LLM API pricing
Compare per-token prices across LLM API providers.
LLM market heatmap
3,582 models grouped by vendor — click a vendor, then a family to filter the catalog
Models
| Model | Providers | Input from / 1M | Output from / 1M | Context | Capabilities |
|---|---|---|---|---|---|
| AionLabs: Aion-2.0 | 2 | $0.80/1M tokens | $1.60/1M tokens | — | |
| AionLabs: Aion-3.0 | 2 | $3.00/1M tokens | $6.00/1M tokens | — | |
| Amazon: Nova Lite 1.0 | 2 | $0.06/1M tokens | $0.24/1M tokens | — | |
| Amazon: Nova Micro 1.0 | 2 | $0.04/1M tokens | $0.14/1M tokens | — | |
| Amazon: Nova Premier 1.0 | 2 | $2.50/1M tokens | $12.50/1M tokens | — | |
| Anthropic: Claude 3 Haiku | 2 | $0.25/1M tokens | $1.25/1M tokens | — | |
| Claude Haiku 4.5 | 3 | $1.00/1M tokens | $5.00/1M tokens | — | |
| Anthropic: Claude Opus 4.1 | 2 | $15.00/1M tokens | $75.00/1M tokens | — | |
| Anthropic: Claude Opus 4.5 | 3 | $5.00/1M tokens | $25.00/1M tokens | — | |
| Claude Opus 4.6 | 3 | $5.00/1M tokens | $25.00/1M tokens | — | |
| Anthropic: Claude Sonnet 4 | 2 | $3.00/1M tokens | $15.00/1M tokens | — | |
| Anthropic: Claude Sonnet 4.5 | 2 | $3.00/1M tokens | $15.00/1M tokens | — | |
| Arcee AI: Trinity Large Thinking | 2 | $0.25/1M tokens | $0.80/1M tokens | — | |
| Baichuan M2 Plus | 1 | $1.49/1M tokens | $4.46/1M tokens | — | |
| Baichuan M3 | 1 | $1.49/1M tokens | $4.46/1M tokens | — | |
| Baichuan M3 Plus | 2 | $0.74/1M tokens | $1.34/1M tokens | — | |
| Baichuan Text Embedding | 1 | $0.07/1M tokens | $0.07/1M tokens | — | |
| Baichuan2 53b | 1 | $1.49/1M tokens | $1.49/1M tokens | — | |
| Baichuan2 Turbo | 1 | $1.19/1M tokens | $1.19/1M tokens | — | |
| Baichuan3 Turbo | 1 | $1.78/1M tokens | $1.78/1M tokens | — | |
| Baichuan3 Turbo 128k | 1 | $3.57/1M tokens | $3.57/1M tokens | — | |
| Baichuan4 | 1 | $14.86/1M tokens | $14.86/1M tokens | — | |
| Baichuan4 Air | 1 | $0.15/1M tokens | $0.15/1M tokens | — | |
| Baichuan4 Turbo | 1 | $2.23/1M tokens | $2.23/1M tokens | — | |
| MiniMaxAI MiniMax M2 5 | 1 | $0.30/1M tokens | $1.20/1M tokens | — | |
| Deepseek Ai DeepSeek V3 0324 | 1 | $0.77/1M tokens | $0.77/1M tokens | — | |
| Deepseek Ai DeepSeek V3 1 | 1 | $0.50/1M tokens | $1.50/1M tokens | — | |
| Moonshotai Kimi K2 Instruct 0905 | 1 | $0.60/1M tokens | $2.50/1M tokens | — | |
| Moonshotai Kimi K2 Thinking | 1 | $0.60/1M tokens | $2.50/1M tokens | — | |
| Moonshotai Kimi K2 5 | 1 | $0.60/1M tokens | $3.00/1M tokens | — | |
| Nvidia Nemotron 120B A12B | 1 | $0.30/1M tokens | $0.75/1M tokens | — | |
| Openai Gpt Oss 120b | 1 | $0.10/1M tokens | $0.50/1M tokens | — | |
| Zai Org GLM 4 6 | 1 | $0.60/1M tokens | $2.20/1M tokens | — | |
| Zai Org GLM 4 7 | 1 | $0.60/1M tokens | $2.20/1M tokens | — | |
| Zai Org GLM 5 | 1 | $0.95/1M tokens | $3.15/1M tokens | — | |
| ByteDance Seed: Seed-2.0-Code | 2 | $0.50/1M tokens | $3.00/1M tokens | — | |
| ByteDance Seed: Seed-2.0-Lite | 2 | $0.25/1M tokens | $2.00/1M tokens | — | |
| ByteDance Seed: Seed-2.0-Mini | 2 | $0.10/1M tokens | $0.40/1M tokens | — | |
| Swe 1 6 | 1 | $0.50/1M tokens | $2.50/1M tokens | — | FC |
| Swe 1 7 | 1 | $0.50/1M tokens | $2.50/1M tokens | — | FC |
| Swe 1 7 Lightning | 1 | $2.50/1M tokens | $12.50/1M tokens | — | FC |
| Databricks Qwen3 Next 80b A3b Instruct | 1 | $0.15/1M tokens | $1.20/1M tokens | — | FC |
| DeepSeek: DeepSeek V3 0324 | 2 | $0.24/1M tokens | $0.90/1M tokens | — | |
| DeepSeek: DeepSeek V3.1 | 2 | $0.25/1M tokens | $0.95/1M tokens | — | |
| DeepSeek: DeepSeek V3.2 | 3 | $0.21/1M tokens | $0.31/1M tokens | — | |
| DeepSeek: DeepSeek V4 Flash 0423 | 4 | $0.05/1M tokens | $0.12/1M tokens | — | |
| DeepSeek: DeepSeek V4 Flash 0731 | 3 | $0.03/1M tokens | $0.07/1M tokens | — | |
| DeepSeek: DeepSeek V4 Flash | 1 | $0.36/1M tokens | $1.09/1M tokens | — | |
| Eu Twelvelabs Pegasus 1 2 V1 0 | 1 | Free | $7.50/1M tokens | — | |
| Gemini Robotics Er 2 Streaming Preview | 1 | $2.00/1M tokens | $10.00/1M tokens | — | Vision FC |
| GLM-4-32B-0414-128K | 1 | $0.10/1M tokens | $0.10/1M tokens | — | |
| GLM-4.5 | 1 | $0.60/1M tokens | $2.20/1M tokens | — | |
| GLM-4.5-AirX | 1 | $1.10/1M tokens | $4.50/1M tokens | — | |
| GLM-4.5-Flash | 1 | Free | Free | — | |
| GLM-4.5-X | 1 | $2.20/1M tokens | $8.90/1M tokens | — | |
| GLM-4.5V | 1 | $0.60/1M tokens | $1.80/1M tokens | — | Vision |
| GLM-4.6 | 1 | $0.60/1M tokens | $2.20/1M tokens | — | |
| GLM-4.6V | 1 | $0.30/1M tokens | $0.90/1M tokens | — | Vision |
| GLM-4.6V-Flash | 1 | Free | Free | — | Vision |
| GLM-4.6V-FlashX | 1 | $0.04/1M tokens | $0.40/1M tokens | — | Vision |
| GLM-4.7-Flash | 1 | Free | Free | — | |
| GLM-4.7-FlashX | 2 | $0.07/1M tokens | $0.40/1M tokens | — | |
| GLM-OCR | 1 | $0.03/1M tokens | $0.03/1M tokens | — | Vision |
| Global Twelvelabs Pegasus 1 2 V1 0 | 1 | Free | $7.50/1M tokens | — | |
| Google: Gemini 2.5 Pro Preview 05-06 | 2 | $1.25/1M tokens | $10.00/1M tokens | — | |
| Google: Nano Banana Pro (Gemini 3 Pro Image) | 2 | $2.00/1M tokens | $12.00/1M tokens | — | |
| Google: Gemini 3.5 Flash | 3 | $1.50/1M tokens | $9.00/1M tokens | — | |
| Google: Gemini 3.6 Flash | 3 | $0.75/1M tokens | $3.75/1M tokens | — | |
| Google: Gemma 3 27B | 2 | $0.08/1M tokens | $0.16/1M tokens | — | |
| Google: Gemma 4 26B A4B | 3 | $0.04/1M tokens | $0.22/1M tokens | — | |
| Hunyuan A13b | 2 | $0.07/1M tokens | $0.30/1M tokens | — | |
| Hunyuan Embedding | 1 | $0.10/1M tokens | $0.10/1M tokens | — | |
| Hunyuan T1 Vision | 1 | $0.45/1M tokens | $1.34/1M tokens | — | |
| Hunyuan Translation | 1 | $0.18/1M tokens | $0.53/1M tokens | — | |
| Hunyuan Translation Lite | 1 | $0.15/1M tokens | $0.45/1M tokens | — | |
| Hunyuan Turbos Vision | 1 | $0.45/1M tokens | $1.34/1M tokens | — | |
| Hunyuan Turbos Vision Video | 1 | $0.45/1M tokens | $1.34/1M tokens | — | |
| inclusionAI: Ling 3.0 Flash | 2 | $0.02/1M tokens | $0.06/1M tokens | — | |
| inclusionAI: Ling 3.0 Flash Fin | 2 | Free | Free | — | |
| inclusionAI: Ling 3.0 Flash Sante (free) | 2 | Free | Free | — | |
| Kwaipilot: KAT-Coder-Pro V2 | 2 | $0.30/1M tokens | $1.20/1M tokens | — | |
| Kwaipilot: KAT-Coder-Pro V2.5 | 2 | $0.74/1M tokens | $2.96/1M tokens | — | |
| Meituan: LongCat 2.0 | 1 | Free | Free | — | |
| Meta: Llama 3.1 8B Instruct | 2 | $0.02/1M tokens | $0.04/1M tokens | — | |
| Meta: Llama 3.3 70B Instruct | 2 | $0.10/1M tokens | $0.32/1M tokens | — | |
| Meta: Llama 4 Maverick | 2 | $0.20/1M tokens | $0.70/1M tokens | — | |
| Meta: Llama 4 Scout | 2 | $0.10/1M tokens | $0.30/1M tokens | — | |
| Meta: Muse Spark 1.2 | 4 | $1.25/1M tokens | $4.25/1M tokens | — | |
| Meta: Muse Spark 1.3 | 3 | $1.25/1M tokens | $4.25/1M tokens | — | |
| MiniMax-M2 | 1 | $0.30/1M tokens | $1.20/1M tokens | — | |
| MiniMax-M2.1 | 1 | $0.30/1M tokens | $1.20/1M tokens | — | |
| MiniMax-M2.1-highspeed | 1 | $0.60/1M tokens | $2.40/1M tokens | — | |
| MiniMax-M2.5 | 1 | $0.30/1M tokens | $1.20/1M tokens | — | |
| MiniMax-M2.5-highspeed | 1 | $0.60/1M tokens | $2.40/1M tokens | — | |
| MiniMax-M3 >512k | 1 | $0.60/1M tokens | $2.40/1M tokens | — | |
| MiniMax-M3 ≤512k Permanent 50% off | 1 | $0.30/1M tokens | $1.20/1M tokens | — | |
| MiniMax: MiniMax M2.1 | 2 | $0.30/1M tokens | $1.20/1M tokens | — | |
| MiniMax: MiniMax M2.5 | 3 | $0.27/1M tokens | $0.95/1M tokens | — | |
| MiniMax: MiniMax M2.7 | 3 | $0.21/1M tokens | $0.84/1M tokens | — | |
| MiniMax: MiniMax M3 | 3 | $0.23/1M tokens | $0.96/1M tokens | — |