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 2,608Per 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) 200Other units (see the platform’s wording) 14
Showing 101–200 of 866
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Tencent: Hy-MT2-30B-A3B | $0.074/M in | prompt: 0.000000074 / token | |
| OpenRouter | Tencent: Hy-MT2-7B | $0.074/M in | prompt: 0.000000074 / token | |
| OpenRouter | ByteDance Seed: Seed 1.6 Flash | $0.075/M in | prompt: 0.000000075 / token | |
| OpenRouter | Mistral: Mistral Small 3.2 24B | $0.075/M in | prompt: 0.000000075 / token | |
| OpenRouter | Nex AGI: Nex-N2.5-Pro | $0.075/M in | prompt: 0.000000075 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Super | $0.075/M in | prompt: 0.000000075 / token | |
| OpenRouter | OpenAI: GPT-4o-mini (batch) | $0.075/M in | prompt: 0.000000075 / token | |
| OpenRouter | OpenAI: gpt-oss-safeguard-20b | $0.075/M in | prompt: 0.000000075 / token | |
| OpenRouter | PrismML: Ternary Bonsai 2 27B | $0.075/M in | prompt: 0.000000075 / token | |
| APIMart | claude-haiku-5-5 | $0.08/M in | Input $0.08 / Output $0.4 · Per 1M tokens | |
| APIMart | gpt-4.1-nano | $0.08/M in | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-4.1-nano-2025-04-14 | $0.08/M in | Input $0.08 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-6-luna | $0.08/M in | Input $0.08 / Output $0.4 · Per 1M tokens | |
| APIMart | text-embedding-ada-002 | $0.08/M in | Input $0.08 / Output $0.08 · Per 1M tokens | |
| OpenRouter | Google: Gemma 3 27B | $0.08/M in | prompt: 0.00000008 / token | |
| OpenRouter | MythoMax 13B | $0.08/M in | prompt: 0.00000008 / token | |
| OpenRouter | LiquidAI: LFM3-1.7B | $0.08/M in | prompt: 0.00000008 / token | |
| OpenRouter | PrismML: Ternary Bonsai 2 9B | $0.08/M in | prompt: 0.00000008 / token | |
| OpenRouter | Qwen: Qwen3 32B | $0.08/M in | prompt: 0.00000008 / token | |
| OpenRouter | Qwen: Qwen3 Next 80B A3B Instruct | $0.09/M in | prompt: 0.00000009 / token | |
| Replicate | openai/gpt-oss-20b | $0.09/M in | $0.09 per million input tokens | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash 0423 | $0.091/M in | prompt: 0.000000091 / token | |
| APIMart | qwen3.8-flash | $0.0914/M in | Input $0.0914 / Output $0.3086 · Per 1M tokens | |
| OpenRouter | DeepSeek: DeepSeek Pro Latest | $0.0999/M in | prompt: 0.0000000999 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | ByteDance Seed: Seed 1.6 FlashPrompt > 128K | $0.1/M in | prompt: 0.0000001 / token (>128000) | |
| OpenRouter | ByteDance Seed: Seed-2.0-Mini | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | ByteDance: UI-TARS 7B | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Google: Gemini 2.5 Flash Lite | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Meta: Llama 4 Scout | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Meta: Muse Spark 1.2 Contributor | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Meta: Muse Spark 1.3 Contributor | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Mistral: Ministral 3 3B 2512 | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Mistral: Voxtral Small 24B 2507 | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT-4.1 Nano | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT-5.4 Nano (batch) | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro (batch) | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna (batch) | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT-6 Luna | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch)Prompt > 272K | $0.1/M in | prompt: 0.0000001 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna (batch)Prompt > 272K | $0.1/M in | prompt: 0.0000001 / token (>272000) | |
| OpenRouter | Qwen: Qwen2.5 7B Instruct | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Qwen: Qwen3 30B A3B Instruct 2507 | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Qwen: Qwen3.6 35B A3B | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Qwen: Qwen3.7 FlashPrompt > 32K | $0.1/M in | prompt: 0.0000001 / token (>32000) | |
| OpenRouter | Reka Edge | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Reka Flash 3 | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | StepFun: Step 3.5 Flash | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | Anthropic: Claude Haiku Latest | $0.1/M in | prompt: 0.0000001 / token | |
| OpenRouter | OpenAI: GPT Luna Latest | $0.1/M in | prompt: 0.0000001 / token | |
| Replicate | ibm-granite/granite-20b-code-instruct-8k | $0.1/M in | $0.10 per million input tokens | |
| Replicate | meta/llama-2-13b | $0.1/M in | $0.10 per million input tokens | |
| Replicate | meta/llama-2-13b-chat | $0.1/M in | $0.10 per million input tokens | |
| APIMart | text-embedding-3-large | $0.104/M in | Input $0.104 / Output $0.104 · Per 1M tokens | |
| OpenRouter | DeepSeek: DeepSeek V4 Pro 0813 | $0.111/M in | prompt: 0.000000111 / token | |
| APIMart | deepseek-v4.1-flash | $0.1143/M in | Input $0.1143 / Output $0.4571 · Per 1M tokens | |
| APIMart | GPT-4o Mini | $0.12/M in | Input $0.12 / Output $0.48 · Per 1M tokens | |
| kie.ai | DeepSeek V4.1 Flash | $0.12/M in | 24 credits per million tokens ($0.12) | |
| OpenRouter | Qwen: Qwen3 14B | $0.12/M in | prompt: 0.00000012 / token | |
| OpenRouter | Qwen: Qwen3 30B A3B | $0.12/M in | prompt: 0.00000012 / token | |
| OpenRouter | Qwen: Qwen3 Coder Next | $0.12/M in | prompt: 0.00000012 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite (batch) | $0.125/M in | prompt: 0.000000125 / token | |
| 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 |
