0.34 | 262K |
| GPT Oss 20b | Fireworks AI | $0.07 | $0.3 | 131K |
| Qwen3 Coder 30b A3b Instruct | Novita AI | $0.07 | $0.27 | 160K |
| Ernie 4.5 21B A3b Thinking | Novita AI | $0.07 | $0.28 | 131K |
| Baichuan M2 32b | Novita AI | $0.07 | $0.07 | 131K |
| Ernie 4.5 21B A3b | Novita AI | $0.07 | $0.28 | 120K |
| Qwen2.5 7b Instruct | Novita AI | $0.07 | $0.07 | 32K |
| Glm 4.7 Flash | Novita AI | $0.07 | $0.4 | 200K |
| DeepSeek R1 Distill Qwen 14B | Nscale | $0.07 | $0.07 | — |
| Amazon.nova Lite V1:0 | Amazon Bedrock | $0.072 | $0.288 | 300K |
| Nvidia.nemotron Nano 3 30b | Amazon Bedrock | $0.072 | $0.288 | 262K |
| Nvidia.nemotron Nano 9b V2 | Amazon Bedrock | $0.072 | $0.276 | 128K |
| Mistral Small 3.2 24B Instruct 2506 | DeepInfra | $0.075 | $0.2 | 128K |
| GPT Oss 20b | Groq | $0.075 | $0.3 | 131K |
| GPT Oss Safeguard 20b | Groq | $0.075 | $0.3 | 131K |
| Gemini 2.0 Flash Lite | Google Vertex AI | $0.075 | $0.3 | — |
| Qwen3 32B | DeepInfra | $0.08 | $0.28 | 41K |
| Gemma 3 27b It | DeepInfra | $0.08 | $0.16 | 131K |
| NVIDIA Nemotron 3.5 Lightning | DeepInfra | $0.08 | $0.2 | 262K |
| DeepSeek V4 Flash 0731 | DeepInfra | $0.08 | $0.18 | 1.0M |
| Qwen3 14B | Nebius | $0.08 | $0.24 | 33K |
| Qwen3 4B | Nebius | $0.08 | $0.24 | 33K |
| Qwen3 Vl 8b Instruct | Novita AI | $0.08 | $0.5 | 131K |
| Openai.gpt Oss 20b 1:0 | Amazon Bedrock | $0.084 | $0.36 | 128K |
| NVIDIA Nemotron 3 Super 120B A12B | DeepInfra | $0.085 | $0.4 | 262K |
| Qwen3 235B A22B Instruct 2507 | DeepInfra | $0.09 | $0.55 | 262K |
| Qwen3 Next 80B A3B Instruct | DeepInfra | $0.09 | $1.1 | 262K |
| Gemma 4 31B It Turbo | DeepInfra | $0.09 | $0.34 | 262K |
| DeepSeek V4 Flash | DeepInfra | $0.09 | $0.18 | 1.0M |
| Qwen3 235b A22b Instruct 2507 | Novita AI | $0.09 | $0.58 | 131K |
| Qwen3 30b A3b Fp8 | Novita AI | $0.09 | $0.45 | 41K |
| Mythomax L2 13b | Novita AI | $0.09 | $0.09 | 4K |
| DeepSeek R1 Distill Qwen 1.5B | Nscale | $0.09 | $0.09 | — |
| Llama 4 Scout 17B 16E Instruct | Nscale | $0.09 | $0.29 | — |
| GPT Oss 20b | Replicate | $0.09 | $0.36 | — |
| Claude Haiku 5 5 | Anthropic | $0.1 | $0.5 | 1M |
| Gemini 2.5 Flash Lite | Google Gemini | $0.1 | $0.4 | 1.0M |
| Muse Spark 1.2 Contributor | Meta | $0.1 | $0.2 | 1.0M |
| Muse Spark 1.3 Contributor | Meta | $0.1 | $0.2 | 1.0M |
| Devstral Small | Mistral AI | $0.1 | $0.3 | 256K |
| Ministral 3b 2512 | Mistral AI | $0.1 | $0.1 | 131K |
| Ministral 3b | Mistral AI | $0.1 | $0.1 | 131K |
| Voxtral Small 2507 | Mistral AI | $0.1 | $0.4 | 33K |
| Voxtral Small | Mistral AI | $0.1 | $0.4 | 33K |
| Mistral Small | Mistral AI | $0.1 | $0.3 | 32K |
| Ministral 3 3b 2512 | Mistral AI | $0.1 | $0.1 | 131K |
| GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | 1.0M |
| GPT 4.1 Nano | OpenAI | $0.1 | $0.4 | 1.0M |
| GPT 6 Luna | OpenAI | $0.1 | $0.5 | 922K |
| GPT 6 Luna | Perplexity | $0.1 | $0.5 | — |
| Claude Haiku 5 5 | Perplexity | $0.1 | $0.5 | — |
| GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | 1.0M |
| GPT 4.1 Nano | Azure OpenAI | $0.1 | $0.4 | 1.0M |
| GPT 6 Luna | Azure OpenAI | $0.1 | $0.5 | 922K |
| GPT 6 Luna | Azure OpenAI | $0.1 | $0.5 | 922K |
| GPT Oss 120b | Baseten | $0.1 | $0.5 | 128K |
| Meta.llama3 2 1b Instruct V1:0 | Amazon Bedrock | $0.1 | $0.1 | 128K |
| Us.meta.llama3 2 1b Instruct V1:0 | Amazon Bedrock | $0.1 | $0.1 | 128K |
| Claude Haiku 5 5 | Amazon Bedrock | $0.1 | $0.5 | 1M |
| Llama 3.1 8b | Cerebras | $0.1 | $0.1 | 128K |
| Llama3.1 8b | Cerebras | $0.1 | $0.1 | 128K |
| Gemma 4 26b A4b It | Cloudflare Workers AI | $0.1 | $0.3 | 256K |
| Llama 3.3 70B Instruct Turbo | DeepInfra | $0.1 | $0.32 | 131K |
| Llama 4 Scout 17B 16E Instruct | DeepInfra | $0.1 | $0.3 | 328K |
| Llama 3.3 Nemotron Super 49B V1.5 | DeepInfra | $0.1 | $0.4 | 131K |
| Qwen3.6 35B A3B | DeepInfra | $0.1 | $0.95 | 262K |
| Seed 2.0 Mini | DeepInfra | $0.1 | $0.4 | 256K |
| Qwen3.5 9B | DeepInfra | $0.1 | $0.15 | 262K |
| Llama V3p1 8b Instruct | Fireworks AI | $0.1 | $0.1 | 131K |
| Llama V3p2 1b Instruct | Fireworks AI | $0.1 | $0.1 | 131K |
| Llama V3p2 3b Instruct | Fireworks AI | $0.1 | $0.1 | 131K |
| Codegemma 2b | Fireworks AI | $0.1 | $0.1 | 8K |
| Cogito V1 Preview Llama 3b | Fireworks AI | $0.1 | $0.1 | 131K |
| Deepseek Coder 1b Base | Fireworks AI | $0.1 | $0.1 | 16K |
| Deepseek R1 Distill Qwen 1p5b | Fireworks AI | $0.1 | $0.1 | 131K |
| Ernie 4p5 21b A3b Pt | Fireworks AI | $0.1 | $0.1 | 131K |
| Ernie 4p5 300b A47b Pt | Fireworks AI | $0.1 | $0.1 | 131K |
| Gemma 2b It | Fireworks AI | $0.1 | $0.1 | 8K |
| Llama Guard 3 1b | Fireworks AI | $0.1 | $0.1 | 131K |
| Llama V2 70b | Fireworks AI | $0.1 | $0.1 | 4K |
| Llama V3p1 405b Instruct Long | Fireworks AI | $0.1 | $0.1 | 4K |
| Llama V3p1 70b Instruct 1b | Fireworks AI | $0.1 | $0.1 | 4K |
| Llama V3p2 1b | Fireworks AI | $0.1 | $0.1 | 131K |
| Llama V3p2 3b | Fireworks AI | $0.1 | $0.1 | 131K |
| Minimax M1 80k | Fireworks AI | $0.1 | $0.1 | 4K |
| Ministral 3 3b Instruct 2512 | Fireworks AI | $0.1 | $0.1 | 256K |
| Nemotron Nano V2 12b Vl | Fireworks AI | $0.1 | $0.1 | 131K |
| Phi 2 3b | Fireworks AI | $0.1 | $0.1 | 2K |
| Phi 3 Mini 128k Instruct | Fireworks AI | $0.1 | $0.1 | 131K |
| Qwen2 Vl 2b Instruct | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 0p5b Instruct | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 1p5b Instruct | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 Coder 0p5b | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 Coder 0p5b Instruct | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 Coder 1p5b | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 Coder 1p5b Instruct | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 Coder 3b | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen2p5 Coder 3b Instruct | Fireworks AI | $0.1 | $0.1 | 33K |
| Qwen3 0p6b | Fireworks AI | $0.1 | $0.1 | 41K |
| Qwen3 1p7b | Fireworks AI | $0.1 | $0.1 | 131K |
| Qwen3 1p7b Fp8 Draft | Fireworks AI | $0.1 | $0.1 | 262K |
| Qwen3 1p7b Fp8 Draft 131072 | Fireworks AI | $0.1 | $0.1 | 131K |
| Qwen3 1p7b Fp8 Draft 40960 | Fireworks AI | $0.1 | $0.1 | 41K |
| Stablecode 3b | Fireworks AI | $0.1 | $0.1 | 4K |
| Starcoder2 3b | Fireworks AI | $0.1 | $0.1 | 16K |
| Gemma 3 27b It | Nebius | $0.1 | $0.3 | 110K |
| Llama 3.3 Nemotron Super 49B V1 | Nebius | $0.1 | $0.4 | 131K |
| Qwen3 32B | Nebius | $0.1 | $0.3 | 41K |
| Qwen3 30B A3B | Nebius | $0.1 | $0.3 | 33K |
| Cosmos3 Super Reasoner | Nebius | $0.1 | $0.3 | 262K |
| Qwen3 30B A3B Instruct 2507 | Nebius | $0.1 | $0.3 | 262K |
| Qwen3 32b Fp8 | Novita AI | $0.1 | $0.45 | 41K |
| Llama 2 13b | Replicate | $0.1 | $0.5 | 4K |
| Llama 2 13b Chat | Replicate | $0.1 | $0.5 | 4K |
| GPT 4.1 Nano | Replicate | $0.1 | $0.4 | — |
| Together AI Up To 4b | Together AI | $0.1 | $0.1 | — |
| Qwen 2 1.5b Instruct | Together AI | $0.1 | $0.1 | 33K |
| Mistral Small 24B Instruct 2501 | Together AI | $0.1 | $0.3 | 33K |
| Mimo V2 Flash | Novita AI | $0.11 | $0.33 | 262K |
| Gemma 3 27b It | Novita AI | $0.119 | $0.2 | 98K |
| Anthropic.claude Haiku 5 5 | Amazon Bedrock | $0.12 | $0.6 | 1M |
| Qwen3 14B | DeepInfra | $0.12 | $0.24 | 41K |
| Qwen3 30B A3B | DeepInfra | $0.12 | $0.5 | 41K |
| Hermes 3 Llama 3.1 70B | Hyperbolic | $0.12 | $0.3 | 33K |
| Qwen2.5 72B Instruct | Hyperbolic | $0.12 | $0.3 | 131K |
| Qwen2.5 Coder 32B Instruct | Hyperbolic | $0.12 | $0.3 | 33K |
| Llama 3.2 3B Instruct | Hyperbolic | $0.12 | $0.3 | 33K |
| Llama 3.3 70B Instruct | Hyperbolic | $0.12 | $0.3 | 131K |
| Meta Llama 3 70B Instruct | Hyperbolic | $0.12 | $0.3 | 131K |
| Meta Llama 3.1 405B Instruct | Hyperbolic | $0.12 | $0.3 | 33K |
| Meta Llama 3.1 70B Instruct | Hyperbolic | $0.12 | $0.3 | 33K |
| Meta Llama 3.1 8B Instruct | Hyperbolic | $0.12 | $0.3 | 33K |
| Deepseek V4 Flash 0731 | Perplexity | $0.13 | $0.26 | — |
| DeepSeek V4 Flash 0731 | Baseten | $0.13 | $0.26 | 1.0M |
| Eu.meta.llama3 2 1b Instruct V1:0 | Amazon Bedrock | $0.13 | $0.13 | 128K |
| Gemma 4 31B It | DeepInfra | $0.13 | $0.38 | 262K |
| Llama 3.3 70B Instruct | Nebius | $0.13 | $0.4 | 131K |
| Meta Llama 3.1 70B Instruct | Nebius | $0.13 | $0.4 | 128K |
| Qwen2.5 72B Instruct | Nebius | $0.13 | $0.4 | 128K |
| Qwen2 VL 72B Instruct | Nebius | $0.13 | $0.4 | 131K |
| Hermes 4 70B | Nebius | $0.13 | $0.4 | 131K |
| Glm 4.5 Air | Novita AI | $0.13 | $0.85 | 131K |
| Gemma 4 26b A4b It | Novita AI | $0.13 | $0.4 | 262K |
| Llama 3.3 70b Instruct | Novita AI | $0.135 | $0.4 | 12K |
| Deepseek Coder | DeepSeek | $0.14 | $0.28 | 128K |
| Model Router | Azure OpenAI | $0.14 | free | 200K |
| Databricks Deepseek V4 Flash 0731 | Databricks | $0.14 | $0.28 | 1M |
| Qwen3 Next 80B A3B Thinking | DeepInfra | $0.14 | $1.4 | 262K |
| Qwen3.5 35B A3B | DeepInfra | $0.14 | $1 | 262K |
| Hy3 | DeepInfra | $0.14 | $0.58 | 262K |
| DeepSeek V4.1 Flash | DeepInfra | $0.14 | $0.42 | 1.0M |
| DeepSeek V4.1 Flash 1017 | DeepInfra | $0.14 | $0.42 | 1.0M |
| Deepseek V4 Flash | Fireworks AI | $0.14 | $0.28 | 1.0M |
| DeepSeek V4 Flash | Nebius | $0.14 | $0.28 | 1.0M |
| DeepSeek V4 Flash 0731 | Nebius | $0.14 | $0.28 | 1.0M |
| Hermes 2 Pro Llama 3 8b | Novita AI | $0.14 | $0.14 | 8K |
| Ernie 4.5 Vl 28b A3b | Novita AI | $0.14 | $0.56 | 30K |
| Hy3 | Novita AI | $0.14 | $0.58 | 262K |
| Deepseek V4 Flash | Novita AI | $0.14 | $0.28 | 1.0M |
Showing 300 of 1,557 matching models (25+ interactive results).
Cheapest input tokens
What the input side of your bill costs per 1M tokens.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemini Exp 1114 | Google Gemini | free | free | — | 1.0M |
| 2 | Gemini Exp 1206 | Google Gemini | free | free | — | 2.1M |
| 3 | Gemma 3 27b It | Google Gemini | free | free | — | 131K |
| 4 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 5 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 6 | Learnlm 1.5 Pro Experimental | Google Gemini | free | free | — | 33K |
| 7 | Labs Leanstral 1 5 | Mistral AI | free | free | — | 262K |
| 8 | Labs Leanstral 1 5 1 | Mistral AI | free | free | — | 262K |
| 9 | Pplx 70b Online | Perplexity | free | $2.8 | — | 4K |
| 10 | Pplx 7b Online | Perplexity | free | $0.28 | — | 4K |
| 11 | Sonar Medium Online | Perplexity | free | $1.8 | — | 12K |
| 12 | Sonar Small Online | Perplexity | free | $0.28 | — | 12K |
| 13 | Gemma 2b It Lora | Cloudflare Workers AI | free | free | — | 8K |
| 14 | Mistral 7b Instruct V0.2 Lora | Cloudflare Workers AI | free | free | — | 15K |
| 15 | Llama 2 7b Chat Hf Lora | Cloudflare Workers AI | free | free | — | 8K |
15 models shown — estimate your monthly bill →
Best blended cost
Weighted 3:1 in favour of input, which is how most apps actually bill.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemini Exp 1114 | Google Gemini | free | free | — | 1.0M |
| 2 | Gemini Exp 1206 | Google Gemini | free | free | — | 2.1M |
| 3 | Gemma 3 27b It | Google Gemini | free | free | — | 131K |
| 4 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 5 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 6 | Learnlm 1.5 Pro Experimental | Google Gemini | free | free | — | 33K |
| 7 | Labs Leanstral 1 5 | Mistral AI | free | free | — | 262K |
| 8 | Labs Leanstral 1 5 1 | Mistral AI | free | free | — | 262K |
| 9 | Gemma 2b It Lora | Cloudflare Workers AI | free | free | — | 8K |
| 10 | Mistral 7b Instruct V0.2 Lora | Cloudflare Workers AI | free | free | — | 15K |
| 11 | Llama 2 7b Chat Hf Lora | Cloudflare Workers AI | free | free | — | 8K |
| 12 | Gemma 7b It Lora | Cloudflare Workers AI | free | free | — | 4K |
| 13 | Codegeex4 | Ollama | free | free | — | 33K |
| 14 | Codegemma | Ollama | free | free | — | 8K |
| 15 | Codellama | Ollama | free | free | — | 4K |
15 models shown — estimate your monthly bill →
Cost by use case
Pre-ranked shortlists — each page is computed from the raw dataset, not written by hand.
Cheapest chat APIs
Every chat model with a published price, ranked by blended cost for a typical mix of input and output tokens.…
Cheapest long-context models
Models with at least a 200K-token context window, ranked by input price — for summarising books, legal dumps a…
Cheapest vision models
Models that accept images, sorted by input cost. Useful for OCR, screenshot QA and document extraction at scal…
Cheapest tool-calling models
Models that support function calling, ranked by blended cost — the backbone of agent loops and structured extr…
Cheapest reasoning models
Models flagged as reasoning-capable, sorted by input cost, for maths, planning and multi-step debugging.…
Cheapest cached-input pricing
Models with explicit cache-read pricing — the single biggest lever for high-volume apps that resend the same s…
Cheapest embedding models
Embedding endpoints ranked by price per million tokens, for RAG indexes and semantic search at scale.…
Cheapest model for a customer-support bot
Blended cost estimate for a support bot profile: short prompts, medium answers, high volume, heavy prompt reus…
Cheapest model for summarisation at scale
Ranked for an input-heavy workload (long documents, short summaries), where output tokens matter far less than…
Cheapest models for code generation
Tool-capable models sorted by blended cost — relevant for codegen, refactors and test writing in CI.…
This week in AI pricing
A report compiled every week from the same dataset: which providers moved, what launched, and what the floor of the market costs per 1M tokens. Interpretation and longer analysis live in the guides.
Providers
Model counts and price floors per provider.
Fireworks AIplatform
280 models · from free/1M in
DeepInfraplatform
136 models · from $0.019/1M in
Novita AIplatform
132 models · from $0.01/1M in
Amazon Bedrockplatform
117 models · from $0.02/1M in
OpenAIfirst-party
114 models · from $0.02/1M in
Azure OpenAIplatform
113 models · from $0.022/1M in
Together AIplatform
92 models · from free/1M in
Perplexityfirst-party
79 models · from free/1M in
Nebiusplatform
61 models · from $0.01/1M in
Databricksplatform
58 models · from $0.02/1M in
Mistral AIfirst-party
53 models · from free/1M in
Google Geminifirst-party
43 models · from free/1M in
xAIfirst-party
43 models · from $1/1M in
Replicateplatform
40 models · from $0.03/1M in
Basetenplatform
32 models · from $0.1/1M in
Cloudflare Workers AIplatform
30 models · from free/1M in
Frequently asked
› How often is this pricing data updated?
The dataset is refreshed on an automated schedule (every 6 hours by default) from public provider data and community-maintained price registries. Each model page and the JSON API carry the timestamp of the last successful refresh.
› Where do these numbers come from?
Every price keeps its provenance: each model page lists the upstream sources it was assembled from, and where two independent sources overlap the page shows both so you can see whether they agree. See the methodology page for the full pipeline.
› Is this the price I will actually pay?
No. Providers change prices, add regional multipliers, tiered discounts and minimum commitments. Use these figures to compare models on a like-for-like basis, then confirm with the provider's own pricing page before you commit to a budget.
› Can I use this data in my own project?
Yes — the JSON API at /api/models is free to read, and llms.txt plus llms-full.txt expose the same dataset for AI agents. Attribution is appreciated.