How much does 1 million tokens cost?
A source-backed table of what 1 million tokens costs on each model, for input, cached input and output.
| Model | Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|---|
| North Mini Code cheapest input | Cohere | $0 | n/a | $0 |
| Lyria 3 Clip Preview | $0 | n/a | $0 | |
| Lyria 3 Pro Preview | $0 | n/a | $0 | |
| Devstral Small 2 | Mistral | $0 | n/a | $0 |
| GLM-4.5-Flash | Zhipu AI | $0 | $0 | $0 |
| GLM-4.7-Flash | Zhipu AI | $0 | $0 | $0 |
| text-embedding-3-small | OpenAI | $0.020 | n/a | $0 |
| Qwen3-ASR Flash | Alibaba | $0.035 | n/a | $0.035 |
| Command R7B | Cohere | $0.037 | n/a | $0.15 |
| Command R7B Arabic | Cohere | $0.037 | n/a | $0.15 |
| Ministral 3B (latest) | Mistral | $0.040 | n/a | $0.040 |
| Qwen Flash | Alibaba | $0.050 | n/a | $0.40 |
| Qwen Turbo | Alibaba | $0.050 | n/a | $0.20 |
| GPT-5 Nano | OpenAI | $0.050 | $0.0050 | $0.40 |
| Qwen-Omni Turbo | Alibaba | $0.070 | n/a | $0.27 |
| GLM-4.7-FlashX | Zhipu AI | $0.070 | $0.010 | $0.40 |
| Gemini 2.0 Flash-Lite | $0.075 | n/a | $0.30 | |
| Qwen2.5-Omni 7B | Alibaba | $0.10 | n/a | $0.40 |
| Gemini 2.0 Flash | $0.10 | $0.025 | $0.40 | |
| Gemini 2.5 Flash-Lite | $0.10 | $0.010 | $0.40 | |
| Devstral Small | Mistral | $0.10 | n/a | $0.30 |
| Devstral Small 2505 | Mistral | $0.10 | n/a | $0.30 |
| Ministral 8B (latest) | Mistral | $0.10 | n/a | $0.10 |
| Mistral Embed | Mistral | $0.10 | n/a | $0 |
| Mistral Small 3.2 | Mistral | $0.10 | n/a | $0.30 |
| Voxtral Small (latest) | Mistral | $0.10 | n/a | $0.30 |
| GPT-4.1 nano | OpenAI | $0.10 | $0.025 | $0.40 |
| text-embedding-ada-002 | OpenAI | $0.10 | n/a | $0 |
| text-embedding-3-large | OpenAI | $0.13 | n/a | $0 |
| DeepSeek Chat | DeepSeek | $0.14 | $0.0028 | $0.28 |
| DeepSeek Reasoner | DeepSeek | $0.14 | $0.0028 | $0.28 |
| DeepSeek V4 Flash | DeepSeek | $0.14 | $0.0028 | $0.28 |
| Command R | Cohere | $0.15 | n/a | $0.60 |
| Gemini Embedding 001 | $0.15 | n/a | $0 | |
| Mistral Nemo | Mistral | $0.15 | n/a | $0.15 |
| Mistral Small (latest) | Mistral | $0.15 | n/a | $0.60 |
| Mistral Small 4 | Mistral | $0.15 | n/a | $0.60 |
| Open Mistral Nemo | Mistral | $0.15 | n/a | $0.15 |
| Pixtral 12B | Mistral | $0.15 | n/a | $0.15 |
| GPT-4o mini | OpenAI | $0.15 | $0.075 | $0.60 |
| Qwen-MT Turbo | Alibaba | $0.16 | n/a | $0.49 |
| Qwen2.5 7B Instruct | Alibaba | $0.17 | n/a | $0.70 |
| Qwen3 8B | Alibaba | $0.18 | n/a | $0.70 |
| Qwen3.6 Flash | Alibaba | $0.19 | n/a | $1.13 |
| Qwen3-VL 30B-A3B | Alibaba | $0.20 | n/a | $0.80 |
| Qwen3-VL Plus | Alibaba | $0.20 | n/a | $1.60 |
| Gemini Embedding 2 | $0.20 | n/a | $0 | |
| GPT-5.4 nano | OpenAI | $0.20 | $0.020 | $1.25 |
| GPT-5.6 Luna | OpenAI | $0.20 | $0.020 | $1.20 |
| GLM-4.5-Air | Zhipu AI | $0.20 | $0.030 | $1.10 |
| Qwen-VL Plus | Alibaba | $0.21 | n/a | $0.63 |
| Qwen3.6 35B-A3B | Alibaba | $0.25 | n/a | $1.49 |
| Qwen3.5 35B-A3B | Alibaba | $0.25 | n/a | $2.00 |
| Gemini 3.1 Flash Lite | $0.25 | $0.025 | $1.50 | |
| Gemini 3.1 Flash Lite Preview | $0.25 | $0.025 | $1.50 | |
| Gemini Flash-Lite Latest | $0.25 | $0.025 | $1.50 | |
| Nano Banana 2 Lite | $0.25 | n/a | $30.00 | |
| Mistral 7B | Mistral | $0.25 | n/a | $0.25 |
| GPT-5 Mini | OpenAI | $0.25 | $0.025 | $2.00 |
| Qwen-Omni Turbo Realtime | Alibaba | $0.27 | n/a | $1.07 |
| Qwen3 Coder Flash | Alibaba | $0.30 | n/a | $1.50 |
| Qwen3.5 27B | Alibaba | $0.30 | n/a | $2.40 |
| Gemini 2.5 Flash | $0.30 | $0.030 | $2.50 | |
| Gemini 3.5 Flash Lite | $0.30 | $0.030 | $2.50 | |
| Nano Banana | $0.30 | $0.075 | $30.00 | |
| MiniMax-M2 | MiniMax (minimax.io) | $0.30 | n/a | $1.20 |
| MiniMax-M2.1 | MiniMax (minimax.io) | $0.30 | $0.030 | $1.20 |
| MiniMax-M2.5 | MiniMax (minimax.io) | $0.30 | $0.030 | $1.20 |
| MiniMax-M2.7 | MiniMax (minimax.io) | $0.30 | $0.060 | $1.20 |
| MiniMax-M3 | MiniMax (minimax.io) | $0.30 | $0.060 | $1.20 |
| Codestral (latest) | Mistral | $0.30 | n/a | $0.90 |
| GLM-4.6V | Zhipu AI | $0.30 | n/a | $0.90 |
| Qwen2.5 14B Instruct | Alibaba | $0.35 | n/a | $1.40 |
| Qwen2.5-VL 7B Instruct | Alibaba | $0.35 | n/a | $1.05 |
| Qwen3 14B | Alibaba | $0.35 | n/a | $1.40 |
| Qwen Plus | Alibaba | $0.40 | n/a | $1.20 |
| Qwen3.5 122B-A10B | Alibaba | $0.40 | n/a | $3.20 |
| Qwen3.5 Plus | Alibaba | $0.40 | n/a | $2.40 |
| Devstral 2 | Mistral | $0.40 | n/a | $2.00 |
| Devstral 2 | Mistral | $0.40 | n/a | $2.00 |
| Devstral 2 (latest) | Mistral | $0.40 | n/a | $2.00 |
| Devstral Medium | Mistral | $0.40 | n/a | $2.00 |
| Mistral Medium 3 | Mistral | $0.40 | n/a | $2.00 |
| Mistral Medium 3.1 | Mistral | $0.40 | n/a | $2.00 |
| GPT-4.1 mini | OpenAI | $0.40 | $0.10 | $1.60 |
| Qwen3-Omni Flash | Alibaba | $0.43 | n/a | $1.66 |
| DeepSeek V4 Pro | DeepSeek | $0.43 | $0.0036 | $0.87 |
| Qwen3-Coder 30B-A3B Instruct | Alibaba | $0.45 | n/a | $2.25 |
| Qwen Plus Character (Japanese) | Alibaba | $0.50 | n/a | $1.40 |
| Qwen3-Next 80B-A3B (Thinking) | Alibaba | $0.50 | n/a | $6.00 |
| Qwen3-Next 80B-A3B Instruct | Alibaba | $0.50 | n/a | $2.00 |
| Qwen3.6 Plus | Alibaba | $0.50 | $0.050 | $3.00 |
| Qwen3.7 Plus | Alibaba | $0.50 | $0.050 | $3.00 |
| Gemini 3 Flash Preview | $0.50 | $0.050 | $3.00 | |
| Nano Banana 2 | $0.50 | n/a | $60.00 | |
| Nano Banana 2 | $0.50 | n/a | $60.00 | |
| Magistral Small | Mistral | $0.50 | n/a | $1.50 |
| Mistral Large (latest) | Mistral | $0.50 | n/a | $1.50 |
| Mistral Large 3 | Mistral | $0.50 | n/a | $1.50 |
| GPT-3.5-turbo | OpenAI | $0.50 | $0 | $1.50 |
| Qwen3-Omni Flash Realtime | Alibaba | $0.52 | n/a | $1.99 |
| Qwen3.5 397B-A17B | Alibaba | $0.60 | n/a | $3.60 |
| Qwen3.6 27B | Alibaba | $0.60 | n/a | $3.60 |
| MiniMax-M2.5-highspeed | MiniMax (minimax.io) | $0.60 | $0.060 | $2.40 |
| MiniMax-M2.7-highspeed | MiniMax (minimax.io) | $0.60 | $0.060 | $2.40 |
| Kimi K2 0711 | Moonshot AI | $0.60 | $0.15 | $2.50 |
| Kimi K2 0905 | Moonshot AI | $0.60 | $0.15 | $2.50 |
| Kimi K2 Thinking | Moonshot AI | $0.60 | $0.15 | $2.50 |
| Kimi K2.5 | Moonshot AI | $0.60 | $0.10 | $3.00 |
| GLM-4.5 | Zhipu AI | $0.60 | $0.11 | $2.20 |
| GLM-4.5V | Zhipu AI | $0.60 | n/a | $1.80 |
| GLM-4.6 | Zhipu AI | $0.60 | $0.11 | $2.20 |
| GLM-4.7 | Zhipu AI | $0.60 | $0.11 | $2.20 |
| Qwen2.5 32B Instruct | Alibaba | $0.70 | n/a | $2.80 |
| Qwen3 235B-A22B | Alibaba | $0.70 | n/a | $2.80 |
| Qwen3 32B | Alibaba | $0.70 | n/a | $2.80 |
| Qwen3-VL 235B-A22B | Alibaba | $0.70 | n/a | $2.80 |
| Mixtral 8x7B | Mistral | $0.70 | n/a | $0.70 |
| Qwen-VL OCR | Alibaba | $0.72 | n/a | $0.72 |
| Gemini 3.1 Flash Live Preview | $0.75 | n/a | $4.50 | |
| GPT-5.4 mini | OpenAI | $0.75 | $0.075 | $4.50 |
| Qwen-VL Max | Alibaba | $0.80 | n/a | $3.20 |
| QwQ Plus | Alibaba | $0.80 | n/a | $2.40 |
| Kimi K2.6 | Moonshot AI | $0.95 | $0.16 | $4.00 |
| Kimi K2.7 Code | Moonshot AI | $0.95 | $0.19 | $4.00 |
| Qwen3 Coder Plus | Alibaba | $1.00 | n/a | $5.00 |
| Claude Haiku 4.5 | Anthropic | $1.00 | $0.10 | $5.00 |
| Claude Haiku 4.5 (latest) | Anthropic | $1.00 | $0.10 | $5.00 |
| Gemini Robotics-ER 1.6 Preview | $1.00 | n/a | $5.00 | |
| Grok Build 0.1 | xAI | $1.00 | $0.20 | $2.00 |
| GLM-5 | Zhipu AI | $1.00 | $0.20 | $3.20 |
| o3-mini | OpenAI | $1.10 | $0.55 | $4.40 |
| o4-mini | OpenAI | $1.10 | $0.28 | $4.40 |
| Kimi K2 Thinking Turbo | Moonshot AI | $1.15 | $0.15 | $8.00 |
| QVQ Max | Alibaba | $1.20 | n/a | $4.80 |
| Qwen3 Max | Alibaba | $1.20 | n/a | $6.00 |
| Gemini 2.5 Computer Use Preview 10-2025 | $1.25 | n/a | $10.00 | |
| Gemini 2.5 Pro | $1.25 | $0.13 | $10.00 | |
| Muse Spark 1.1 | Meta | $1.25 | $0.15 | $4.25 |
| GPT-5 | OpenAI | $1.25 | $0.13 | $10.00 |
| GPT-5.1 | OpenAI | $1.25 | $0.13 | $10.00 |
| Grok 4.20 (Non-Reasoning) | xAI | $1.25 | $0.20 | $2.50 |
| Grok 4.20 (Reasoning) | xAI | $1.25 | $0.20 | $2.50 |
| Grok 4.20 Multi-Agent | xAI | $1.25 | $0.20 | $2.50 |
| Grok 4.3 | xAI | $1.25 | $0.20 | $2.50 |
| Qwen3.6 Max Preview | Alibaba | $1.30 | $0.13 | $7.80 |
| Qwen2.5 72B Instruct | Alibaba | $1.40 | n/a | $5.60 |
| GLM-5.1 | Zhipu AI | $1.40 | $0.26 | $4.40 |
| GLM-5.2 | Zhipu AI | $1.40 | $0.26 | $4.40 |
| Qwen3-Coder 480B-A35B Instruct | Alibaba | $1.50 | n/a | $7.50 |
| Gemini 3.5 Flash | $1.50 | $0.15 | $9.00 | |
| Gemini 3.6 Flash | $1.50 | $0.15 | $7.50 | |
| Gemini Flash Latest | $1.50 | $0.15 | $9.00 | |
| Mistral Medium (latest) | Mistral | $1.50 | n/a | $7.50 |
| Mistral Medium 3.5 | Mistral | $1.50 | n/a | $7.50 |
| Qwen Max | Alibaba | $1.60 | n/a | $6.40 |
| GPT-5.2 | OpenAI | $1.75 | $0.17 | $14.00 |
| GPT-5.2 Chat | OpenAI | $1.75 | $0.17 | $14.00 |
| GPT-5.3 Chat (latest) | OpenAI | $1.75 | $0.17 | $14.00 |
| GPT-5.3 Codex | OpenAI | $1.75 | $0.17 | $14.00 |
| GPT-5.3 Codex Spark | OpenAI | $1.75 | $0.17 | $14.00 |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $1.90 | $0.38 | $8.00 |
| Qwen3.8 Max | Alibaba | $2.00 | $0.25 | $6.00 |
| Claude Sonnet 5 | Anthropic | $2.00 | $0.20 | $10.00 |
| Deep Research Max Preview (Apr-21-2026) | $2.00 | $0.20 | $12.00 | |
| Deep Research Preview (Apr-21-2026) | $2.00 | $0.20 | $12.00 | |
| Gemini 3 Pro Preview | $2.00 | $0.20 | $12.00 | |
| Gemini 3.1 Pro Preview | $2.00 | $0.20 | $12.00 | |
| Gemini 3.1 Pro Preview Custom Tools | $2.00 | $0.20 | $12.00 | |
| Nano Banana Pro | $2.00 | n/a | $120.00 | |
| Nano Banana Pro | $2.00 | n/a | $120.00 | |
| Magistral Medium (latest) | Mistral | $2.00 | n/a | $5.00 |
| Mistral Large 2.1 | Mistral | $2.00 | n/a | $6.00 |
| Mixtral 8x22B | Mistral | $2.00 | n/a | $6.00 |
| Pixtral Large (latest) | Mistral | $2.00 | n/a | $6.00 |
| GPT-4.1 | OpenAI | $2.00 | $0.50 | $8.00 |
| GPT-5.6 Terra | OpenAI | $2.00 | $0.20 | $12.00 |
| o3 | OpenAI | $2.00 | $0.50 | $8.00 |
| Grok 4.5 | xAI | $2.00 | $0.30 | $6.00 |
| Kimi K2 Turbo | Moonshot AI | $2.40 | $0.60 | $10.00 |
| Qwen-MT Plus | Alibaba | $2.46 | n/a | $7.37 |
| Qwen3.7 Max | Alibaba | $2.50 | $0.50 | $7.50 |
| Command A | Cohere | $2.50 | n/a | $10.00 |
| Command A Plus | Cohere | $2.50 | n/a | $10.00 |
| Command A Reasoning | Cohere | $2.50 | n/a | $10.00 |
| Command A Translate | Cohere | $2.50 | n/a | $10.00 |
| Command A Vision | Cohere | $2.50 | n/a | $10.00 |
| Command R+ | Cohere | $2.50 | n/a | $10.00 |
| GPT-4o | OpenAI | $2.50 | $1.25 | $10.00 |
| GPT-4o (2024-08-06) | OpenAI | $2.50 | $1.25 | $10.00 |
| GPT-4o (2024-11-20) | OpenAI | $2.50 | $1.25 | $10.00 |
| GPT-5.4 | OpenAI | $2.50 | $0.25 | $15.00 |
| Qwen2.5-VL 72B Instruct | Alibaba | $2.80 | n/a | $8.40 |
| Claude Sonnet 4.5 | Anthropic | $3.00 | $0.30 | $15.00 |
| Claude Sonnet 4.5 (latest) | Anthropic | $3.00 | $0.30 | $15.00 |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $0.30 | $15.00 |
| Kimi K3 | Moonshot AI | $3.00 | $0.30 | $15.00 |
| Gemini 3.5 Live Translate Preview | $3.50 | n/a | $21.00 | |
| GPT-Realtime-2.1 | OpenAI | $4.00 | $0.40 | $24.00 |
| Claude Opus 4.5 | Anthropic | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.5 (latest) | Anthropic | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.6 | Anthropic | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.7 | Anthropic | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.8 | Anthropic | $5.00 | $0.50 | $25.00 |
| Claude Opus 5 | Anthropic | $5.00 | $0.50 | $25.00 |
| GPT-4o (2024-05-13) | OpenAI | $5.00 | n/a | $15.00 |
| GPT-5.5 | OpenAI | $5.00 | $0.50 | $30.00 |
| GPT-5.6 | OpenAI | $5.00 | $0.50 | $30.00 |
| GPT-5.6 Sol | OpenAI | $5.00 | $0.50 | $30.00 |
| GLM-5V-Turbo | Zhipu AI | $5.00 | $1.20 | $22.00 |
| Qwen3-LiveTranslate Flash Realtime | Alibaba | $10.00 | n/a | $10.00 |
| Claude Fable 5 | Anthropic | $10.00 | $1.00 | $50.00 |
| GPT-4 Turbo | OpenAI | $10.00 | n/a | $30.00 |
| Claude Opus 4.1 | Anthropic | $15.00 | $1.50 | $75.00 |
| Claude Opus 4.1 (latest) | Anthropic | $15.00 | $1.50 | $75.00 |
| GPT-5 Pro | OpenAI | $15.00 | n/a | $120.00 |
| o1 | OpenAI | $15.00 | $7.50 | $60.00 |
| o3-pro | OpenAI | $20.00 | n/a | $80.00 |
| GPT-5.2 Pro | OpenAI | $21.00 | n/a | $168.00 |
| GPT-4 | OpenAI | $30.00 | n/a | $60.00 |
| GPT-5.4 Pro | OpenAI | $30.00 | n/a | $180.00 |
| GPT-5.5 Pro | OpenAI | $30.00 | n/a | $180.00 |
| o1-pro | OpenAI | $150.00 | n/a | $600.00 |
Prices per 1M tokens (USD), sorted by input price. Each model links to its official source. See the full pricing table and methodology.
Comparing the cost across providers
The gap between providers for the same million tokens is large: budget models can be over 100 times cheaper than premium ones. But cheaper per token is not always cheaper per task, since a stronger model may solve the job in fewer tokens or one attempt. Use the table to compare, then confirm on your real workload.
FAQ
Why is there such a big price range?
Model size and capability drive cost. Small or open-weight models are cheap to run; flagship reasoning models cost far more per token but often need fewer tokens for hard tasks.