LLM API prices
175 models · USD per 1M tokens
last refresh 15 Sept 2026, 06:37 UTC175 / 219
Tags
| Model | Blended ↑ | Developer | In | Out | Ctx | tok/s | |
|---|---|---|---|---|---|---|---|
| cheapestgpt-oss-20breasoningprompt cachetools | $0.04 | OpenAI · via Darkbloom | 0.02 | 0.10 | 131K | - | |
| Qwen3.7 Flashopen weightsreasoningvision | $0.06 | Alibaba | 0.03 | 0.13 | 1M | - | |
| Mistral Small 3open weights | $0.06 | Mistral | 0.05 | 0.08 | 33K | - | |
| DeepSeek V4 Flash 0731open weightsreasoningprompt cache | $0.06 | DeepSeek · via OpenInference | 0.04 | 0.10 | 1M | - | |
| Command R7B (12-2024) | $0.07 | Cohere | 0.04 | 0.15 | 128K | - | |
| gpt-oss-120breasoningtools | $0.07 | OpenAI · via AkashML | 0.03 | 0.17 | 131K | - | |
| GPT-5 Nanoreasoningvisionprompt cache | $0.07 | OpenAI · via OpenAI | 0.03 | 0.20 | 400K | - | |
| Qwen3 30B A3B Instruct 2507open weightstools200k+ context | $0.08 | Alibaba · via StreamLake | 0.05 | 0.19 | 262K | - | |
| Phi 4open weights | $0.09 | Microsoft | 0.07 | 0.14 | 16K | - | |
| Qwen3.5-9Bopen weightsreasoningvision | $0.09 | Alibaba · via Darkbloom | 0.08 | 0.13 | 262K | - | |
| Gemma 4 26B A4Bopen weightsreasoningvision | $0.09 | Google · via Darkbloom | 0.04 | 0.22 | 262K | - | |
| Gemini 2.5 Flash Litereasoningvisionprompt cache | $0.09 | Google · via Google AI Studio | 0.05 | 0.20 | 1M | - | |
| Gemma 3 27Bopen weightsvisionprompt cache | $0.10 | Google · via DeepInfra | 0.08 | 0.16 | 131K | - | |
| Nova Lite 1.0visiontools200k+ context | $0.11 | Amazon | 0.06 | 0.24 | 300K | - | |
| Mistral Small 3.2 24Bopen weightsvisiontools | $0.11 | Mistral · via DeepInfra | 0.07 | 0.20 | 256K | - | |
| Granite 4.2 8Bopen weightsreasoningprompt cache | $0.11 | IBM · via DeepInfra | 0.06 | 0.25 | 131K | - | |
| Qwen3.5-Flashopen weightsreasoningvision | $0.11 | Alibaba | 0.07 | 0.26 | 1M | - | |
| Qwen3 Coder 30B A3B Instructopen weightscodingtools | $0.12 | Alibaba · via Novita | 0.07 | 0.27 | 262K | - | |
| GLM 5.3 Flashopen weightsreasoningvision | $0.12 | Zhipu · via DeepInfra | 0.07 | 0.25 | 1M | - | |
| Qwen3 32Bopen weightsreasoningtools | $0.13 | Alibaba · via DeepInfra | 0.08 | 0.28 | 131K | - | |
| gpt-oss-safeguard-20breasoningprompt cachetools | $0.13 | OpenAI | 0.07 | 0.30 | 131K | - | |
| Qwen3 14Bopen weightsreasoningtools | $0.13 | Alibaba · via NextBit | 0.10 | 0.22 | 131K | - | |
| GLM 4.7 Flashopen weightsreasoningtools | $0.15 | Zhipu · via Venice | 0.06 | 0.40 | 200K | - | |
| Llama 4 Scoutopen weightsvisiontools | $0.15 | Meta · via DeepInfra | 0.10 | 0.30 | 1M | - | |
| Gemma 4 31Bopen weightsreasoningvision | $0.15 | Google · via DeepInfra | 0.09 | 0.34 | 262K | - | |
| Qwen3 235B A22B Instruct 2507open weightsprompt cachetools | $0.15 | Alibaba · via GMICloud | 0.09 | 0.35 | 262K | - | |
| Llama 3.3 70B Instructopen weightstools | $0.16 | Meta · via DeepInfra | 0.10 | 0.32 | 131K | - | |
| GPT-4.1 Nanovisionprompt cachetools | $0.18 | OpenAI · via Azure | 0.10 | 0.40 | 1M | - | |
| Qwen3 VL 32B Instructopen weightsvisiontools | $0.18 | Alibaba | 0.10 | 0.42 | 131K | - | |
| Qwen3 8Bopen weightsreasoningtools | $0.20 | Alibaba | 0.12 | 0.46 | 131K | - | |
| Qwen3 VL 8B Instructopen weightsvisiontools | $0.20 | Alibaba · via Alibaba | 0.12 | 0.46 | 262K | - | |
| Qwen3.6 35B A3Bopen weightsreasoningvision | $0.21 | Alibaba · via Darkbloom | 0.05 | 0.70 | 262K | - | |
| Qwen3 30B A3Bopen weightsreasoningtools | $0.22 | Alibaba · via DeepInfra | 0.12 | 0.50 | 131K | - | |
| Qwen3.8 Flashopen weightsreasoningvision | $0.23 | Alibaba · via Makora | 0.15 | 0.47 | 1M | - | |
| Qwen3 VL 30B A3B Instructopen weightsvisiontools | $0.23 | Alibaba · via Alibaba | 0.13 | 0.52 | 262K | - | |
| DeepSeek V3.2open weightsreasoningprompt cache | $0.23 | DeepSeek · via GMICloud | 0.21 | 0.31 | 164K | - | |
| GPT-5.6 Lunareasoningvisionprompt cache | $0.23 | OpenAI · via OpenAI | 0.10 | 0.60 | 1M | - | |
| GPT-5.6 Luna Proreasoningvisionprompt cache | $0.23 | OpenAI · via OpenAI | 0.10 | 0.60 | 1M | - | |
| GPT-5.4 Nanoreasoningvisionprompt cache | $0.23 | OpenAI · via OpenAI | 0.10 | 0.63 | 400K | - | |
| Qwen3.5-35B-A3Bopen weightsreasoningvision | $0.25 | Alibaba · via Darkbloom | 0.08 | 0.75 | 262K | - | |
| Mistral Small 4open weightsreasoningvision | $0.26 | Mistral · via Mistral | 0.15 | 0.60 | 262K | - | |
| GPT-4o-minivisionprompt cachetools | $0.26 | OpenAI · via Azure | 0.15 | 0.60 | 128K | - | |
| DeepSeek V4.1 Flashopen weightsreasoningvision | $0.26 | DeepSeek · via Relace | 0.15 | 0.60 | 1M | - | |
| Qwen3 Next 80B A3B Instructopen weightstools200k+ context | $0.27 | Alibaba · via Alibaba | 0.10 | 0.78 | 262K | - | |
| Gemini 3.1 Flash Litereasoningvisionprompt cache | $0.28 | Google · via Google | 0.13 | 0.75 | 1M | - | |
| Qwen3 Coder Nextopen weightscodingprompt cache | $0.29 | Alibaba · via Parasail | 0.12 | 0.80 | 262K | - | |
| Sabaopen weightsprompt cachetools | $0.30 | Mistral | 0.20 | 0.60 | 33K | - | |
| Llama 4 Maverickopen weightsvisiontools | $0.30 | Meta · via DigitalOcean | 0.19 | 0.65 | 1M | - | |
| DeepSeek V3.2 Expopen weightsreasoningtools | $0.31 | DeepSeek · via SiliconFlow | 0.27 | 0.41 | 164K | - | |
| DeepSeek V4 Flash Vision Expopen weightsreasoningvision | $0.32 | DeepSeek · via DeepInfra | 0.22 | 0.65 | 1M | - | |
| GPT-5 Minireasoningvisionprompt cache | $0.34 | OpenAI · via OpenAI | 0.13 | 1.00 | 400K | - | |
| Qwen3 VL 235B A22B Instructopen weightsvisionprompt cache | $0.37 | Alibaba · via DeepInfra | 0.20 | 0.88 | 262K | - | |
| Qwen-Plusopen weightsprompt cachetools | $0.39 | Alibaba | 0.26 | 0.78 | 1M | - | |
| Qwen3 Coder Flashopen weightscodingprompt cache | $0.39 | Alibaba | 0.20 | 0.97 | 1M | - | |
| Mistral Small 3.1 24Bopen weightsvision | $0.40 | Mistral | 0.35 | 0.56 | 128K | - | |
| Qwen3 Next 80B A3B Thinkingopen weightsreasoningtools | $0.41 | Alibaba · via Google | 0.15 | 1.20 | 262K | - | |
| DeepSeek V3 0324open weightstools | $0.41 | DeepSeek · via DeepInfra | 0.24 | 0.90 | 164K | - | |
| Qwen3.6 Flashopen weightsreasoningvision | $0.42 | Alibaba | 0.19 | 1.13 | 1M | - | |
| DeepSeek V3.1open weightsreasoningprompt cache | $0.43 | DeepSeek · via DeepInfra | 0.25 | 0.95 | 164K | - | |
| Gemini 2.5 Flashreasoningvisionprompt cache | $0.43 | Google · via Google AI Studio | 0.15 | 1.25 | 1M | - |
click a row to compare (up to 3) · cheapest provider shown - open a model for every route · blended = 3×in + out, /4 · colour = price band in view - OpenRouter API (live) + routes d'accès par modèle (219 modèles)