AI model API prices
What each model charges per million tokens, cheapest first on a blended three-to-one input/output rate. The table is machine-read from theOpenRouter registry, which lists provider rates per token; the models we have reported on ourselves carry our own sourcing on their page. Where no rate is published, the cell is blank rather than estimated.
Last checked 30 Oct 2026 · 363 models · cached rates where published
| Model | Vendor | Input | Output | Cached in | Context | Licence | Released |
|---|---|---|---|---|---|---|---|
| Mistral Nemo | Mistral | $0.03 | $0.03 | — | 131K tokens | open weights | |
| Summarize | Scaledown | $0.04 | $0 | — | 1M tokens | ||
| Extract | Scaledown | $0.04 | $0 | — | 1M tokens | ||
| Ling 3.0 Flash | Inclusionai | $0.02 | $0.06 | $0 | 262K tokens | open weights | |
| gpt-oss-20b | OpenAI | $0.02 | $0.09 | $0.01 | 131K tokens | open weights | |
| Llama 3 8B Lunaris | Sao10K | $0.04 | $0.05 | — | 8K tokens | open weights | |
| Nex-N2.5-Mini | Nex Agi | $0.03 | $0.10 | $0 | 262K tokens | open weights | |
| GLM 5.3 Flash | Z.ai | $0.05 | $0.07 | $0.03 | 1.048576M tokens | open weights | |
| GLM Flash Latest | ~Z Ai | $0.05 | $0.07 | $0.03 | 1.048576M tokens | ||
| Qwen3.7 Flash | Alibaba | $0.03 | $0.13 | $0.01 | 1M tokens | ||
| Llama 3.1 8B Instruct | Meta | $0.05 | $0.08 | $0.03 | 131K tokens | open weights | |
| Mistral Small 3 | Mistral | $0.05 | $0.08 | — | 33K tokens | open weights | |
| Schematron V2 Turbo | Inference Net | $0.03 | $0.15 | $0.03 | 128K tokens | open weights | |
| Nova Micro 1.0 | Amazon | $0.04 | $0.14 | — | 128K tokens | ||
| Gemma 3 4B | $0.05 | $0.10 | — | 131K tokens | open weights | ||
| Command R7B | Cohere | $0.04 | $0.15 | — | 128K tokens | ||
| Mercury 2.5 | Inception | $0.04 | $0.15 | $0 | 260K tokens | ||
| Llama 3.2 1B Instruct | Meta | $0.03 | $0.20 | — | 60K tokens | open weights | |
| DeepSeek V4 Flash Latest | ~Deepseek | $0.05 | $0.15 | $0.03 | 1.048576M tokens | ||
| Laguna XS 2.1 | Poolside | $0.06 | $0.12 | $0.03 | 262K tokens | open weights | |
| Gemma 3 12B | $0.05 | $0.15 | — | 131K tokens | open weights | ||
| Hy-MT2-1.8B | Tencent | $0.04 | $0.18 | — | 8K tokens | open weights | |
| Granite 4.2 8B | Ibm Granite | $0.06 | $0.15 | $0.01 | 131K tokens | open weights | |
| MythoMax 13B | Gryphe | $0.08 | $0.11 | — | 8K tokens | open weights | |
| Phi 4 | Microsoft | $0.07 | $0.14 | — | 16K tokens | open weights | |
| Solar Mini 4 | Upstage | $0.05 | $0.20 | $0.01 | 524K tokens | ||
| Ling 3.0 Flash VL | Inclusionai | $0.06 | $0.18 | $0.01 | 131K tokens | open weights | |
| Ternary Bonsai 2 9B | Prism Ml | $0.08 | $0.13 | $0.04 | 262K tokens | open weights | |
| Schematron V2 Small | Inference Net | $0.05 | $0.23 | $0.05 | 128K tokens | open weights | |
| Ministral 3 3B 2512 | Mistral | $0.10 | $0.10 | $0.01 | 131K tokens | open weights | |
| Reka Edge | Rekaai | $0.10 | $0.10 | — | 16K tokens | open weights | |
| Nemotron 3.5 Lightning | Nvidia | $0.07 | $0.20 | $0.04 | 262K tokens | open weights | |
| Nova Lite 1.0 | Amazon | $0.06 | $0.24 | — | 300K tokens | ||
| Nemotron 3 Nano 30B A3B | Nvidia | $0.06 | $0.24 | $0.01 | 262K tokens | open weights | |
| Mistral Small 3.2 24B | Mistral | $0.07 | $0.20 | — | 256K tokens | open weights | |
| Ling 3.1 Flash | Inclusionai | $0.07 | $0.23 | $0.01 | 1M tokens | ||
| Laguna S 2.1 | Poolside | $0.09 | $0.18 | $0.01 | 1.048576M tokens | open weights | |
| Qwen3.5-Flash | Alibaba | $0.07 | $0.26 | — | 1M tokens | ||
| Nex-N2.5-Pro | Nex Agi | $0.07 | $0.25 | $0.01 | 262K tokens | open weights | |
| Llama 3.2 3B Instruct | Meta | $0.05 | $0.33 | — | 131K tokens | open weights | |
| Gemma 4 26B A4B | $0.08 | $0.26 | $0.04 | 262K tokens | open weights | ||
| Qwen3 Coder 30B A3B Instruct | Alibaba | $0.07 | $0.28 | — | 262K tokens | open weights | |
| Qwen2.5 7B Instruct | Alibaba | $0.10 | $0.20 | — | 33K tokens | open weights | |
| UI-TARS 7B | ByteDance | $0.10 | $0.20 | $0.10 | 128K tokens | open weights | |
| Muse Spark 1.3 Contributor | Meta | $0.10 | $0.20 | $0 | 1.048576M tokens | ||
| Muse Spark 1.2 Contributor | Meta | $0.10 | $0.20 | $0 | 1.048576M tokens | ||
| Reka Flash 3 | Rekaai | $0.10 | $0.20 | — | 66K tokens | open weights | |
| Hy-MT2-30B-A3B | Tencent | $0.07 | $0.29 | — | 8K tokens | open weights | |
| Hy-MT2-7B | Tencent | $0.07 | $0.29 | — | 8K tokens | open weights | |
| Qwen3 32B | Alibaba | $0.08 | $0.28 | — | 131K tokens | open weights | |
| Seed 1.6 Flash | Bytedance Seed | $0.07 | $0.30 | — | 262K tokens | ||
| gpt-oss-safeguard-20b | OpenAI | $0.07 | $0.30 | $0.04 | 131K tokens | open weights | |
| GPT-5 Nano | OpenAI | $0.05 | $0.40 | $0.01 | 400K tokens | ||
| GLM 4.7 Flash | Z.ai | $0.06 | $0.40 | — | 200K tokens | open weights | |
| Gemma 3 27B | $0.08 | $0.35 | $0.04 | 131K tokens | open weights | ||
| DeepSeek V4 Flash 0731 | DeepSeek | $0.12 | $0.24 | $0.02 | 1.048576M tokens | open weights | |
| Qwen3 14B | Alibaba | $0.12 | $0.24 | — | 41K tokens | open weights | |
| Ministral 3 8B 2512 | Mistral | $0.15 | $0.15 | $0.01 | 262K tokens | open weights | |
| Qwen3 30B A3B Instruct 2507 | Alibaba | $0.10 | $0.30 | $0.10 | 262K tokens | open weights | |
| Llama 4 Scout | Meta | $0.10 | $0.30 | — | 1.31072M tokens | open weights | |
| Voxtral Small 24B 2507 | Mistral | $0.10 | $0.30 | $0.01 | 33K tokens | open weights | |
| Step 3.5 Flash | StepFun | $0.10 | $0.30 | — | 262K tokens | open weights | |
| Llama 3.3 70B Instruct | Meta | $0.10 | $0.32 | — | 131K tokens | open weights | |
| DeepSeek V4 Flash | DeepSeek | $0.14 | $0.28 | — | — | open weights | |
| Seed-2.0-Mini | Bytedance Seed | $0.10 | $0.40 | — | 262K tokens | ||
| Gemini 2.5 Flash Lite | $0.10 | $0.40 | $0.01 | 1.048576M tokens | |||
| GPT-4.1 Nano | OpenAI | $0.10 | $0.40 | $0.03 | 1.047576M tokens | ||
| MiMo-V2.6-Flash | Xiaomi | $0.14 | $0.28 | $0 | 1.05M tokens | open weights | |
| Llama Guard 4 12B | Meta | $0.18 | $0.18 | — | 164K tokens | open weights | |
| Ternary Bonsai 2 27B | Prism Ml | $0.07 | $0.50 | $0.04 | 262K tokens | open weights | |
| Qwen3.5-9B | Alibaba | $0.17 | $0.25 | — | 262K tokens | open weights | |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | — | — | proprietary | |
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $0.01 | 1M tokens | ||
| Ministral 3 14B 2512 | Mistral | $0.20 | $0.20 | $0.02 | 262K tokens | open weights | |
| Nemotron 3.5 Content Safety | Nvidia | $0.20 | $0.20 | — | 131K tokens | open weights | |
| GPT-6 Luna Pro | OpenAI | $0.10 | $0.50 | $0.01 | 1.05M tokens | ||
| Claude Haiku Latest | ~Anthropic | $0.10 | $0.50 | $0.01 | 1M tokens | ||
| GPT Luna Latest | ~Openai | $0.10 | $0.50 | $0.01 | 1.05M tokens | ||
| Qwen3 235B A22B Instruct 2507 | Alibaba | $0.09 | $0.55 | — | 262K tokens | open weights | |
| LFM2.5-24B-A2B | Liquid AI | $0.05 | $0.70 | $0.03 | 128K tokens | open weights | |
| Qwen3 30B A3B | Alibaba | $0.12 | $0.50 | — | 41K tokens | open weights | |
| Qwen3.8 Omni Flash | Alibaba | $0.15 | $0.47 | $0.02 | 1M tokens | ||
| Qwen3.8 Flash | Alibaba | $0.15 | $0.47 | $0.02 | 1M tokens | open weights | |
| Hy3 | Tencent | $0.13 | $0.53 | $0.03 | 262K tokens | open weights | |
| Qwen3.8-Flash-Next | Alibaba | $0.16 | $0.47 | — | — | proprietary | |
| Nemotron 3.5 Super VL | Nvidia | $0.15 | $0.50 | $0.02 | 1.048576M tokens | open weights | |
| Hunyuan A13B Instruct | Tencent | $0.14 | $0.57 | — | 131K tokens | open weights | |
| Gemma 4 31B | $0.20 | $0.40 | — | 262K tokens | open weights | ||
| Qwen3 VL 30B A3B Instruct | Alibaba | $0.15 | $0.60 | — | 262K tokens | open weights | |
| Command R | Cohere | $0.15 | $0.60 | — | 128K tokens | ||
| DeepSeek V4.1 Flash 1017 | DeepSeek | $0.15 | $0.60 | $0 | 1.048576M tokens | open weights | |
| MiniMax M3.1 Flash | MiniMax | $0.15 | $0.60 | $0.01 | 1.048576M tokens | open weights | |
| Mistral Small 4 | Mistral | $0.15 | $0.60 | $0.01 | 262K tokens | open weights | |
| gpt-oss-120b | OpenAI | $0.15 | $0.60 | $0.07 | 131K tokens | open weights | |
| GPT-4o-mini | OpenAI | $0.15 | $0.60 | $0.07 | 128K tokens | ||
| GPT-4o-mini | OpenAI | $0.15 | $0.60 | $0.07 | 128K tokens | ||
| Solar Pro 4 | Upstage | $0.15 | $0.60 | $0.03 | 524K tokens | ||
| Hy3 preview | Tencent | $0.18 | $0.60 | $0.06 | 262K tokens | open weights | |
| Qwen3 Coder Next | Alibaba | $0.12 | $0.80 | $0.07 | 262K tokens | open weights | |
| Qwen3.6 35B A3B | Alibaba | $0.10 | $0.90 | $0.03 | 262K tokens | open weights | |
| Saba | Mistral | $0.20 | $0.60 | $0.02 | 33K tokens | ||
| Llama 4 Maverick | Meta | $0.19 | $0.65 | $0.05 | 524K tokens | open weights | |
| DeepSeek V3.2 Exp | DeepSeek | $0.27 | $0.41 | — | 164K tokens | open weights | |
| GLM 4.5 Air | Z.ai | $0.13 | $0.85 | $0.03 | 131K tokens | open weights | |
| DeepSeek Flash Latest | ~Deepseek | $0.03 | $1.14 | $0.03 | 1.048576M tokens | ||
| DeepSeek V3.2 | DeepSeek | $0.28 | $0.42 | $0.03 | 164K tokens | open weights | |
| DeepSeek V4 Flash Vision Exp | DeepSeek | $0.22 | $0.65 | $0.01 | 1.048576M tokens | open weights | |
| Mercury 3 | Inception | $0.20 | $0.70 | — | 1M tokens | proprietary | |
| Qwen3 Next 80B A3B Instruct | Alibaba | $0.09 | $1.10 | — | 262K tokens | open weights | |
| Cydonia 24B V4.1 | Thedrummer | $0.30 | $0.50 | $0.15 | 131K tokens | open weights | |
| Qwen3.5-35B-A3B | Alibaba | $0.14 | $1 | $0.05 | 262K tokens | open weights | |
| Qwen2.5 72B Instruct | Alibaba | $0.36 | $0.40 | — | 33K tokens | open weights | |
| Qwen3 VL 8B Instruct | Alibaba | $0.25 | $0.75 | $0.12 | 262K tokens | open weights | |
| Uncensored | Cognitivecomputations | $0.20 | $0.90 | — | 128K tokens | open weights | |
| Mercury 2 | Inception | $0.25 | $0.75 | $0.03 | 128K tokens | ||
| LFM2.5-2.6B | Liquid AI | $0.35 | $0.50 | $0.04 | 128K tokens | open weights | |
| Qwen3 Coder Flash | Alibaba | $0.20 | $0.97 | $0.04 | 1M tokens | ||
| Qwen-Plus | Alibaba | $0.26 | $0.78 | $0.05 | 1M tokens | ||
| Llama 3.1 70B Instruct | Meta | $0.40 | $0.40 | — | 131K tokens | open weights | |
| UnslopNemo 12B | Thedrummer | $0.40 | $0.40 | — | 1.024M tokens | open weights | |
| Mistral Small 3.1 24B | Mistral | $0.35 | $0.56 | — | 128K tokens | open weights | |
| GLM Latest | ~Z Ai | $0.07 | $1.40 | $0.07 | 1.048576M tokens | ||
| Qwen3.6 Flash | Alibaba | $0.19 | $1.13 | — | 1M tokens | ||
| ReMM SLERP 13B | Undi95 | $0.35 | $0.65 | — | 6K tokens | open weights | |
| DeepSeek V3.1 | DeepSeek | $0.25 | $0.95 | $0.13 | 164K tokens | open weights | |
| MiniMax-01 | MiniMax | $0.20 | $1.10 | — | 1.000192M tokens | open weights | |
| Particle-1 | Particle Ai | $0.25 | $1 | $0 | 1.048576M tokens | ||
| Beam 1.0 501B A23B | Reflection | $0.25 | $1 | $0.05 | 1.048576M tokens | open weights | |
| Step 3.7 Flash | StepFun | $0.20 | $1.15 | $0.04 | 262K tokens | open weights | |
| MiniMax M2 | MiniMax | $0.26 | $1.02 | — | 205K tokens | open weights | |
| Codestral 2508 | Mistral | $0.30 | $0.90 | $0.03 | 256K tokens | ||
| GLM 4.6V | Z.ai | $0.30 | $0.90 | $0.06 | 131K tokens | open weights | |
| MAI Code 1.1 Flash | Microsoft | $0.20 | $1.20 | — | — | proprietary | |
| GPT-5.6 Luna Pro | OpenAI | $0.20 | $1.20 | $0.02 | 1.05M tokens | ||
| GPT-5.6 Luna | OpenAI | $0.20 | $1.20 | $0.02 | 1.05M tokens | ||
| DeepSeek V3 | DeepSeek | $0.26 | $1.03 | — | 164K tokens | open weights | |
| DeepSeek V3.1 Terminus | DeepSeek | $0.27 | $1 | — | 164K tokens | open weights | |
| GPT-5.4 Nano | OpenAI | $0.20 | $1.25 | $0.02 | 400K tokens | ||
| Qwen3 VL 30B A3B Thinking | Alibaba | $0.29 | $1 | — | 262K tokens | open weights | |
| Qwen3 Coder 480B A35B | Alibaba | $0.30 | $1 | $0.10 | 262K tokens | open weights | |
| Perceptron Mk1.5 | Perceptron | $0.15 | $1.50 | — | 37K tokens | ||
| Perceptron Mk1 | Perceptron | $0.15 | $1.50 | — | 33K tokens | ||
| Weaver | Mancer | $0.40 | $0.75 | — | 8K tokens | ||
| DeepSeek V3 0324 | DeepSeek | $0.29 | $1.14 | $0.11 | 164K tokens | open weights | |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | — | — | MIT (open weights) | |
| LongCat 2.0 | Meituan | $0.30 | $1.20 | $0.01 | 1.048756M tokens | open weights | |
| Muse Glimmer 30B | Meta | $0.30 | $1.20 | $0.04 | 131K tokens | open weights | |
| MiniMax M3 | MiniMax | $0.30 | $1.20 | $0.06 | 1.048576M tokens | open weights | |
| MiniMax M2.7 | MiniMax | $0.30 | $1.20 | $0.06 | 205K tokens | open weights | |
| MiniMax M2.5 | MiniMax | $0.30 | $1.20 | $0.03 | 205K tokens | open weights | |
| MiniMax M2-her | MiniMax | $0.30 | $1.20 | $0.03 | 66K tokens | ||
| MiniMax M2.1 | MiniMax | $0.30 | $1.20 | $0.03 | 205K tokens | open weights | |
| MiMo-V2.6-Pro | Xiaomi | $0.43 | $0.87 | $0 | 1.05M tokens | open weights | |
| Qwen3.7 Plus | Alibaba | $0.32 | $1.28 | $0.06 | 1M tokens | ||
| Nano Banana 2 Lite | $0.25 | $1.50 | — | 66K tokens | |||
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | $0.03 | 1.048576M tokens | |||
| Gemini 3.1 Flash Lite Preview | $0.25 | $1.50 | $0.03 | 1.048576M tokens | |||
| Qwen3.8 27B | Alibaba | $0.15 | $1.88 | $0.04 | 1M tokens | open weights | |
| Qwen3.5 Plus 2026-02-15 | Alibaba | $0.26 | $1.56 | — | 1M tokens | ||
| GLM 5.3 FlashX | Z.ai | $0.37 | $1.25 | $0.09 | 1.048576M tokens | ||
| Command A+ | Cohere | $0.30 | $1.50 | $0.15 | 192K tokens | ||
| Skyfall 36B V2 | Thedrummer | $0.55 | $0.80 | $0.25 | 33K tokens | open weights | |
| Qwen3 VL 235B A22B Instruct | Alibaba | $0.21 | $1.90 | $0.10 | 262K tokens | open weights | |
| Inkling Small | Thinkingmachines | $0.45 | $1.20 | $0.10 | 524K tokens | open weights | |
| Gemma 2 27B | $0.65 | $0.65 | — | 8K tokens | open weights | ||
| Qwen3.5 Plus 2026-04-20 | Alibaba | $0.30 | $1.80 | — | 1M tokens | ||
| Seed-2.0-Lite | Bytedance Seed | $0.25 | $2 | — | 262K tokens | ||
| Seed 1.6 | Bytedance Seed | $0.25 | $2 | — | 262K tokens | ||
| GPT-5.1-Codex-Mini | OpenAI | $0.25 | $2 | $0.03 | 400K tokens | ||
| GPT-5 Mini | OpenAI | $0.25 | $2 | $0.03 | 400K tokens | ||
| Hermes 3 70B Instruct | Nousresearch | $0.70 | $0.70 | — | 131K tokens | open weights | |
| GPT-4.1 Mini | OpenAI | $0.40 | $1.60 | $0.10 | 1.047576M tokens | ||
| Qwen3.5-122B-A10B | Alibaba | $0.26 | $2.08 | — | 262K tokens | open weights | |
| Qwen3.6 Plus | Alibaba | $0.33 | $1.95 | — | 1M tokens | ||
| Qwen2.5 Coder 32B Instruct | Alibaba | $0.66 | $1 | — | 33K tokens | open weights | |
| Mistral Large 3 2512 | Mistral | $0.50 | $1.50 | $0.05 | 262K tokens | ||
| Devstral 2 2512 | Mistral | $0.40 | $2 | $0.04 | 262K tokens | open weights | |
| Mistral Medium 3.1 | Mistral | $0.40 | $2 | $0.04 | 131K tokens | ||
| Mistral Medium 3 | Mistral | $0.40 | $2 | $0.04 | 131K tokens | ||
| MiMo-V2.5 | Xiaomi | $0.40 | $2 | $0.08 | 1.05M tokens | open weights | |
| MiMo-V2.5-Pro | Xiaomi | $0.48 | $1.80 | $0.10 | 1.05M tokens | open weights | |
| Nemotron 3 Super | Nvidia | $0.30 | $2.40 | $0.15 | 1.048576M tokens | open weights | |
| Qwen3.5-27B | Alibaba | $0.26 | $2.60 | — | 262K tokens | open weights | |
| Nova 2 Lite | Amazon | $0.30 | $2.50 | — | 1M tokens | ||
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | $0.03 | 1.048576M tokens | |||
| Nano Banana | $0.30 | $2.50 | $0.03 | 33K tokens | |||
| Gemini 2.5 Flash | $0.30 | $2.50 | $0.03 | 1.048576M tokens | |||
| Moondream 3 Preview | Moondream | $0.30 | $2.50 | — | 32K tokens | open weights | |
| Moondream 3.1 | Moondream | $0.30 | $2.50 | — | 32K tokens | open weights | |
| Llama 3.1 Euryale 70B v2.2 | Sao10K | $0.85 | $0.85 | — | 131K tokens | open weights | |
| Qwen2.5 VL 72B Instruct | Alibaba | $0.80 | $1 | $0.40 | 128K tokens | open weights | |
| Aion 3.5 Mini | Aion Labs | $0.70 | $1.40 | $0.18 | 262K tokens | ||
| Aion-3.0-Mini | Aion Labs | $0.70 | $1.40 | $0.18 | 131K tokens | ||
| GLM 4.6 | Z.ai | $0.50 | $2 | $0.10 | 205K tokens | open weights | |
| GLM 4.5V | Z.ai | $0.60 | $1.80 | $0.11 | 66K tokens | open weights | |
| GLM 4.7 | Z.ai | $0.54 | $1.98 | $0.10 | 205K tokens | open weights | |
| Morph V3 Fast | Morph | $0.80 | $1.20 | — | 262K tokens | ||
| R1 0528 | DeepSeek | $0.50 | $2.15 | $0.35 | 164K tokens | open weights | |
| Relace Apply 3 | Relace | $0.85 | $1.25 | — | 256K tokens | ||
| GLM 5.3 | Z.ai | $0.08 | $3.60 | $0.08 | 1.048576M tokens | open weights | |
| MiniMax M1 | MiniMax | $0.55 | $2.20 | — | 1M tokens | ||
| DeepSeek V4 Pro 0813 | DeepSeek | $0.66 | $1.98 | $0.02 | 1.048576M tokens | open weights | |
| Aion-2.0 | Aion Labs | $0.80 | $1.60 | $0.20 | 131K tokens | ||
| Aion-RP 1.0 | Aion Labs | $0.80 | $1.60 | — | 33K tokens | ||
| Seed 2.1 Turbo | Bytedance Seed | $0.50 | $2.50 | — | 262K tokens | ||
| Kimi K2.5 | Moonshot | $0.50 | $2.50 | $0.15 | 262K tokens | open weights | |
| Hermes 3 405B Instruct | Nousresearch | $1 | $1 | — | 131K tokens | open weights | |
| Sonar | Perplexity | $1 | $1 | — | 127K tokens | ||
| GLM 4.5 | Z.ai | $0.60 | $2.20 | $0.11 | 131K tokens | open weights | |
| Kimi K2 0711 | Moonshot | $0.57 | $2.30 | — | 131K tokens | open weights | |
| DeepSeek V4 Pro 0423 | DeepSeek | $0.82 | $1.63 | $0.07 | 1.048576M tokens | open weights | |
| Qwen3.6 27B | Alibaba | $0.32 | $3.20 | — | 262K tokens | open weights | |
| Mistral Large 4 | Mistral | $0.70 | $2.10 | $0.07 | 1M tokens | open weights | |
| Mistral Large 4 | Mistral | $0.70 | $2.10 | $0.07 | 1.048576M tokens | open weights | |
| Nemotron 3 Ultra | Nvidia | $0.60 | $2.40 | $0.12 | 262K tokens | open weights | |
| GPT Audio Mini | OpenAI | $0.60 | $2.40 | — | 128K tokens | ||
| Kimi K2 Thinking | Moonshot | $0.60 | $2.50 | $0.15 | 262K tokens | open weights | |
| Kimi K2 0905 | Moonshot | $0.60 | $2.50 | — | 262K tokens | open weights | |
| DeepSeek Pro Latest | ~Deepseek | $0.10 | $4 | $0.10 | 1.048576M tokens | ||
| Seed-2.0-Code | Bytedance Seed | $0.50 | $3 | — | 262K tokens | ||
| Nano Banana 2 | $0.50 | $3 | — | 131K tokens | |||
| Nano Banana 2 | $0.50 | $3 | — | 66K tokens | |||
| Gemini 3 Flash Preview | $0.50 | $3 | $0.05 | 1.048576M tokens | |||
| Morph V3 Large | Morph | $0.90 | $1.90 | — | 262K tokens | ||
| Kimi K2.7 Code | Moonshot | $0.56 | $3.10 | $0.15 | 262K tokens | open weights | |
| Glimpse | Elorian | $0.60 | $3 | $0.06 | 262K tokens | ||
| Qwen3 235B A22B Thinking 2507 | Alibaba | $0.45 | $3.50 | — | 128K tokens | open weights | |
| GPT-3.5 Turbo | OpenAI | $1 | $2 | — | 4K tokens | ||
| Grok Build 0.1 | xAI | $1 | $2 | $0.20 | 256K tokens | ||
| Hy4 preview | Tencent | $0.83 | $2.50 | $0.04 | 1.048576M tokens | open weights | |
| Qwen3.5 397B A17B | Alibaba | $0.50 | $3.60 | $0.30 | 262K tokens | open weights | |
| Kimi K2.6 | Moonshot | $0.65 | $3.41 | $0.15 | 262K tokens | open weights | |
| Nova Pro 1.0 | Amazon | $0.80 | $3.20 | — | 300K tokens | ||
| Pareto 26.10 | Unbiased | $0.80 | $3.20 | $0.03 | 1.048576M tokens | ||
| Pareto Latest | ~Unbiased | $0.80 | $3.20 | $0.03 | 1.048576M tokens | ||
| Step 5 Preview | StepFun | $1 | $2.70 | $0.10 | 1.048576M tokens | open weights | |
| Gemini 3.8 Flash | $0.75 | $3.75 | — | — | proprietary | ||
| Gemini 3.7 Flash | $0.75 | $3.75 | — | — | proprietary | ||
| Gemini 3.6 Flash | $0.75 | $3.75 | $0.07 | 1.048576M tokens | |||
| Hermes 4 405B | Nousresearch | $1 | $3 | $0.20 | 131K tokens | open weights | |
| Relace Search | Relace | $1 | $3 | — | 256K tokens | ||
| Gemini Flash Latest | $0.75 | $3.75 | $0.07 | 1.048576M tokens | |||
| GLM 5 | Z.ai | $1 | $3.20 | $0.20 | 205K tokens | open weights | |
| Grok 4.3 | xAI | $1.25 | $2.50 | $0.20 | 1M tokens | ||
| Grok 4.20 Multi-Agent | xAI | $1.25 | $2.50 | $0.20 | 2M tokens | ||
| Grok 4.20 | xAI | $1.25 | $2.50 | $0.20 | 2M tokens | ||
| GPT-5.4 Mini | OpenAI | $0.75 | $4.50 | $0.07 | 400K tokens | ||
| GPT Mini Latest | ~Openai | $0.75 | $4.50 | $0.07 | 400K tokens | ||
| Sakana Namazu | Sakana | $0.95 | $4 | $0.15 | 262K tokens | ||
| GLM 5.2 | Z.ai | $0.01 | $7 | $0.01 | 1.048576M tokens | open weights | |
| Inkling | Thinkingmachines | $1 | $4.05 | $0.17 | 524K tokens | open weights | |
| GLM 5V Turbo | Z.ai | $1.20 | $4 | $0.24 | 203K tokens | ||
| GLM 5 Turbo | Z.ai | $1.20 | $4 | $0.24 | 203K tokens | ||
| Palmyra X5 | Writer | $0.60 | $6 | — | 1.04M tokens | ||
| GPT-6.1 Terra | OpenAI | $1 | $5 | $0.05 | — | proprietary | |
| Claude Haiku 4.5 | Anthropic | $1 | $5 | $0.10 | 200K tokens | ||
| Muse Spark Open | Meta | $1.25 | $4.25 | $0.15 | 1.048576M tokens | open weights | |
| Muse Spark 1.3 | Meta | $1.25 | $4.25 | $0.15 | 1.048576M tokens | ||
| Muse Spark 1.2 | Meta | $1.25 | $4.25 | $0.15 | 1.048576M tokens | ||
| Muse Spark 1.1 | Meta | $1.25 | $4.25 | $0.15 | 1.048576M tokens | ||
| GPT-6.1 Terra Pro | OpenAI | $1 | $5 | $0.05 | 1.05M tokens | ||
| GPT Terra Latest | ~Openai | $1 | $5 | $0.05 | 1.05M tokens | ||
| GLM 5.1 | Z.ai | $1.40 | $4.40 | $0.26 | 205K tokens | open weights | |
| Qwen3.7 Max | Alibaba | $1.48 | $4.42 | $0.29 | 1M tokens | ||
| GPT-5 Image Mini | OpenAI | $2.50 | $2 | $0.25 | 400K tokens | ||
| Kimi Latest | ~Moonshotai | $0.17 | $9.34 | $0.17 | 1.048576M tokens | ||
| Grok 4.7 | xAI | $2 | $6 | — | — | proprietary | |
| Qwen3.8-Max | Alibaba | $2 | $6 | — | 1M tokens | proprietary | |
| Qwen3.8 Max | Alibaba | $2 | $6 | $0.25 | 1M tokens | ||
| Qwen3.8 2.4T A95B | Alibaba | $2 | $6 | $0.25 | 1.048576M tokens | open weights | |
| Nano Banana 2.1 | $1.50 | $7.50 | — | 66K tokens | |||
| Mistral Medium 3.5 | Mistral | $1.50 | $7.50 | — | 262K tokens | ||
| Mistral Large 2407 | Mistral | $2 | $6 | $0.20 | 131K tokens | ||
| Mixtral 8x22B Instruct | Mistral | $2 | $6 | $0.20 | 66K tokens | open weights | |
| Mistral Large | Mistral | $2 | $6 | $0.20 | 128K tokens | ||
| Fugu Max | Sakana | $2 | $6 | $0.25 | 1M tokens | ||
| Grok 4.6 | xAI | $2 | $6 | $0.50 | 500K tokens | ||
| Grok 4.5 | xAI | $2 | $6 | $0.30 | 500K tokens | ||
| Grok Latest | ~X Ai | $2 | $6 | $0.50 | 500K tokens | ||
| Magnum v4 72B | Anthracite Org | $2.50 | $5 | — | 33K tokens | open weights | |
| GPT-3.5 Turbo 16k | OpenAI | $3 | $4 | — | 16K tokens | ||
| Gemini 3.5 Flash | $1.50 | $9 | $0.15 | 1.048576M tokens | |||
| Gemini 2.5 Pro | $1.25 | $10 | $0.13 | 1.048576M tokens | |||
| Gemini 2.5 Pro Preview 06-05 | $1.25 | $10 | $0.13 | 1.048576M tokens | |||
| GPT-5.1-Codex-Max | OpenAI | $1.25 | $10 | $0.13 | 400K tokens | ||
| GPT-5.1 | OpenAI | $1.25 | $10 | $0.13 | 400K tokens | ||
| GPT-5.1-Codex | OpenAI | $1.25 | $10 | $0.13 | 400K tokens | ||
| GPT-5 | OpenAI | $1.25 | $10 | $0.13 | 400K tokens | ||
| o3 | OpenAI | $2 | $8 | $0.50 | 200K tokens | ||
| GPT-4.1 | OpenAI | $2 | $8 | $0.50 | 1.047576M tokens | ||
| Sonar Reasoning Pro | Perplexity | $2 | $8 | — | 128K tokens | ||
| Sonar Deep Research | Perplexity | $2 | $8 | — | 128K tokens | ||
| Claude Opus 5 | Anthropic | $5 | — | $0.50 | — | proprietary | |
| Aion 3.5 | Aion Labs | $3 | $6 | $0.75 | 262K tokens | ||
| Aion-3.0 | Aion Labs | $3 | $6 | $0.75 | 131K tokens | ||
| Pareto 26.9 | Unbiased | $2.50 | $7.50 | $0.25 | 262K tokens | ||
| Kimi K3 | Moonshot | $0.19 | $15 | $0.18 | 1.048576M tokens | open weights | |
| GPT-6.1 Sol | OpenAI | $2 | $10 | $0.10 | — | proprietary | |
| Claude Sonnet 5 | Anthropic | $2 | $10 | — | — | proprietary | |
| Kimi K3.1 Pro | Moonshot | $2 | $10 | — | — | weights promised | |
| Claude Sonnet 5.5 | Anthropic | $2 | $10 | $0.10 | 1M tokens | ||
| Gemini 4 Argon | $2 | $10 | $0.10 | 1.048576M tokens | |||
| GPT-6.1 Sol Pro | OpenAI | $2 | $10 | $0.10 | 1.05M tokens | ||
| GPT-6 Sol Pro | OpenAI | $2 | $10 | $0.20 | 1.05M tokens | ||
| GPT-6 Sol | OpenAI | $2 | $10 | $0.20 | 1.05M tokens | ||
| Claude Sonnet Latest | ~Anthropic | $2 | $10 | $0.10 | 1M tokens | ||
| Gemini Pro Latest | $2 | $10 | $0.10 | 1.048576M tokens | |||
| GPT Sol Latest | ~Openai | $2 | $10 | $0.10 | 1.05M tokens | ||
| GLM 5.3 Prime | Z.ai | $2.80 | $8.80 | $0.56 | 1M tokens | ||
| Command A | Cohere | $2.50 | $10 | — | 256K tokens | open weights | |
| Command R+ | Cohere | $2.50 | $10 | — | 128K tokens | ||
| GPT Audio | OpenAI | $2.50 | $10 | — | 128K tokens | ||
| GPT-4o | OpenAI | $2.50 | $10 | $1.25 | 128K tokens | ||
| GPT-4o | OpenAI | $2.50 | $10 | $1.25 | 128K tokens | ||
| GPT-4o | OpenAI | $2.50 | $10 | $1.25 | 128K tokens | ||
| Nano Banana Pro | $2 | $12 | $0.20 | 131K tokens | |||
| Gemini 3.1 Pro Preview Custom Tools | $2 | $12 | $0.20 | 1.048576M tokens | |||
| Gemini 3.1 Pro Preview | $2 | $12 | $0.20 | 1.048576M tokens | |||
| Nano Banana Pro | $2 | $12 | $0.20 | 66K tokens | |||
| GPT-5.6 Terra Pro | OpenAI | $2 | $12 | $0.20 | 1.05M tokens | ||
| GPT-5.6 Terra | OpenAI | $2 | $12 | $0.20 | 1.05M tokens | ||
| GPT-5.3-Codex | OpenAI | $1.75 | $14 | $0.17 | 400K tokens | ||
| GPT-5.2-Codex | OpenAI | $1.75 | $14 | $0.17 | 400K tokens | ||
| GPT-5.2 Chat | OpenAI | $1.75 | $14 | $0.17 | 128K tokens | ||
| GPT-5.2 | OpenAI | $1.75 | $14 | $0.17 | 400K tokens | ||
| Nova Premier 1.0 | Amazon | $2.50 | $12.50 | $0.63 | 1M tokens | ||
| MiMo-V2.6-Pro-UltraSpeed | Xiaomi | $4.35 | $8.70 | $0.04 | 1.048576M tokens | ||
| GPT-5.4 | OpenAI | $2.50 | $15 | $0.25 | 1.05M tokens | ||
| Qwen3.8 Max Prime | Alibaba | $4 | $12 | $0.50 | 1M tokens | ||
| Claude Sonnet 4.6 | Anthropic | $3 | $15 | $0.30 | 1M tokens | ||
| Claude Sonnet 4.5 | Anthropic | $3 | $15 | $0.30 | 1M tokens | ||
| Ember-1 | Fireworks | $3 | $15 | $0.30 | 1.048576M tokens | ||
| Sonar Pro Search | Perplexity | $3 | $15 | — | 200K tokens | ||
| Sonar Pro | Perplexity | $3 | $15 | — | 200K tokens | ||
| GPT-4o | OpenAI | $5 | $15 | — | 128K tokens | ||
| Claude Opus 5.5 | Anthropic | $4 | $20 | — | — | proprietary | |
| Muse Wonder | Meta | $4 | $20 | — | — | proprietary | |
| GPT-5.6 Sol Pro | OpenAI | $4 | $20 | $0.40 | 1.05M tokens | ||
| GPT-5.6 Sol | OpenAI | $4 | $20 | $0.40 | 1.05M tokens | ||
| Claude Opus Latest | ~Anthropic | $4 | $20 | $0.20 | 1M tokens | ||
| GPT-5.4 Image 2 | OpenAI | $8 | $15 | $2 | 272K tokens | ||
| Claude Opus 4.8 | Anthropic | $5 | $25 | $0.50 | 1M tokens | ||
| Claude Opus 4.7 | Anthropic | $5 | $25 | $0.50 | 1M tokens | ||
| Claude Opus 4.6 | Anthropic | $5 | $25 | $0.50 | 1M tokens | ||
| Claude Opus 4.5 | Anthropic | $5 | $25 | $0.50 | 200K tokens | ||
| GPT-5 Image | OpenAI | $10 | $10 | $1.25 | 400K tokens | ||
| GPT Chat Latest | OpenAI | $5 | $30 | $0.50 | 400K tokens | ||
| GPT-5.5 | OpenAI | $5 | $30 | $0.50 | 1.05M tokens | ||
| Fugu Ultra v2 | Sakana | $5 | $30 | $0.50 | 1M tokens | ||
| Fugu Ultra | Sakana | $5 | $30 | $0.50 | 1M tokens | ||
| GPT-6 Astra | OpenAI | $10 | $50 | — | — | proprietary | |
| Claude Fable 5.1 | Anthropic | $10 | $50 | $0.25 | — | proprietary | |
| Claude Fable 5 | Anthropic | $10 | $50 | $1 | 1M tokens | ||
| GPT-6 Astra Pro | OpenAI | $10 | $50 | $1 | 1.05M tokens | ||
| Claude Fable Latest | ~Anthropic | $10 | $50 | $0.25 | 1M tokens | ||
| GPT Astra Latest | ~Openai | $10 | $50 | $1 | 1.05M tokens | ||
| Claude Opus 4.1 | Anthropic | $15 | $75 | $1.50 | 200K tokens | ||
| o3 Pro | OpenAI | $20 | $80 | — | 200K tokens | ||
| GPT-4 | OpenAI | $30 | $60 | — | 8K tokens | ||
| GPT-5 Pro | OpenAI | $15 | $120 | — | 400K tokens | ||
| GPT-5.2 Pro | OpenAI | $21 | $168 | — | 400K tokens | ||
| GPT-5.5 Pro | OpenAI | $30 | $180 | — | 1.05M tokens | ||
| GPT-5.4 Pro | OpenAI | $30 | $180 | — | 1.05M tokens |
All prices in US dollars per million tokens. Cache-write rates appear on the model pages where a vendor publishes one.
Head-to-head comparisons
- GPT-6.1 Terra vs GPT-6.1 Sol
- GPT-6.1 Sol vs Claude Sonnet 5
- GPT-6 Astra vs Claude Fable 5.1
- Claude Opus 5.5 vs Muse Wonder
- Gemini 3.8 Flash vs DeepSeek V4.1 Flash
- Qwen3.8-Max vs DeepSeek V4.1 Flash
- Mistral Large 4 vs DeepSeek V4.1 Flash
- Mercury 3 vs Gemini 3.8 Flash
- MAI Code 1.1 Flash vs DeepSeek V4 Flash
- Qwen3.8-Flash-Next vs DeepSeek V4 Flash
- Aion-2.0 vs Aion-RP 1.0
- Aion 3.5 vs Aion-3.0
- Aion 3.5 Mini vs Aion-3.0-Mini
- Claude Fable 5.1 vs Claude Fable 5
- Claude Opus 4.6 vs Claude Opus 4.5
- Claude Opus 4.8 vs Claude Opus 4.7
- Claude Sonnet 4.6 vs Claude Sonnet 4.5
- Claude Sonnet 5 vs Claude Sonnet 5.5
- Command A vs Command R+
- Devstral 2 2512 vs Mistral Medium 3
- Fugu Ultra v2 vs Fugu Ultra
- Nano Banana vs Gemini 2.5 Flash
- Gemini 2.5 Pro vs Gemini 2.5 Pro Preview 06-05
- Nano Banana 2 vs Nano Banana 2
- Gemini 3.1 Flash Lite vs Gemini 3.1 Flash Lite Preview
- Gemini 3.1 Pro Preview vs Nano Banana Pro
- Gemini 3.7 Flash vs Gemini 3.6 Flash
- Nano Banana Pro vs Gemini 3.1 Pro Preview Custom Tools
- GLM 5V Turbo vs GLM 5 Turbo
- GPT-4o vs GPT-4o
- GPT-4o-mini vs GPT-4o-mini
- GPT-5.1 vs GPT-5
- GPT-5.1-Codex-Max vs GPT-5.1-Codex
- GPT-5.1-Codex-Mini vs GPT-5 Mini
- GPT-5.2 Chat vs GPT-5.2
- GPT-5.3-Codex vs GPT-5.2-Codex
- GPT-5.5 Pro vs GPT-5.4 Pro
- GPT-5.6 Luna Pro vs GPT-5.6 Luna
- GPT-5.6 Sol Pro vs GPT-5.6 Sol
- GPT-5.6 Terra Pro vs GPT-5.6 Terra
- GPT-6.1 Sol vs GPT-6.1 Sol Pro
- GPT-6.1 Terra vs GPT-6.1 Terra Pro
- GPT-6 Astra vs GPT-6 Astra Pro
- GPT-6 Luna vs GPT-6 Luna Pro
- GPT-6 Sol Pro vs GPT-6 Sol
- GPT Audio vs GPT-4o
- GPT Chat Latest vs GPT-5.5
- Grok 4.20 Multi-Agent vs Grok 4.20
- Grok 4.6 vs Grok 4.5
- Hy-MT2-30B-A3B vs Hy-MT2-7B
- Kimi K2 Thinking vs Kimi K2 0905
- MiniMax M2.5 vs MiniMax M2.1
- MiniMax M2.7 vs MiniMax M2-her
- Mistral Large 2407 vs Mistral Large
- Mistral Large 4 vs Mistral Large 4
- Mistral Medium 3.5 vs Mixtral 8x22B Instruct
- Moondream 3 Preview vs Moondream 3.1
- Muse Spark 1.2 vs Muse Spark 1.1
- Muse Spark 1.3 Contributor vs Muse Spark 1.2 Contributor
- Muse Spark Open vs Muse Spark 1.3
- o3 vs GPT-4.1
- Perceptron Mk1.5 vs Perceptron Mk1
- Qwen3.8-Max vs Qwen3.8 2.4T A95B
- Qwen3.8 Omni Flash vs Qwen3.8 Flash
- Qwen3 Coder Flash vs Qwen-Plus
- Seed-2.0-Lite vs Seed 1.6
- Sonar Pro Search vs Sonar Pro
- Sonar Reasoning Pro vs Sonar Deep Research
- Summarize vs Extract
- Ministral 3 8B 2512 vs Voxtral Small 24B 2507
- Qwen3 14B vs Qwen3 30B A3B Instruct 2507
- GLM 4.5V vs GLM 4.7
- DeepSeek V3 vs DeepSeek V3.1 Terminus
- Kimi K2.5 vs Kimi K2 0711
- Nemotron 3.5 Lightning vs Nemotron 3 Nano 30B A3B
- Qwen3 Coder 30B A3B Instruct vs Qwen2.5 7B Instruct
- Qwen3.8 27B vs Qwen3.5 Plus 2026-02-15
- Llama 4 Scout vs Llama 3.3 70B Instruct
- Qwen2.5 72B Instruct vs Qwen3 VL 8B Instruct
- Qwen3.5-27B vs Qwen2.5 VL 72B Instruct
- Ministral 3 3B 2512 vs Mistral Small 3.2 24B
- gpt-oss-safeguard-20b vs GPT-5 Nano
- Qwen3 VL 30B A3B Thinking vs Qwen3 Coder 480B A35B
- DeepSeek V3.2 vs DeepSeek V4 Flash Vision Exp
- Qwen3 235B A22B Instruct 2507 vs Qwen3 30B A3B
- MiMo-V2.5 vs MiMo-V2.5-Pro
- Qwen3 Coder Next vs Qwen3.6 35B A3B
- Qwen3 Next 80B A3B Instruct vs Qwen3.5-35B-A3B
- Gemma 3 4B vs Gemma 3 12B
- Llama 3.1 8B Instruct vs Llama 3.2 1B Instruct
- Qwen3.6 Plus vs Qwen2.5 Coder 32B Instruct
- Qwen3.5-Flash vs Qwen3 32B
- Hy3 vs Hunyuan A13B Instruct
- MiniMax-01 vs MiniMax M2
- DeepSeek V4.1 Flash vs DeepSeek V3 0324
- Ling 3.0 Flash VL vs Ling 3.1 Flash
- Qwen3.8-Flash-Next vs Qwen3 VL 30B A3B Instruct
- Reka Edge vs Reka Flash 3
- DeepSeek V4 Flash vs DeepSeek V4 Flash 0731
- Gemma 4 26B A4B vs Gemma 3 27B
How this table is kept
Prices move fast and quietly: OpenAI halved GPT-6.1 Sol and Luna within hours of a rival launch, Anthropic cut cached reads 75% without touching headline rates, and DeepSeek retired V4 Pro rather than reprice it. Each row here is re-checked against the report linked from its model page, and the date at the top of this page is the date of the last pass. If a rate has changed since, the source link is where to check first.