8,429 prices on 4,154 listings · last collected 7 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 201–300 of 2,592
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | OpenAI: GPT-5 Mini (batch) | $0.125/M in | prompt: 0.000000125 / token | |
| OpenRouter | Z.ai: GLM 4.5 Air | $0.13/M in | prompt: 0.00000013 / token | |
| OpenRouter | Tencent: Hy3 | $0.132/M in | prompt: 0.000000132 / token | |
| APIMart | qwen3.6-flash | $0.1371/M in | Input $0.1371 / Output $0.8227 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3 235B A22B Instruct 2507 | $0.14/M in | prompt: 0.00000014 / token | |
| OpenRouter | Qwen: Qwen3.5-35B-A3B | $0.14/M in | prompt: 0.00000014 / token | |
| OpenRouter | Tencent: Hunyuan A13B Instruct | $0.14/M in | prompt: 0.00000014 / token | |
| OpenRouter | Xiaomi: MiMo-V2.6-Flash | $0.14/M in | prompt: 0.00000014 / token | |
| OpenRouter | Cohere: Command R (08-2024) | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite (batch)Audio input | $0.15/M in | audio: 0.00000015 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite (batch) | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | MiniMax: MiniMax M3.1 Flash | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Mistral: Ministral 3 8B 2512 | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Mistral: Mistral Small 4 | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Super VL | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | OpenAI: GPT-4o-mini | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | OpenAI: GPT-4o-mini (2024-07-18) | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Perceptron: Perceptron Mk1 | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Perceptron: Perceptron Mk1.5 | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Qwen: Qwen3 Coder 30B A3B Instruct | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Qwen: Qwen3 VL 30B A3B Instruct | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Qwen: Qwen3.8 27B | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Qwen: Qwen3.8 Flash | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Qwen: Qwen3.8 Omni Flash | $0.15/M in | prompt: 0.00000015 / token | |
| OpenRouter | Upstage: Solar Pro 4 | $0.15/M in | prompt: 0.00000015 / token | |
| Replicate | openai/gpt-4o-mini | $0.15/M in | $0.15 per million input tokens | |
| OpenRouter | MoonshotAI: Kimi Latest | $0.151/M in | prompt: 0.000000151 / token | |
| APIMart | step-3.7-flash | $0.1542/M in | Input $0.1542 / Output $0.9254 · Per 1M tokens | |
| APIMart | gpt-5.4-nano | $0.16/M in | Input $0.16 / Output $1 · Per 1M tokens | |
| APIMart | gpt-5.6-luna | $0.16/M in | Input $0.16 / Output $0.96 · Per 1M tokens | |
| APIMart | omni-moderation-latest | $0.16/M in | Input $0.16 / Output $0.16 · Per 1M tokens | |
| APIMart | text-moderation-latest | $0.16/M in | Input $0.16 / Output $0.16 · Per 1M tokens | |
| APIMart | text-moderation-stable | $0.16/M in | Input $0.16 / Output $0.16 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.8 27B (batch) | $0.16/M in | prompt: 0.00000016 / token | |
| OpenRouter | Qwen: Qwen3.5-9B | $0.17/M in | prompt: 0.00000017 / token | |
| Replicate | meta/llama-4-scout-instruct | $0.17/M in | $0.17 per million input tokens | |
| APIMart | deepseek-v4-flash | $0.1714/M in | Input $0.1714 / Output $0.5143 · Per 1M tokens | |
| OpenRouter | Meta: Llama Guard 4 12B | $0.18/M in | prompt: 0.00000018 / token | |
| OpenRouter | Tencent: Hy3 preview | $0.18/M in | prompt: 0.00000018 / token | |
| Replicate | openai/gpt-oss-120b | $0.18/M in | $0.18 per million input tokens | |
| OpenRouter | Qwen: Qwen3.6 Flash | $0.1875/M in | prompt: 0.0000001875 / token | |
| OpenRouter | MoonshotAI: Kimi K3 | $0.192/M in | prompt: 0.000000192 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash | $0.195/M in | prompt: 0.000000195 / token | |
| APIMart | gemini-3.1-flash-lite-preview | $0.2/M in | Input $0.2 / Output $1.2 · Per 1M tokens | |
| APIMart | gpt-5-mini | $0.2/M in | Input $0.2 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-5-mini-2025-08-07 | $0.2/M in | Input $0.2 / Output $1.6 · Per 1M tokens | |
| APIMart | gpt-5.1-codex-mini | $0.2/M in | Input $0.2 / Output $1.6 · Per 1M tokens | |
| OpenRouter | ByteDance Seed: Seed-2.0-MiniPrompt > 128K | $0.2/M in | prompt: 0.0000002 / token (>128000) | |
| OpenRouter | Venice: Uncensored | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | Google: Gemma 4 31B | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | Mistral: Ministral 3 14B 2512 | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | Mistral: Saba | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | NVIDIA: Nemotron 3.5 Content Safety | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-4.1 Mini (batch) | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.4 Nano | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro (batch)Prompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna (batch)Prompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 LunaPrompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna ProPrompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.7 FlashPrompt > 256K | $0.2/M in | prompt: 0.0000002 / token (>256000) | |
| OpenRouter | Ricursive: Ripple 65B Preview | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | StepFun: Step 3.7 Flash | $0.2/M in | prompt: 0.0000002 / token | |
| OpenRouter | OpenAI: GPT Luna LatestPrompt > 272K | $0.2/M in | prompt: 0.0000002 / token (>272000) | |
| Replicate | meta/llama-guard-4-12b | $0.2/M in | $0.20 per million input tokens | |
| APIMart | deepseek-v3-0324 | $0.2056/M in | Input $0.2056 / Output $0.8224 · Per 1M tokens | |
| APIMart | deepseek-v3.2 | $0.2056/M in | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| APIMart | deepseek-v3.2-exp | $0.2056/M in | Input $0.2056 / Output $0.3084 · Per 1M tokens | |
| OpenRouter | MiniMax: MiniMax M2.7 | $0.21/M in | prompt: 0.00000021 / token | |
| OpenRouter | Qwen: Qwen3 VL 235B A22B Instruct | $0.21/M in | prompt: 0.00000021 / token | |
| APIMart | minimax-m2.1 | $0.216/M in | Input $0.216 / Output $0.864 · Per 1M tokens | |
| OpenRouter | MiniMax: MiniMax M3 (batch) | $0.224/M in | prompt: 0.000000224 / token | |
| kie.ai | Gemini 3.6 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims fal charges $0.75/M in | |
| kie.ai | Gemini 3.7 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims fal charges $0.75/M in | |
| kie.ai | Gemini 3.8 Flash | $0.225/M in | 45 credits per million tokens ($0.225)Claims fal charges $0.75/M in | |
| APIMart | qwen3.6-plus | $0.2286/M in | Input $0.2286 / Output $1.3718 · Per 1M tokens | |
| APIMart | qwen3.7-plus | $0.2286/M in | Input $0.2286 / Output $0.9146 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.7 Plus (batch) | $0.23/M in | prompt: 0.00000023 / token | |
| OpenRouter | DeepSeek: DeepSeek V4 Pro 0423 | $0.231246/M in | prompt: 0.000000231246 / token | |
| APIMart | gemini-3.5-flash-lite | $0.24/M in | Input $0.24 / Output $1.9992 · Per 1M tokens | |
| APIMart | minimax-m2.5 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | minimax-m2.7 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | minimax-m3 | $0.24/M in | Input $0.24 / Output $0.96 · Per 1M tokens | |
| APIMart | qwen-turbo | $0.24/M in | Input $0.24 / Output $2.4 · Per 1M tokens | |
| OpenRouter | Meta: Muse Glimmer 30B (batch) | $0.24/M in | prompt: 0.00000024 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)Prompt > 100K | $0.25/M in | prompt: 0.00000025 / token (>100000) | |
| OpenRouter | ByteDance Seed: Seed 1.6 | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | ByteDance Seed: Seed-2.0-Lite | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | DeepSeek: DeepSeek V3.1 | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview (batch) | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite Preview | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite (batch)Audio input | $0.25/M in | audio: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5 Mini | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.1-Codex-Mini | $0.25/M in | prompt: 0.00000025 / token | |
| OpenRouter | Qwen: Qwen3 VL 8B Instruct | $0.25/M in | prompt: 0.00000025 / token | |
| Replicate | meta/llama-4-maverick-instruct | $0.25/M in | $0.25 per million input tokens | |
| Replicate | openai/gpt-5-mini | $0.25/M in | $0.25 per million input tokens | |
| Replicate | openai/gpt-5-structuredgpt-5-mini | $0.25/M in | $0.25 per million input tokens (gpt-5-mini) |
