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 301–400 of 2,592
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| fal | Isaac 0.1 | $0.26/M in | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| fal | Isaac 0.1 [OpenAI Compatible Endpoint] | $0.26/M in | $0.26 per 1M input tokens, $2.17 per 1M output tokens | |
| OpenRouter | DeepSeek: DeepSeek V3.2 | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen-Plus | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen3.5-122B-A10B | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen3.5-27B | $0.26/M in | prompt: 0.00000026 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-02-15 | $0.26/M in | prompt: 0.00000026 / token | |
| Replicate | perceptron-ai-inc/isaac-0.1 | $0.26/M in | $0.26 per million input tokens | |
| Replicate | qwen/qwen3-235b-a22b-instruct-2507 | $0.264/M in | $0.264 per million input tokens | |
| OpenRouter | DeepSeek: DeepSeek V3.1 Terminus | $0.27/M in | prompt: 0.00000027 / token | |
| OpenRouter | DeepSeek: DeepSeek V3.2 Exp | $0.27/M in | prompt: 0.00000027 / token | |
| kie.ai | Claude-Haiku-4-5 | $0.275/M in | 55 credits per million tokens ($0.275)Claims fal charges $1/M in | |
| Replicate | qwen/qwen3-7-plus256000 | $0.276/M in | $0.276 per million input tokens (,256000) | |
| OpenRouter | DeepSeek: DeepSeek V3 0324 | $0.29/M in | prompt: 0.00000029 / token | |
| OpenRouter | Qwen: Qwen3 VL 30B A3B Thinking | $0.29/M in | prompt: 0.00000029 / token | |
| kie.ai | gpt-6-1-terra | $0.3/M in | 60 credits per million tokens ($0.3)Claims fal charges $1/M in | |
| OpenRouter | Amazon: Nova 2 Lite | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Cohere: Command A+ | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Google: Gemini 2.5 Flash | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Google: Gemini 2.5 Flash LiteAudio input | $0.3/M in | audio: 0.0000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash LiteAudio input | $0.3/M in | audio: 0.0000003 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Meituan: LongCat 2.0 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Meta: Muse Glimmer 30B | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | MiniMax: MiniMax M2.5 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | MiniMax: MiniMax M3 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Mistral: Codestral 2508 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Moondream: Moondream 3 Preview | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Moondream: Moondream 3.1 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Qwen: Qwen3 Coder 480B A35B | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-20 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Reflection: Beam 1.0 501B A23B | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | TheDrummer: Cydonia 24B V4.1 | $0.3/M in | prompt: 0.0000003 / token | |
| OpenRouter | Z.ai: GLM 4.6V | $0.3/M in | prompt: 0.0000003 / token | |
| Replicate | google/gemini-2.5-flash | $0.3/M in | $0.30 per million input tokens | |
| APIMart | babbage-002 | $0.32/M in | Input $0.32 / Output $0.32 · Per 1M tokens | |
| APIMart | gpt-4.1-mini | $0.32/M in | Input $0.32 / Output $1.28 · Per 1M tokens | |
| APIMart | gpt-4.1-mini-2025-04-14 | $0.32/M in | Input $0.32 / Output $1.28 · Per 1M tokens | |
| OpenRouter | DeepSeek: DeepSeek V3 | $0.32/M in | prompt: 0.00000032 / token | |
| OpenRouter | Qwen: Qwen3.6 27B | $0.32/M in | prompt: 0.00000032 / token | |
| OpenRouter | Qwen: Qwen3.7 Plus | $0.32/M in | prompt: 0.00000032 / token | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 32K | $0.325/M in | prompt: 0.000000325 / token (>32000) | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-02-15Prompt > 256K | $0.325/M in | prompt: 0.000000325 / token (>256000) | |
| OpenRouter | Qwen: Qwen3.6 Plus | $0.325/M in | prompt: 0.000000325 / token | |
| OpenRouter | Z.ai: GLM 5.2 (batch) | $0.341/M in | prompt: 0.000000341 / token | |
| OpenRouter | Z.ai: GLM 5.3 (batch) | $0.341/M in | prompt: 0.000000341 / token | |
| APIMart | mimo-v2.5-pro | $0.3429/M in | Input $0.3429 / Output $0.6858 · Per 1M tokens | |
| APIMart | qwen3.8-27b | $0.3429/M in | Input $0.3429 / Output $1.3714 · Per 1M tokens | |
| OpenRouter | LiquidAI: LFM2.5-2.6B | $0.35/M in | prompt: 0.00000035 / token | |
| OpenRouter | Meta: Llama 4 Maverick | $0.35/M in | prompt: 0.00000035 / token | |
| OpenRouter | ReMM SLERP 13B | $0.35/M in | prompt: 0.00000035 / token | |
| OpenRouter | Mistral: Mistral Small 3.1 24B | $0.351/M in | prompt: 0.000000351 / token | |
| APIMart | glm-4.6 | $0.36/M in | Input $0.36 / Output $1.44 · Per 1M tokens | |
| OpenRouter | Qwen2.5 72B Instruct | $0.36/M in | prompt: 0.00000036 / token | |
| OpenRouter | Thinking Machines: Inkling Small (batch) | $0.36/M in | prompt: 0.00000036 / token | |
| OpenRouter | Z.ai: GLM 5.3 FlashX | $0.37/M in | prompt: 0.00000037 / token | |
| OpenRouter | Z.ai: GLM 5.3 FlashX Legal | $0.37/M in | prompt: 0.00000037 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch)Audio input | $0.375/M in | audio: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch) | $0.375/M in | prompt: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch)Audio input | $0.375/M in | audio: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch) | $0.375/M in | prompt: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch)Audio input | $0.375/M in | audio: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch) | $0.375/M in | prompt: 0.000000375 / token | |
| OpenRouter | OpenAI: GPT-5.4 Mini (batch) | $0.375/M in | prompt: 0.000000375 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-20Prompt > 256K | $0.375/M in | prompt: 0.000000375 / token (>256000) | |
| APIMart | GPT-3.5 Turbo | $0.4/M in | Input $0.4 / Output $1.2 · Per 1M tokens | |
| APIMart | gemini-3-flash-preview | $0.4/M in | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMart | gemini-3-flash-preview-nothinking | $0.4/M in | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMart | gemini-3-flash-preview-thinking | $0.4/M in | Input $0.4 / Output $2.4 · Per 1M tokens | |
| APIMart | glm-4.7 | $0.4/M in | Input $0.4 / Output $1.68 · Per 1M tokens | |
| APIMart | gpt-3.5-turbo-0125 | $0.4/M in | Input $0.4 / Output $1.2 · Per 1M tokens | |
| APIMart | kimi-k2-instruct | $0.4/M in | Input $0.4 / Output $1.68 · Per 1M tokens | |
| APIMart | kimi-k2-thinking | $0.4/M in | Input $0.4 / Output $1.68 · Per 1M tokens | |
| fal | Moondream3 Preview [Caption] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| fal | Moondream3 Preview [Detect] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| fal | Moondream3 Preview [Point] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| fal | Moondream 3 Preview [Query] | $0.4/M in | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| OpenRouter | Mancer: Weaver (alpha) | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouter | Mistral: Devstral 2 2512 | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouter | Mistral: Mistral Medium 3 | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouter | Mistral: Mistral Medium 3.1 | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouter | Morph: Morph V3 Fast (batch) | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-4.1 Mini | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouter | OpenAI: GPT-5.6 LunaPrompt > 272K | $0.4/M in | prompt: 0.0000004 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna ProPrompt > 272K | $0.4/M in | prompt: 0.0000004 / token (>272000) | |
| OpenRouter | TheDrummer: UnslopNemo 12B | $0.4/M in | prompt: 0.0000004 / token | |
| OpenRouter | Xiaomi: MiMo-V2.5 | $0.4/M in | prompt: 0.0000004 / token | |
| Replicate | openai/gpt-4.1-mini | $0.4/M in | $0.40 per million input tokens | |
| APIMart | deepseek-r1-0528 | $0.408/M in | Input $0.408 / Output $1.2322 · Per 1M tokens | |
| APIMart | kimi-k2.5 | $0.4112/M in | Input $0.4112 / Output $0.5551 · Per 1M tokens | |
| OpenRouter | Tencent: Hy4 | $0.417/M in | prompt: 0.000000417 / token | |
| OpenRouter | Xiaomi: MiMo-V2.6-Pro | $0.435/M in | prompt: 0.000000435 / token | |
| kie.ai | gpt-5-2 | $0.44/M in | 87.5 credits per million tokens ($0.44)Claims fal charges $1.75/M in | |
| OpenRouter | DeepSeek: DeepSeek V4 Flash Vision Exp | $0.44/M in | prompt: 0.00000044 / token | |
| APIMart | deepseek-r1 | $0.448/M in | Input $0.448 / Output $1.792 · Per 1M tokens | |
| APIMart | deepseek-r1-250528 | $0.448/M in | Input $0.448 / Output $1.792 · Per 1M tokens | |
| OpenRouter | Morph: Morph V3 Large (batch) | $0.45/M in | prompt: 0.00000045 / token | |
| OpenRouter | Qwen: Qwen3 235B A22B Thinking 2507 | $0.45/M in | prompt: 0.00000045 / token | |
| OpenRouter | Thinking Machines: Inkling Small | $0.45/M in | prompt: 0.00000045 / token | |
| APIMart | gpt-4o-mini-realtime-preview | $0.48/M in | Input $0.48 / Output $1.92 · Per 1M tokens |
