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 |
|---|---|---|---|---|---|
| Cohere: North Mini Code (free) | 1 | Free | Free | 256,000 | FC Reasoning |
| Dots Studio: Dots3-Note Preview (free) | 1 | Free | Free | 512,000 | Vision FC Reasoning |
| Google: Gemma 4 26B A4B (free) | 1 | Free | Free | 262,144 | Vision FC Reasoning |
| Google: Gemma 4 31B (free) | 1 | Free | Free | 262,144 | Vision FC Reasoning |
| Google: Lyria 3 Clip Preview | 1 | Free | Free | 1,048,576 | Vision |
| Google: Lyria 3 Pro Preview | 1 | Free | Free | 1,048,576 | Vision |
| inclusionAI: Ling 3.0 Flash Fin (free) | 1 | Free | Free | 262,144 | FC Reasoning |
| inclusionAI: Ling 3.0 Flash Sante (free) | 1 | Free | Free | 262,144 | FC Reasoning |
| inclusionAI: Ling 3.0 Flash VL (free) | 1 | Free | Free | 262,144 | Vision FC Reasoning |
| LiquidAI: LFM2.5-2.6B (free) | 1 | Free | Free | 65,536 | FC Reasoning |
| Nex AGI: Nex-N2.5-Mini (free) | 1 | Free | Free | 262,144 | Vision FC Reasoning |
| Nex AGI: Nex-N2.5-Pro (free) | 1 | Free | Free | 262,144 | Vision FC Reasoning |
| NVIDIA: Nemotron 3 Nano Omni (free) | 1 | Free | Free | 256,000 | Vision FC Reasoning |
| NVIDIA: Nemotron 3 Super (free) | 1 | Free | Free | 262,144 | FC Reasoning |
| NVIDIA: Nemotron 3 Ultra (free) | 1 | Free | Free | 1,000,000 | FC Reasoning |
| NVIDIA: Nemotron 3.5 Content Safety (free) | 1 | Free | Free | 128,000 | Vision Reasoning |
| NVIDIA: Nemotron 3.5 Lightning (free) | 1 | Free | Free | 1,000,000 | FC Reasoning |
| Free Models Router | 1 | Free | Free | 200,000 | Vision FC Reasoning |
| Poolside: Laguna S 2.1 (free) | 1 | Free | Free | 262,144 | FC Reasoning |
| Poolside: Laguna XS 2.1 (free) | 1 | Free | Free | 262,144 | FC Reasoning |
| Thinking Machines: Inkling Small (free) | 1 | Free | Free | 1,048,576 | Vision FC Reasoning |
| Thinking Machines: Inkling (free) | 1 | Free | Free | 1,048,576 | Vision FC Reasoning |
| IBM: Granite 4.0 Micro | 1 | $0.02/1M tokens | $0.11/1M tokens | 131,000 | |
| inclusionAI: Ling 3.0 Flash | 1 | $0.02/1M tokens | $0.06/1M tokens | 262,144 | FC Reasoning |
| Mistral: Mistral Nemo | 1 | $0.02/1M tokens | $0.03/1M tokens | 131,072 | FC |
| Inference.net: Schematron V2 Turbo | 1 | $0.03/1M tokens | $0.15/1M tokens | 128,000 | |
| Meta: Llama 3.2 1B Instruct | 1 | $0.03/1M tokens | $0.20/1M tokens | 60,000 | |
| OpenAI: GPT-5 Nano (batch) | 1 | $0.03/1M tokens | $0.20/1M tokens | 400,000 | Vision FC Reasoning |
| OpenAI: gpt-oss-20b | 1 | $0.03/1M tokens | $0.13/1M tokens | 131,072 | FC Reasoning |
| Qwen: Qwen3.7 Flash | 1 | $0.03/1M tokens | $0.13/1M tokens | 1,000,000 | Vision FC Reasoning |
| DeepSeek: DeepSeek V4 Flash Latest | 1 | $0.03/1M tokens | $0.07/1M tokens | 1,310,720 | FC Reasoning |
| Amazon: Nova Micro 1.0 | 1 | $0.04/1M tokens | $0.14/1M tokens | 128,000 | FC |
| Cohere: Command R7B (12-2024) | 1 | $0.04/1M tokens | $0.15/1M tokens | 128,000 | |
| DeepSeek: DeepSeek V4 Flash 0731 | 1 | $0.04/1M tokens | $0.08/1M tokens | 1,310,720 | FC Reasoning |
| Google: Gemma 4 26B A4B | 1 | $0.04/1M tokens | $0.22/1M tokens | 262,144 | Vision FC Reasoning |
| Inception: Mercury 2.5 | 1 | $0.04/1M tokens | $0.15/1M tokens | 260,000 | FC Reasoning |
| OpenAI: gpt-oss-120b | 1 | $0.04/1M tokens | $0.17/1M tokens | 131,072 | FC Reasoning |
| Google: Gemini 2.5 Flash Lite (batch) | 1 | $0.05/1M tokens | $0.20/1M tokens | 1,048,576 | Vision FC Reasoning |
| Google: Gemma 3 12B | 1 | $0.05/1M tokens | $0.15/1M tokens | 131,072 | Vision FC |
| Google: Gemma 3 4B | 1 | $0.05/1M tokens | $0.10/1M tokens | 131,072 | Vision |
| Inference.net: Schematron V2 Small | 1 | $0.05/1M tokens | $0.23/1M tokens | 128,000 | |
| Meta: Llama 3.1 8B Instruct | 1 | $0.05/1M tokens | $0.08/1M tokens | 131,072 | FC |
| Meta: Llama 3.2 3B Instruct | 1 | $0.05/1M tokens | $0.33/1M tokens | 131,072 | |
| Mistral: Mistral Small 3 | 1 | $0.05/1M tokens | $0.08/1M tokens | 32,768 | |
| NVIDIA: Nemotron 3 Nano 30B A3B | 1 | $0.05/1M tokens | $0.20/1M tokens | 262,144 | FC Reasoning |
| OpenAI: GPT-4.1 Nano (batch) | 1 | $0.05/1M tokens | $0.20/1M tokens | 1,047,576 | Vision FC |
| OpenAI: GPT-5 Nano | 1 | $0.05/1M tokens | $0.40/1M tokens | 400,000 | Vision FC Reasoning |
| OpenAI: gpt-oss-20b (batch) | 1 | $0.05/1M tokens | $0.20/1M tokens | 131,072 | Reasoning |
| Amazon: Nova Lite 1.0 | 1 | $0.06/1M tokens | $0.24/1M tokens | 300,000 | Vision FC |
| IBM: Granite 4.2 8B | 1 | $0.06/1M tokens | $0.25/1M tokens | 131,072 | FC Reasoning |
| inclusionAI: Ling 3.0 Flash Fin | 1 | $0.06/1M tokens | $0.18/1M tokens | 262,144 | FC Reasoning |
| inclusionAI: Ling 3.0 Flash VL | 1 | $0.06/1M tokens | $0.18/1M tokens | 131,072 | Vision FC Reasoning |
| Poolside: Laguna XS 2.1 | 1 | $0.06/1M tokens | $0.12/1M tokens | 262,144 | FC Reasoning |
| Z.ai: GLM 4.7 Flash | 1 | $0.06/1M tokens | $0.40/1M tokens | 200,000 | FC Reasoning |
| DeepSeek: DeepSeek V4 Flash 0423 | 1 | $0.07/1M tokens | $0.13/1M tokens | 1,048,576 | FC Reasoning |
| Qwen: Qwen3 Coder 30B A3B Instruct | 1 | $0.07/1M tokens | $0.28/1M tokens | 262,144 | FC |
| Qwen: Qwen3.5-Flash | 1 | $0.07/1M tokens | $0.26/1M tokens | 1,000,000 | Vision FC Reasoning |
| ByteDance Seed: Seed 1.6 Flash | 1 | $0.08/1M tokens | $0.30/1M tokens | 262,144 | Vision FC Reasoning |
| Google: Gemma 3 27B | 1 | $0.08/1M tokens | $0.45/1M tokens | 131,072 | Vision FC |
| Mistral: Ministral 3 8B 2512 (batch) | 1 | $0.08/1M tokens | $0.08/1M tokens | 262,144 | Vision FC |
| Mistral: Mistral Small 4 (batch) | 1 | $0.08/1M tokens | $0.30/1M tokens | 262,144 | Vision FC Reasoning |
| Mistral: Mistral Small 3.2 24B | 1 | $0.08/1M tokens | $0.20/1M tokens | 256,000 | Vision FC |
| NVIDIA: Nemotron 3.5 Lightning | 1 | $0.08/1M tokens | $0.20/1M tokens | 262,144 | FC Reasoning |
| OpenAI: GPT-4o-mini (batch) | 1 | $0.08/1M tokens | $0.30/1M tokens | 128,000 | Vision FC |
| OpenAI: gpt-oss-safeguard-20b | 1 | $0.08/1M tokens | $0.30/1M tokens | 131,072 | FC Reasoning |
| Qwen: Qwen3 32B | 1 | $0.08/1M tokens | $0.28/1M tokens | 131,072 | FC Reasoning |
| Z.ai: GLM 5.3 Flash (batch) | 1 | $0.08/1M tokens | $0.25/1M tokens | 1,048,576 | Vision FC Reasoning |
| Z.ai: GLM Flash Latest | 1 | $0.08/1M tokens | $0.25/1M tokens | 1,310,720 | Vision FC Reasoning |
| Google: Gemma 4 31B | 1 | $0.09/1M tokens | $0.34/1M tokens | 262,144 | Vision FC Reasoning |
| NVIDIA: Nemotron 3 Super | 1 | $0.09/1M tokens | $0.40/1M tokens | 262,144 | FC Reasoning |
| Poolside: Laguna S 2.1 | 1 | $0.09/1M tokens | $0.18/1M tokens | 1,048,576 | FC Reasoning |
| Qwen: Qwen3 235B A22B Instruct 2507 | 1 | $0.09/1M tokens | $0.35/1M tokens | 262,144 | FC |
| Qwen: Qwen3 30B A3B Instruct 2507 | 1 | $0.09/1M tokens | $0.30/1M tokens | 262,144 | FC |
| Qwen: Qwen3 Next 80B A3B Instruct | 1 | $0.09/1M tokens | $1.10/1M tokens | 262,144 | FC |
| Upstage: Solar Pro 4 | 1 | $0.09/1M tokens | $0.36/1M tokens | 524,288 | FC Reasoning |
| ByteDance Seed: Seed-2.0-Mini | 1 | $0.10/1M tokens | $0.40/1M tokens | 262,144 | Vision FC Reasoning |
| ByteDance: UI-TARS 7B | 1 | $0.10/1M tokens | $0.20/1M tokens | 128,000 | Vision |
| Google: Gemini 2.5 Flash Lite | 1 | $0.10/1M tokens | $0.40/1M tokens | 1,048,576 | Vision FC Reasoning |
| Meta: Llama 3.3 70B Instruct | 1 | $0.10/1M tokens | $0.32/1M tokens | 131,072 | FC |
| Meta: Llama 4 Scout | 1 | $0.10/1M tokens | $0.30/1M tokens | 1,310,720 | Vision FC |
| Meta: Muse Spark 1.2 Contributor | 1 | $0.10/1M tokens | $0.20/1M tokens | 1,048,576 | Vision FC Reasoning |
| Meta: Muse Spark 1.3 Contributor | 1 | $0.10/1M tokens | $0.20/1M tokens | 1,048,576 | Vision FC Reasoning |
| Mistral: Ministral 3 3B 2512 | 1 | $0.10/1M tokens | $0.10/1M tokens | 131,072 | Vision FC |
| Mistral: Voxtral Small 24B 2507 | 1 | $0.10/1M tokens | $0.30/1M tokens | 32,768 | FC |
| OpenAI: GPT-4.1 Nano | 1 | $0.10/1M tokens | $0.40/1M tokens | 1,047,576 | Vision FC |
| OpenAI: GPT-5.4 Nano (batch) | 1 | $0.10/1M tokens | $0.63/1M tokens | 400,000 | Vision FC Reasoning |
| OpenAI: GPT-5.6 Luna Pro (batch) | 1 | $0.10/1M tokens | $0.60/1M tokens | 1,050,000 | Vision FC Reasoning |
| OpenAI: GPT-5.6 Luna (batch) | 1 | $0.10/1M tokens | $0.60/1M tokens | 1,050,000 | Vision FC Reasoning |
| Qwen: Qwen2.5 7B Instruct | 1 | $0.10/1M tokens | $0.20/1M tokens | 32,768 | FC |
| Qwen: Qwen3 VL 32B Instruct | 1 | $0.10/1M tokens | $0.42/1M tokens | 131,072 | Vision FC |
| Qwen: Qwen3.5-9B | 1 | $0.10/1M tokens | $0.15/1M tokens | 262,144 | Vision FC Reasoning |
| Qwen: Qwen3.6 35B A3B | 1 | $0.10/1M tokens | $0.90/1M tokens | 262,144 | Vision FC Reasoning |
| Reka Flash 3 | 1 | $0.10/1M tokens | $0.20/1M tokens | 65,536 | Reasoning |
| StepFun: Step 3.5 Flash | 1 | $0.10/1M tokens | $0.30/1M tokens | 262,144 | FC Reasoning |
| DeepSeek: DeepSeek V4 Flash 0731 (batch) | 1 | $0.11/1M tokens | $0.33/1M tokens | 1,048,576 | FC Reasoning |
| DeepSeek: DeepSeek V4 Flash Vision Exp (batch) | 1 | $0.11/1M tokens | $0.33/1M tokens | 1,048,576 | Vision FC Reasoning |
| Qwen: Qwen3 30B A3B | 1 | $0.12/1M tokens | $0.50/1M tokens | 131,072 | FC Reasoning |
| Qwen: Qwen3 8B | 1 | $0.12/1M tokens | $0.46/1M tokens | 131,072 | FC Reasoning |
| Qwen: Qwen3 Coder Next | 1 | $0.12/1M tokens | $0.80/1M tokens | 262,144 | FC |
| Qwen: Qwen3 VL 8B Instruct | 1 | $0.12/1M tokens | $0.46/1M tokens | 262,144 | Vision FC |