11,195 prices on 4,854 listings · last collected 6 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 201–300 of 1,235
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| ReplicatePlatform-hosted | meta/llama-2-13b-chat | $0.5/M out | $0.50 per million output tokens | |
| RunwareNot disclosed | Claude Haiku 5.5≤ 100K context | $0.5/M out | $5e-7 / outputToken · ≤ 100K context | |
| RunwareNot disclosed | GPT-6 Luna≤ 272K context | $0.5/M out | $5e-7 / outputToken · ≤ 272K context | |
| RunwareNot disclosed | GPT-Image-2.6 FlareSVG authoring · GPT-6 Luna | $0.5/M out | $5e-7 / outputToken · SVG authoring · GPT-6 Luna · Output | |
| RunwareNot disclosed | GPT-Image-2.6 SunburstSVG authoring · GPT-6 Luna | $0.5/M out | $5e-7 / outputToken · SVG authoring · GPT-6 Luna · Output | |
| RunwareNot disclosed | GLM-5.3-Flash | $0.5/M out | $5e-7 / outputToken | |
| APIMartNot disclosed | deepseek-v4-flash | $0.514/M out | Input $0.1714 / Output $0.5143 · Per 1M tokens | |
| OpenRouterThird-party | Tencent: Hy3peak 0000–1600 UTC · via Tencent · fp8 | $0.528/M out | completion: 0.000000528 / token (utc_start 0, utc_end 1600; endpoint tencent/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 235B A22B Instruct 2507via DeepInfra · fp8 | $0.55/M out | completion: 0.00000055 / token (endpoint deepinfra/fp8) | |
| AibermNot disclosed | GPT-5 Mini | $0.552/M out | model_ratio 0.15 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $2/M out | |
| OpenRouterThird-party | Mistral: Mistral Small 3.1 24B | $0.555/M out | completion: 0.000000555 / token (endpoint cloudflare) | |
| APIMartNot disclosed | kimi-k2.5 | $0.555/M out | Input $0.4112 / Output $0.5551 · Per 1M tokens | |
| OpenRouterThird-party | Tencent: Hunyuan A13B Instruct | $0.57/M out | completion: 0.00000057 / token (endpoint siliconflow/fp8) | |
| AibermNot disclosed | Claude Haiku 4.5 | $0.575/M out | model_ratio 0.25 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $5/M out | |
| AibermNot disclosed | Claude Haiku 4.5 20251001 | $0.575/M out | model_ratio 0.25 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $5/M out | |
| AibermNot disclosed | Claude Haiku 4.5 20251001 Thinking | $0.575/M out | model_ratio 0.25 × $2/M · group default ×0.23 · completion_ratio 5Claims official price $5/M out | |
| OpenRouterOfficial | Cohere: Command R (08-2024) | $0.6/M out | completion: 0.0000006 / token (endpoint cohere) | |
| OpenRouterOfficial | Mistral: Sabavia Mistral · zdr | $0.6/M out | completion: 0.0000006 / token (endpoint mistral/zdr) | |
| OpenRouterOfficial | Mistral: Mistral Small 4via Mistral · zdr | $0.6/M out | completion: 0.0000006 / token (endpoint mistral/zdr) | |
| OpenRouterOfficial | Morph: Morph V3 Fast (batch) | $0.6/M out | completion: 0.0000006 / token | |
| OpenRouterOfficial partner | OpenAI: GPT-4o-minivia Azure | $0.6/M out | completion: 0.0000006 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-4o-mini (2024-07-18) | $0.6/M out | completion: 0.0000006 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Luna Pro (batch) | $0.6/M out | completion: 0.0000006 / token (endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Luna (batch) | $0.6/M out | completion: 0.0000006 / token (endpoint openai) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 30B A3B Instructvia DeepInfra · fp8 | $0.6/M out | completion: 0.0000006 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Tencent: Hy3 preview | $0.6/M out | completion: 0.0000006 / token (endpoint gmicloud/bf16) | |
| OpenRouterNot disclosed | Upstage: Solar Pro 4via Upstage · zdr | $0.6/M out | completion: 0.0000006 / token (endpoint upstage/zdr) | |
| ReplicateOfficial partner | openai/gpt-4o-mini | $0.6/M out | $0.60 per million output tokens | |
| ReplicateOfficial partner | openai/gpt-image-2.6-flaresvg-gpt-6-luna · gpt-6-luna | $0.6/M out | $0.0000006 gpt-6-luna output tokens (svg-gpt-6-luna) | |
| ReplicateOfficial partner | openai/gpt-image-2.6-sunburstsvg-gpt-6-luna · gpt-6-luna | $0.6/M out | $0.0000006 gpt-6-luna output tokens (svg-gpt-6-luna) | |
| RunwareNot disclosed | DeepSeek-V4.1-Flash | $0.6/M out | $6e-7 / outputToken | |
| RunwareNot disclosed | DeepSeek-V4.1-Flash-1017 | $0.6/M out | $6e-7 / outputToken | |
| RunwareNot disclosed | MiniMax M3.1 Flash | $0.6/M out | $6e-7 / outputToken | |
| OpenRouterOfficial | OpenAI: GPT-5.4 Nano (batch) | $0.625/M out | completion: 0.000000625 / token (endpoint openai) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V4 Flash Vision Expvia DeepInfra · fp8 | $0.647/M out | completion: 0.0000006468 / token (endpoint deepinfra/fp8) | |
| AibermNot disclosed | Gemini 3.1 Flash Lite | $0.648/M out | model_ratio 0.22 × $2/M · group default ×0.23 · completion_ratio 6.4Claims official price $1.5/M out | |
| AibermNot disclosed | Gemini 3.1 Flash Lite Preview | $0.648/M out | model_ratio 0.22 × $2/M · group default ×0.23 · completion_ratio 6.4Claims official price $1.5/M out | |
| AibermNot disclosed | Gemini 3.1 Flash Lite | $0.648/M out | model_ratio 0.22 × $2/M · group default ×0.23 · completion_ratio 6.4Claims official price $1.5/M out | |
| OpenRouterThird-party | Google: Gemma 2 27B | $0.65/M out | completion: 0.00000065 / token (endpoint nextbit/int4) | |
| ReplicatePlatform-hosted | meta/llama-4-scout-instruct | $0.65/M out | $0.65 per million output tokens | |
| OpenRouterThird-party | Xiaomi: MiMo-V2.6-Provia GMICloud · bf16 | $0.653/M out | completion: 0.0000006525 / token (endpoint gmicloud/bf16) | |
| APIMartNot disclosed | mimo-v2.5-pro | $0.686/M out | Input $0.3429 / Output $0.6858 · Per 1M tokens | |
| OpenRouterOfficial | LiquidAI: LFM2.5-24B-A2B | $0.7/M out | completion: 0.0000007 / token (endpoint liquid/fp8) | |
| OpenRouterThird-party | Meta: Llama 3.1 70B Instruct | $0.72/M out | completion: 0.00000072 / token (endpoint amazon-bedrock) | |
| ReplicatePlatform-hosted | openai/gpt-oss-120b | $0.72/M out | $0.72 per million output tokens | |
| AibermNot disclosed | Gemini 2.5 Flash | $0.736/M out | model_ratio 0.16 × $2/M · group default ×0.23 · completion_ratio 10Claims official price $2.5/M out | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Lite (batch) | $0.75/M out | completion: 0.00000075 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.1 Flash Lite (batch)Reasoning | $0.75/M out | internal_reasoning: 0.00000075 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 LunaPrompt > 272Kvia Amazon Bedrock · global | $0.75/M out | completion: 0.00000075 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Luna ProPrompt > 272Kvia OpenAI | $0.75/M out | completion: 0.00000075 / token (>272000; endpoint openai) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 8B Instruct | $0.75/M out | completion: 0.00000075 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Qwen: Qwen3.5-35B-A3Bvia Darkbloom · fp4 | $0.75/M out | completion: 0.00000075 / token (endpoint darkbloom/fp4) | |
| OpenRouterNot disclosed | OpenAI: GPT Luna LatestPrompt > 272K | $0.75/M out | completion: 0.00000075 / token (>272000) | |
| RunwareNot disclosed | GPT-6 Luna> 272K context | $0.75/M out | $7.5e-7 / outputToken · > 272K context | |
| AibermNot disclosed | GPT-5.6 Luna | $0.78/M out | model_ratio 0.2826 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $6/M out | |
| AibermNot disclosed | GPT-6 Luna | $0.78/M out | model_ratio 0.2826 × $2/M · group default ×0.23 · completion_ratio 6Claims official price $6/M out | |
| OpenRouterOfficial | Qwen: Qwen-Plus | $0.78/M out | completion: 0.00000078 / token (endpoint alibaba) | |
| OpenRouterOfficial | ByteDance Seed: Seed-2.0-MiniPrompt > 128K | $0.8/M out | completion: 0.0000008 / token (>128000; endpoint seed/fp8) | |
| OpenRouterOfficial | KT: Mi:dm K 3.0 Pro | $0.8/M out | completion: 0.0000008 / token (endpoint kt) | |
| OpenRouterOfficial | OpenAI: GPT-4.1 Mini (batch) | $0.8/M out | completion: 0.0000008 / token (endpoint openai) | |
| OpenRouterThird-party | Qwen: Qwen3 Coder Next | $0.8/M out | completion: 0.0000008 / token (endpoint parasail/bf16) | |
| OpenRouterOfficial | Qwen: Qwen3.7 FlashPrompt > 256Kvia Alibaba | $0.8/M out | completion: 0.0000008 / token (>256000; endpoint alibaba) | |
| OpenRouterThird-party | TheDrummer: Skyfall 36B V2 | $0.8/M out | completion: 0.0000008 / token (endpoint parasail/fp8) | |
| AibermNot disclosed | Gemini 3 Flash | $0.81/M out | model_ratio 0.22 × $2/M · group default ×0.23 · completion_ratio 8Claims official price $3/M out | |
| AibermNot disclosed | GPT-6.1 Terra | $0.812/M out | model_ratio 0.35325 × $2/M · group default ×0.23 · completion_ratio 5 | |
| APIMartNot disclosed | deepseek-v3-0324 | $0.822/M out | Input $0.2056 / Output $0.8224 · Per 1M tokens | |
| APIMartNot disclosed | qwen3.6-flash | $0.823/M out | Input $0.1371 / Output $0.8227 · Per 1M tokens | |
| OpenRouterThird-party | MiniMax: MiniMax M2.7via GMICloud · fp8 | $0.84/M out | completion: 0.00000084 / token (endpoint gmicloud/fp8) | |
| OpenRouterThird-party | Sao10K: Llama 3.1 Euryale 70B v2.2 | $0.85/M out | completion: 0.00000085 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Z.ai: GLM 4.5 Airvia Novita · bf16 | $0.85/M out | completion: 0.00000085 / token (endpoint novita/bf16) | |
| APIMartNot disclosed | minimax-m2.1 | $0.864/M out | Input $0.216 / Output $0.864 · Per 1M tokens | |
| OpenRouterThird-party | Xiaomi: MiMo-V2.5-Provia AtlasCloud · fp8 | $0.87/M out | completion: 0.00000087 / token (endpoint atlas-cloud/fp8) | |
| OpenRouterThird-party | MiniMax: MiniMax M3 (batch) | $0.88/M out | completion: 0.00000088 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Qwen: Qwen3 VL 235B A22B Instructvia DeepInfra · fp8 | $0.88/M out | completion: 0.00000088 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Venice: Uncensored | $0.9/M out | completion: 0.0000009 / token (endpoint venice/fp16) | |
| OpenRouterOfficial | Mistral: Codestral 2508via Mistral | $0.9/M out | completion: 0.0000009 / token (endpoint mistral) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Luna Pro (batch)Prompt > 272K | $0.9/M out | completion: 0.0000009 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Luna (batch)Prompt > 272K | $0.9/M out | completion: 0.0000009 / token (>272000; endpoint openai) | |
| OpenRouterThird-party | Z.ai: GLM 4.6Vvia Novita · bf16 | $0.9/M out | completion: 0.0000009 / token (endpoint novita/bf16) | |
| APIMartNot disclosed | qwen3.7-plus | $0.915/M out | Input $0.2286 / Output $0.9146 · Per 1M tokens | |
| OpenRouterOfficial | Qwen: Qwen3.7 Plus (batch) | $0.92/M out | completion: 0.00000092 / token (endpoint alibaba) | |
| APIMartNot disclosed | step-3.7-flash | $0.925/M out | Input $0.1542 / Output $0.9254 · Per 1M tokens | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.1via DeepInfra · fp4 | $0.95/M out | completion: 0.00000095 / token (endpoint deepinfra/fp4) | |
| OpenRouterThird-party | MiniMax: MiniMax M2.5via Venice | $0.95/M out | completion: 0.00000095 / token (endpoint venice) | |
| OpenRouterOfficial | Morph: Morph V3 Large (batch) | $0.95/M out | completion: 0.00000095 / token (endpoint morph/fp8) | |
| ReplicatePlatform-hosted | meta/llama-4-maverick-instruct | $0.95/M out | $0.95 per million output tokens | |
| AibermNot disclosed | MiniMax M2.1 | $0.954/M out | model_ratio 0.5 × $2/M · group default ×0.23 · completion_ratio 4.148Claims official price $1.2/M out | |
| APIMartNot disclosed | gpt-5.6-luna | $0.96/M out | Input $0.16 / Output $0.96 · Per 1M tokens | |
| APIMartNot disclosed | minimax-m2.5 | $0.96/M out | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMartNot disclosed | minimax-m2.7 | $0.96/M out | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMartNot disclosed | minimax-m3 | $0.96/M out | Input $0.24 / Output $0.96 · Per 1M tokens | |
| OpenRouterThird-party | Meta: Muse Glimmer 30B (batch) | $0.96/M out | completion: 0.00000096 / token (endpoint deepinfra/bf16) | |
| OpenRouterThird-party | MiniMax: MiniMax M3via CoreWeave · fp4 | $0.96/M out | completion: 0.00000096 / token (endpoint coreweave/fp4) | |
| OpenRouterThird-party | Thinking Machines: Inkling Small (batch) | $0.96/M out | completion: 0.00000096 / token (endpoint deepinfra/fp8) | |
| OpenRouterOfficial | Qwen: Qwen3 Coder Flash | $0.975/M out | completion: 0.000000975 / token (endpoint alibaba) | |
| APIMartNot disclosed | gpt-5.4-nano | $1/M out | Input $0.16 / Output $1 · Per 1M tokens | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3 0324via SiliconFlow · fp8 | $1/M out | completion: 0.000001 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | DeepSeek: DeepSeek V3.1 Terminus | $1/M out | completion: 0.000001 / token (endpoint siliconflow/fp8) | |
| OpenRouterThird-party | Meta: Llama 4 Maverickvia Parasail · fp8 | $1/M out | completion: 0.000001 / token (endpoint parasail/fp8) | |
| OpenRouterOfficial | OpenAI: GPT-5 Mini (batch) | $1/M out | completion: 0.000001 / token (endpoint openai) |
