8,429 prices on 4,154 listings · last collected 4 h ago · 36 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on six 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.
Unit
All 8,429Per second of output 1,919Per minute 34Per video 486Per image 1,521Per megapixel 308Per million input tokens 982Per million output tokens 977Per million tokens 48Per million cached input tokens (read) 458Per million cache-write tokens 191Per thousand characters 64Per second of compute time 93Per run (default parameters) 1,023Other units (see the platform’s wording) 325
Showing 201–300 of 977
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Google: Gemma 2 27B | $0.65/M out | completion: 0.00000065 / token | |
| OpenRouter | ReMM SLERP 13B | $0.65/M out | completion: 0.00000065 / token | |
| Replicate | meta/llama-4-scout-instruct | $0.65/M out | $0.65 per million output tokens | |
| APIMart | mimo-v2.5-pro | $0.6858/M out | Input $0.3429 / Output $0.6858 · Per 1M tokens | |
| OpenRouter | LiquidAI: LFM2.5-24B-A2B | $0.7/M out | completion: 0.0000007 / token | |
| OpenRouter | Meta: Llama 3.1 70B Instruct | $0.72/M out | completion: 0.00000072 / token | |
| Replicate | openai/gpt-oss-120b | $0.72/M out | $0.72 per million output tokens | |
| OpenRouter | Google: Gemini 3.1 Flash Lite (batch) | $0.75/M out | completion: 0.00000075 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite (batch)Reasoning | $0.75/M out | internal_reasoning: 0.00000075 / token | |
| OpenRouter | Mancer: Weaver (alpha) | $0.75/M out | completion: 0.00000075 / token | |
| OpenRouter | OpenAI: GPT-6 LunaPrompt > 272K | $0.75/M out | completion: 0.00000075 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna ProPrompt > 272K | $0.75/M out | completion: 0.00000075 / token (>272000) | |
| OpenRouter | Qwen: Qwen3 VL 8B Instruct | $0.75/M out | completion: 0.00000075 / token | |
| OpenRouter | OpenAI: GPT Luna LatestPrompt > 272K | $0.75/M out | completion: 0.00000075 / token (>272000) | |
| OpenRouter | Qwen: Qwen-Plus | $0.78/M out | completion: 0.00000078 / token | |
| OpenRouter | Meta: Llama 3.3 70B Instruct | $0.79/M out | completion: 0.00000079 / token | |
| OpenRouter | ByteDance Seed: Seed 1.6 FlashPrompt > 128K | $0.8/M out | completion: 0.0000008 / token (>128000) | |
| OpenRouter | ByteDance Seed: Seed-2.0-MiniPrompt > 128K | $0.8/M out | completion: 0.0000008 / token (>128000) | |
| OpenRouter | OpenAI: GPT-4.1 Mini (batch) | $0.8/M out | completion: 0.0000008 / token | |
| OpenRouter | Qwen: Qwen3 235B A22B Instruct 2507 | $0.8/M out | completion: 0.0000008 / token | |
| OpenRouter | Qwen: Qwen3 Coder Next | $0.8/M out | completion: 0.0000008 / token | |
| OpenRouter | Qwen: Qwen3.7 FlashPrompt > 256K | $0.8/M out | completion: 0.0000008 / token (>256000) | |
| OpenRouter | TheDrummer: Skyfall 36B V2 | $0.8/M out | completion: 0.0000008 / token | |
| APIMart | deepseek-v3-0324 | $0.8224/M out | Input $0.2056 / Output $0.8224 · Per 1M tokens | |
| APIMart | qwen3.6-flash | $0.8227/M out | Input $0.1371 / Output $0.8227 · Per 1M tokens | |
| OpenRouter | MiniMax: MiniMax M2.7 | $0.84/M out | completion: 0.00000084 / token | |
| OpenRouter | Sao10K: Llama 3.1 Euryale 70B v2.2 | $0.85/M out | completion: 0.00000085 / token | |
| OpenRouter | Z.ai: GLM 4.5 Air | $0.85/M out | completion: 0.00000085 / token | |
| APIMart | minimax-m2.1 | $0.864/M out | Input $0.216 / Output $0.864 · Per 1M tokens | |
| OpenRouter | Xiaomi: MiMo-V2.6-Pro | $0.87/M out | completion: 0.00000087 / token | |
| OpenRouter | MiniMax: MiniMax M3 (batch) | $0.88/M out | completion: 0.00000088 / token | |
| OpenRouter | DeepSeek: DeepSeek V3 | $0.89/M out | completion: 0.00000089 / token | |
| OpenRouter | Venice: Uncensored | $0.9/M out | completion: 0.0000009 / token | |
| OpenRouter | Mistral: Codestral 2508 | $0.9/M out | completion: 0.0000009 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro (batch)Prompt > 272K | $0.9/M out | completion: 0.0000009 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna (batch)Prompt > 272K | $0.9/M out | completion: 0.0000009 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.6 35B A3B | $0.9/M out | completion: 0.0000009 / token | |
| OpenRouter | Z.ai: GLM 4.6V | $0.9/M out | completion: 0.0000009 / token | |
| APIMart | qwen3.7-plus | $0.9146/M out | Input $0.2286 / Output $0.9146 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.7 Plus (batch) | $0.92/M out | completion: 0.00000092 / token | |
| APIMart | step-3.7-flash | $0.9254/M out | Input $0.1542 / Output $0.9254 · Per 1M tokens | |
| OpenRouter | DeepSeek: DeepSeek V3.1 | $0.95/M out | completion: 0.00000095 / token | |
| OpenRouter | Morph: Morph V3 Large (batch) | $0.95/M out | completion: 0.00000095 / token | |
| Replicate | meta/llama-4-maverick-instruct | $0.95/M out | $0.95 per million output tokens | |
| APIMart | gpt-5.6-luna | $0.96/M out | Input $0.16 / Output $0.96 · Per 1M tokens | |
| APIMart | minimax-m2.5 | $0.96/M out | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | minimax-m2.7 | $0.96/M out | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | minimax-m3 | $0.96/M out | Input $0.24 / Output $0.96 · Per 1M tokens | |
| OpenRouter | Meta: Muse Glimmer 30B (batch) | $0.96/M out | completion: 0.00000096 / token | |
| OpenRouter | Thinking Machines: Inkling Small (batch) | $0.96/M out | completion: 0.00000096 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash | $0.975/M out | completion: 0.000000975 / token | |
| APIMart | gpt-5.4-nano | $1/M out | Input $0.16 / Output $1 · Per 1M tokens | |
| OpenRouter | DeepSeek: DeepSeek V3.1 Terminus | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Meta: Llama 4 Maverick | $1/M out | completion: 0.000001 / token | |
| OpenRouter | OpenAI: GPT-5 Mini (batch) | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Perplexity: Sonar | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Qwen2.5 Coder 32B Instruct | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Qwen: Qwen2.5 VL 72B Instruct | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Qwen: Qwen3 Coder 480B A35B | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Qwen: Qwen3 VL 30B A3B Thinking | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Qwen: Qwen3.5-35B-A3B | $1/M out | completion: 0.000001 / token | |
| OpenRouter | Reflection: Beam 1.0 501B A23B | $1/M out | completion: 0.000001 / token | |
| Replicate | qwen/qwen3-235b-a22b-instruct-2507 | $1.06/M out | $1.06 per million output tokens | |
| kie.ai | gpt-image-2-6-flareText to imageSVG output · gpt-5.6-luna Output | $1.08/M out | 216 credits per million tokens ($1.08)Claims fal charges $1.2/M out | |
| kie.ai | gpt-image-2-6-sunburstText to imageSVG output · gpt-5.6-luna Output | $1.08/M out | 216 credits per million tokens ($1.08)Claims fal charges $1.2/M out | |
| OpenRouter | Qwen: Qwen3 Next 80B A3B Instruct | $1.1/M out | completion: 0.0000011 / token | |
| Replicate | qwen/qwen3-7-plus256000 | $1.101/M out | $1.101 per million output tokens (,256000) | |
| kie.ai | Gemini 3.6 Flash | $1.125/M out | 225 credits per million tokens ($1.125)Claims fal charges $3.75/M out | |
| kie.ai | Gemini 3.7 Flash | $1.125/M out | 225 credits per million tokens ($1.125)Claims fal charges $3.75/M out | |
| kie.ai | Gemini 3.8 Flash | $1.125/M out | 225 credits per million tokens ($1.125)Claims fal charges $3.75/M out | |
| OpenRouter | Qwen: Qwen3.6 Flash | $1.125/M out | completion: 0.000001125 / token | |
| OpenRouter | DeepSeek: DeepSeek V3 0324 | $1.14/M out | completion: 0.00000114 / token | |
| OpenRouter | StepFun: Step 3.7 Flash | $1.15/M out | completion: 0.00000115 / token | |
| APIMart | GPT-3.5 Turbo | $1.2/M out | Input $0.4 / Output $1.2 · Per 1M tokens | |
| APIMart | gemini-3.1-flash-lite-preview | $1.2/M out | Input $0.2 / Output $1.2 · Per 1M tokens | |
| APIMart | gpt-3.5-turbo-0125 | $1.2/M out | Input $0.4 / Output $1.2 · Per 1M tokens | |
| APIMart | nano-banana-2-lite | $1.2/M out | Input $0.2 / Output $1.2 · Per 1M tokens | |
| OpenRouter | Meituan: LongCat 2.0 | $1.2/M out | completion: 0.0000012 / token | |
| OpenRouter | Meta: Muse Glimmer 30B | $1.2/M out | completion: 0.0000012 / token | |
| OpenRouter | MiniMax: MiniMax M2.5 | $1.2/M out | completion: 0.0000012 / token | |
| OpenRouter | MiniMax: MiniMax M3 | $1.2/M out | completion: 0.0000012 / token | |
| OpenRouter | Morph: Morph V3 Fast | $1.2/M out | completion: 0.0000012 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna | $1.2/M out | completion: 0.0000012 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro | $1.2/M out | completion: 0.0000012 / token | |
| OpenRouter | Thinking Machines: Inkling Small | $1.2/M out | completion: 0.0000012 / token | |
| APIMart | deepseek-r1-0528 | $1.2322/M out | Input $0.408 / Output $1.2322 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)Prompt > 100K | $1.25/M out | completion: 0.00000125 / token (>100000) | |
| OpenRouter | Google: Gemini 3.5 Flash Lite (batch) | $1.25/M out | completion: 0.00000125 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite (batch)Reasoning | $1.25/M out | internal_reasoning: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-5.4 Nano | $1.25/M out | completion: 0.00000125 / token | |
| OpenRouter | Relace: Relace Apply 3 | $1.25/M out | completion: 0.00000125 / token | |
| OpenRouter | Z.ai: GLM 5.3 FlashX | $1.25/M out | completion: 0.00000125 / token | |
| OpenRouter | Z.ai: GLM 5.3 FlashX Legal | $1.25/M out | completion: 0.00000125 / token | |
| OpenRouter | Tencent: Hy4 | $1.2505/M out | completion: 0.0000012505 / token | |
| APIMart | glm-5 | $1.28/M out | Input $0.8 / Output $1.28 · Per 1M tokens | |
| APIMart | gpt-4.1-mini | $1.28/M out | Input $0.32 / Output $1.28 · Per 1M tokens | |
| APIMart | gpt-4.1-mini-2025-04-14 | $1.28/M out | Input $0.32 / Output $1.28 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.7 Plus | $1.28/M out | completion: 0.00000128 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash Vision Exp | $1.32/M out | completion: 0.00000132 / token | |
| APIMart | qwen3.8-27b | $1.3714/M out | Input $0.3429 / Output $1.3714 · Per 1M tokens |
