8,429 prices on 4,154 listings · last collected 8 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.
Model
Gemini 
Claude 
Qwen 
DeepSeek 
GLM 
Mistral 
Kimi 
Llama 
MiniMax 
Nemotron 
Hunyuan Unit
All 2,592Per second of output 5Per image 32Per million input tokens 866Per million output tokens 859Per million tokens 5Per million cached input tokens (read) 425Per million cache-write tokens 188Per thousand characters 2Per second of compute time 12Per run (default parameters) 184Other units (see the platform’s wording) 14
Showing 1101–1200 of 2,592
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| 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 | |
| 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 | |
| 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 | |
| APIMart | qwen3.6-plus | $1.3718/M out | Input $0.2286 / Output $1.3718 · Per 1M tokens | |
| OpenRouter | Z.ai: GLM 5.2 (batch) | $1.381/M out | completion: 0.000001381 / token | |
| OpenRouter | Z.ai: GLM 5.3 (batch) | $1.381/M out | completion: 0.000001381 / token | |
| OpenRouter | AionLabs: Aion-3.0-Mini | $1.4/M out | completion: 0.0000014 / token |
