11,195 prices on 4,854 listings · last collected 8 h ago · 442 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on ten platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.
Platform
Unit price
All 11,195Per second of output 2,701Per minute 34Per video 674Per image 1,827Per megapixel 326Per million input tokens 1,298Per million output tokens 1,235Per million tokens 47Per million cached input tokens (read) 641Per million cache-write tokens 227Per thousand characters 75Per second of compute time 98Per run (default parameters) 1,784Other units (see the platform’s wording) 228
Showing 401–500 of 1,235
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterOfficial | Tencent: Hy Image 3.5 Preview | $1.6/M out | output_image: 0.0000016 USD / token | |
| ReplicateOfficial partner | openai/gpt-4.1-mini | $1.6/M out | $1.60 per million output tokens | |
| OpenRouterOfficial | Qwen: Qwen3 Coder FlashPrompt > 32K | $1.625/M out | completion: 0.000001625 / token (>32000; endpoint alibaba) | |
| OpenRouterThird-party | MoonshotAI: Kimi K2.6via Baidu · fp4 | $1.64/M out | completion: 0.00000164 / token (endpoint baidu/fp4) | |
| AibermNot disclosed | GPT-4o | $1.656/M out | model_ratio 0.9 × $2/M · group default ×0.23 · completion_ratio 4Claims official price $10/M out | |
| APIMartNot disclosed | glm-4.7 | $1.68/M out | Input $0.4 / Output $1.68 · Per 1M tokens | |
| APIMartNot disclosed | kimi-k2-instruct | $1.68/M out | Input $0.4 / Output $1.68 · Per 1M tokens | |
| APIMartNot disclosed | kimi-k2-thinking | $1.68/M out | Input $0.4 / Output $1.68 · Per 1M tokens | |
| OpenRouterThird-party | Z.ai: GLM 4.6via Venice · fp4 | $1.75/M out | completion: 0.00000175 / token (endpoint venice/fp4) | |
| OpenRouterThird-party | Z.ai: GLM 4.7via DeepInfra · fp4 | $1.75/M out | completion: 0.00000175 / token (endpoint deepinfra/fp4) | |
| APIMartNot disclosed | deepseek-r1 | $1.792/M out | Input $0.448 / Output $1.792 · Per 1M tokens | |
| APIMartNot disclosed | deepseek-r1-250528 | $1.792/M out | Input $0.448 / Output $1.792 · Per 1M tokens | |
| AibermNot disclosed | Qwen3.7 Plus | $1.794/M out | model_ratio 0.65 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $1.6/M out | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 LunaPrompt > 272Kvia Amazon Bedrock · global | $1.8/M out | completion: 0.0000018 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Luna ProPrompt > 272Kvia Azure | $1.8/M out | completion: 0.0000018 / token (>272000; endpoint azure) | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-04-20 | $1.8/M out | completion: 0.0000018 / token (endpoint alibaba) | |
| OpenRouterThird-party | Z.ai: GLM 4.5Vvia Novita · fp8 | $1.8/M out | completion: 0.0000018 / token (endpoint novita/fp8) | |
| OpenRouterNot disclosed | Z.ai: GLM 5.2via DeepInfra · fp4 | $1.8/M out | completion: 0.0000018 / token (endpoint deepinfra/fp4) | |
| OpenRouterOfficial | Google: Gemini 3.6 Flash (batch) | $1.875/M out | completion: 0.000001875 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.6 Flash (batch)Reasoning | $1.875/M out | internal_reasoning: 0.000001875 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.7 Flash (batch) | $1.875/M out | completion: 0.000001875 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.7 Flash (batch)Reasoning | $1.875/M out | internal_reasoning: 0.000001875 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.8 Flash (batch) | $1.875/M out | completion: 0.000001875 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.8 Flash (batch)Reasoning | $1.875/M out | internal_reasoning: 0.000001875 / token (endpoint google-vertex/global) | |
| AibermNot disclosed | MiniMax M2.7 | $1.88/M out | model_ratio 0.9852 × $2/M · group default ×0.23 · completion_ratio 4.148Claims official price $1.2/M out | |
| AibermNot disclosed | MiniMax M2.7 | $1.88/M out | model_ratio 0.9852 × $2/M · group default ×0.23 · completion_ratio 4.148Claims official price $1.2/M out | |
| AibermNot disclosed | DeepSeek OCR | $1.887/M out | model_ratio 0.86 × $2/M · group default ×0.23 · completion_ratio 4.77 | |
| AibermNot disclosed | DeepSeek R1 0528 | $1.887/M out | model_ratio 0.86 × $2/M · group default ×0.23 · completion_ratio 4.77 | |
| AibermNot disclosed | DeepSeek R1 0528 | $1.887/M out | model_ratio 0.86 × $2/M · group default ×0.23 · completion_ratio 4.77Claims official price $2.19/M out | |
| OpenRouterOfficial | Morph: Morph V3 Large | $1.9/M out | completion: 0.0000019 / token (endpoint morph/fp8) | |
| APIMartNot disclosed | gpt-4o-mini-realtime-preview | $1.92/M out | Input $0.48 / Output $1.92 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4o-mini-realtime-preview-2024-12-17 | $1.92/M out | Input $0.48 / Output $1.92 · Per 1M tokens | |
| OpenRouterThird-party | Z.ai: GLM 5via StreamLake · fp8 | $1.92/M out | completion: 0.00000192 / token (endpoint streamlake/fp8) | |
| RunwareNot disclosed | DeepSeek-V4-Pro-0813 | $1.922/M out | $0.000001922 / outputToken | |
| AibermNot disclosed | GPT-5.6 Terra | $1.95/M out | model_ratio 0.7065 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $15/M out | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-02-15Prompt > 256K | $1.95/M out | completion: 0.00000195 / token (>256000; endpoint alibaba) | |
| OpenRouterOfficial | Qwen: Qwen3.6 Plus | $1.95/M out | completion: 0.00000195 / token (endpoint alibaba) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Pro 0813via Baidu · fp8 | $1.976/M out | completion: 0.00000197604 / token (endpoint baidu/fp8) | |
| AibermNot disclosed | DeepSeek V4 Pro | $1.98/M out | model_ratio 1.43478 × $2/M · group default ×0.23 · completion_ratio 3Claims official price $0.87/M out | |
| AibermNot disclosed | Claude Opus 5.5 | $1.998/M out | model_ratio 0.8688 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $20/M out | |
| APIMartNot disclosed | gemini-3.5-flash-lite | $1.999/M out | Input $0.24 / Output $1.9992 · Per 1M tokens | |
| APIMartNot disclosed | grok-4.20-0309-non-reasoning | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| APIMartNot disclosed | grok-4.20-0309-reasoning | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| APIMartNot disclosed | grok-4.20-multi-agent-0309 | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| APIMartNot disclosed | grok-4.3 | $2/M out | Input $1 / Output $2 · Per 1M tokens | |
| APIMartOfficial | nano-bananaText output | $2/M out | 20 Credits/M ~$2/MClaims official price $2.5/M outMember tiers: platinum $1.9 · diamond $1.8 | |
| OpenRouterOfficial | ByteDance Seed: Seed-2.0-Lite | $2/M out | completion: 0.000002 / token (endpoint seed/fp8) | |
| OpenRouterOfficial | Mistral: Devstral 2 2512 | $2/M out | completion: 0.000002 / token | |
| OpenRouterOfficial | Mistral: Mistral Medium 3via Mistral · zdr | $2/M out | completion: 0.000002 / token (endpoint mistral/zdr) | |
| OpenRouterOfficial | Mistral: Mistral Medium 3.1via Mistral · zdr | $2/M out | completion: 0.000002 / token (endpoint mistral/zdr) | |
| OpenRouterOfficial partner | OpenAI: GPT-3.5 Turbo (older v0613) | $2/M out | completion: 0.000002 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-5 Image MiniText | $2/M out | completion: 0.000002 / token | |
| OpenRouterOfficial partner | OpenAI: GPT-5 Minivia Azure | $2/M out | completion: 0.000002 / token (endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.1-Codex-Mini | $2/M out | completion: 0.000002 / token | |
| OpenRouterThird-party | Qwen: Qwen3.6 27Bvia Chutes · fp8 | $2/M out | completion: 0.000002 / token (endpoint chutes/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3.8 27B (batch) | $2/M out | completion: 0.000002 / token (endpoint deepinfra/bf16) | |
| OpenRouterOfficial | SpaceXAI: Grok 4.3 (batch) | $2/M out | completion: 0.000002 / token (endpoint xai) | |
| OpenRouterOfficial | SpaceXAI: Grok Build 0.1via xAI | $2/M out | completion: 0.000002 / token (endpoint xai) | |
| OpenRouterThird-party | Xiaomi: MiMo-V2.5 | $2/M out | completion: 0.000002 / token (endpoint venice/fp8) | |
| ReplicateOfficial partner | openai/gpt-5-mini | $2/M out | $2 per million output tokens | |
| ReplicateOfficial partner | openai/gpt-5-structuredgpt-5-mini | $2/M out | $2 per million output tokens (gpt-5-mini) | |
| AibermNot disclosed | Claude Haiku 4.5 | $2.013/M out | model_ratio 0.875 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $5/M out | |
| AibermNot disclosed | Claude Haiku 4.5 Thinking | $2.013/M out | model_ratio 0.875 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $5/M out | |
| ReplicateOfficial partner | deepseek-ai/deepseek-v3.1 | $2.016/M out | $2.016 per million output tokens | |
| AibermNot disclosed | Kimi K2.5 | $2.07/M out | model_ratio 0.9 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $3/M out | |
| AibermNot disclosed | Kimi K2.6 | $2.07/M out | model_ratio 0.9 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $4/M out | |
| AibermNot disclosed | Kimi K2.5 | $2.07/M out | model_ratio 0.9 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $3/M out | |
| AibermNot disclosed | Kimi K2.5 Thinking | $2.07/M out | model_ratio 0.9 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $3/M out | |
| AibermNot disclosed | Qwen3.5 397B A17B | $2.07/M out | model_ratio 0.75 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $3.6/M out | |
| AibermNot disclosed | Qwen3.5 Plus | $2.07/M out | model_ratio 0.75 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $2.4/M out | |
| AibermNot disclosed | Qwen3.6 Plus | $2.07/M out | model_ratio 0.75 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $2.4/M out | |
| OpenRouterThird-party | Qwen: Qwen3.5-122B-A10Bvia SiliconFlow · fp8 | $2.08/M out | completion: 0.00000208 / token (endpoint siliconflow/fp8) | |
| OpenRouterOfficial | Mistral: Mistral Large 4via Mistral · zdr | $2.1/M out | completion: 0.0000021 / token (endpoint mistral/zdr) | |
| OpenRouterThird-party | DeepSeek: R1 0528via DeepInfra · fp4 | $2.15/M out | completion: 0.00000215 / token (endpoint deepinfra/fp4) | |
| AibermNot disclosed | GLM-4.6 | $2.151/M out | model_ratio 1.1 × $2/M · group default ×0.23 · completion_ratio 4.25Claims official price $2.2/M out | |
| OpenRouterThird-party | Qwen: Qwen3.5-27Bvia AtlasCloud · fp8 | $2.16/M out | completion: 0.00000216 / token (endpoint atlas-cloud/fp8) | |
| FalOfficial partner | Isaac 0.1 | $2.17/M out | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| FalOfficial partner | Isaac 0.1 [OpenAI Compatible Endpoint] | $2.17/M out | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| ReplicatePlatform-hosted | perceptron-ai-inc/isaac-0.1 | $2.17/M out | $2.17 per million output tokens | |
| OpenRouterNot disclosed | NVIDIA: Nemotron 3 Ultravia KT | $2.2/M out | completion: 0.0000022 / token (endpoint kt) | |
| OpenRouterOfficial | OpenAI: o3 Mini (batch) | $2.2/M out | completion: 0.0000022 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: o4 Mini (batch) | $2.2/M out | completion: 0.0000022 / token (endpoint openai) | |
| OpenRouterOfficial | Z.ai: GLM 4.5 | $2.2/M out | completion: 0.0000022 / token (endpoint z-ai/fp8) | |
| AibermNot disclosed | GPT-5.1 Codex | $2.208/M out | model_ratio 0.6 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $10/M out | |
| AibermNot disclosed | GPT-5.1 Codex Max | $2.208/M out | model_ratio 0.6 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $10/M out | |
| AibermNot disclosed | GPT-5.2 Codex | $2.208/M out | model_ratio 0.6 × $2/M · group default ×0.23 · completion_ratio 8 | |
| AibermNot disclosed | GPT-4.1 | $2.208/M out | model_ratio 1.2 × $2/M · group default ×0.23 · completion_ratio 4Claims official price $8/M out | |
| AibermNot disclosed | GPT-5 Codex | $2.208/M out | model_ratio 0.6 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $10/M out | |
| AibermNot disclosed | GPT-5.1 Codex | $2.208/M out | model_ratio 0.6 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $10/M out | |
| AibermNot disclosed | GPT-5.1 Codex Max | $2.208/M out | model_ratio 0.6 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $10/M out | |
| AibermNot disclosed | GPT-5.2 Codex | $2.208/M out | model_ratio 0.6 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $14/M out | |
| AibermNot disclosed | Claude Sonnet 4.5 20250929 | $2.248/M out | model_ratio 0.9775 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $15/M out | |
| AibermNot disclosed | Claude Sonnet 4.5 20250929 Thinking | $2.248/M out | model_ratio 0.9775 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $15/M out | |
| AibermNot disclosed | Claude Sonnet 4.6 | $2.248/M out | model_ratio 0.9775 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $15/M out | |
| AibermNot disclosed | Claude Sonnet 4.6 Thinking | $2.248/M out | model_ratio 0.9775 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $15/M out | |
| OpenRouterOfficial | OpenAI: GPT-5.4 Mini (batch) | $2.25/M out | completion: 0.00000225 / token (endpoint openai) | |
| OpenRouterOfficial | Qwen: Qwen3.5 Plus 2026-04-20Prompt > 256K | $2.25/M out | completion: 0.00000225 / token (>256000; endpoint alibaba) | |
| OpenRouterThird-party | Tencent: Hy4 previewoff-peak 1600–0000 UTC · via Tencent · fp8 | $2.251/M out | completion: 0.0000022509 / token (utc_start 1600, utc_end 0; endpoint tencent/fp8) | |
| AibermNot disclosed | Gemini 3.6 Flash | $2.3/M out | model_ratio 1 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $7.5/M out | |
| AibermNot disclosed | Gemini 3.7 Flash | $2.3/M out | model_ratio 1 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $7.5/M out |
