8,429 prices on 4,154 listings · last collected 5 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.
Qwen 
Gemini 
Mistral 
Nemotron 
Kimi 
Hunyuan 
DeepSeek 
MiniMax 
Llama Showing 201–273 of 273
“Cheapest” is the lowest exact price in this unit for your search. Rows can differ in resolution, length or quality — read the label, or add it to the search (e.g. “1080”).
Per million output tokens8
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| Replicate | google/gemini-3-pro200000 | $12/M out | $0.012 per thousand output tokens (,200000) | |
| OpenRouter | MoonshotAI: Kimi K3 | $16/M out | completion: 0.000016 / token | |
| Replicate | google/gemini-3-pro200000 | $18/M out | $0.018 per thousand output tokens (200000,) | |
| APIMart | o3-deep-research | $32/M out | Input $8 / Output $32 · Per 1M tokens | |
| APIMart | o3-deep-research-2025-06-26 | $32/M out | Input $8 / Output $32 · Per 1M tokens | |
| APIMart | o3-pro | $64/M out | Input $16 / Output $64 · Per 1M tokens | |
| APIMart | o3-pro-2025-06-10 | $64/M out | Input $16 / Output $64 · Per 1M tokens | |
| OpenRouter | OpenAI: o3 Pro | $80/M out | completion: 0.00008 / token |
Per million tokens1
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| fal | Nemotron 3 Nano Omni | $10/M tokCheapest | $0.01 / 1000 tokens |
Per million cached input tokens (read)33
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Mistral: Ministral 3 3B 2512 | $0.01/M cache readCheapest | input_cache_read: 0.00000001 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Nano 30B A3B | $0.012/M cache read | input_cache_read: 0.000000012 / token | |
| OpenRouter | Mistral: Ministral 3 8B 2512 | $0.015/M cache read | input_cache_read: 0.000000015 / token | |
| OpenRouter | Mistral: Ministral 3 14B 2512 | $0.02/M cache read | input_cache_read: 0.00000002 / token | |
| OpenRouter | Meta: Muse Glimmer 30B (batch) | $0.032/M cache read | input_cache_read: 0.000000032 / token | |
| OpenRouter | Tencent: Hy3 | $0.033/M cache read | input_cache_read: 0.000000033 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash | $0.039/M cache read | input_cache_read: 0.000000039 / token | |
| OpenRouter | Google: Gemma 3 27B | $0.04/M cache read | input_cache_read: 0.00000004 / token | |
| OpenRouter | Meta: Muse Glimmer 30B | $0.04/M cache read | input_cache_read: 0.00000004 / token | |
| OpenRouter | Mistral: Mistral Medium 3 | $0.04/M cache read | input_cache_read: 0.00000004 / token | |
| OpenRouter | MiniMax: MiniMax M3 (batch) | $0.0448/M cache read | input_cache_read: 0.0000000448 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview | $0.05/M cache read | input_cache_read: 0.00000005 / token | |
| OpenRouter | Mistral: Mistral Large 3 2512 | $0.05/M cache read | input_cache_read: 0.00000005 / token | |
| OpenRouter | Qwen: Qwen3 235B A22B Instruct 2507 | $0.05/M cache read | input_cache_read: 0.00000005 / token | |
| OpenRouter | MiniMax: MiniMax M3 | $0.06/M cache read | input_cache_read: 0.00000006 / token | |
| OpenRouter | Tencent: Hy3 preview | $0.06/M cache read | input_cache_read: 0.00000006 / token | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 32K | $0.065/M cache read | input_cache_read: 0.000000065 / token (>32000) | |
| OpenRouter | Qwen: Qwen3 Coder Next | $0.07/M cache read | input_cache_read: 0.00000007 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview | $0.1/M cache read | input_audio_cache: 0.0000001 / token | |
| OpenRouter | Qwen: Qwen3 30B A3B Instruct 2507 | $0.1/M cache read | input_cache_read: 0.0000001 / token | |
| OpenRouter | Qwen: Qwen3 Coder 480B A35B | $0.1/M cache read | input_cache_read: 0.0000001 / token | |
| OpenRouter | Qwen: Qwen3 VL 235B A22B Instruct | $0.1/M cache read | input_cache_read: 0.0000001 / token | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 128K | $0.104/M cache read | input_cache_read: 0.000000104 / token (>128000) | |
| OpenRouter | DeepSeek: DeepSeek V3 0324 | $0.11/M cache read | input_cache_read: 0.00000011 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Ultra | $0.12/M cache read | input_cache_read: 0.00000012 / token | |
| OpenRouter | Qwen: Qwen3 VL 8B Instruct | $0.12/M cache read | input_cache_read: 0.00000012 / token | |
| OpenRouter | MoonshotAI: Kimi K3 | $0.182/M cache read | input_cache_read: 0.000000182 / token | |
| OpenRouter | MoonshotAI: Kimi K3 (batch) | $0.226/M cache read | input_cache_read: 0.000000226 / token | |
| kie.ai | Kimi K3 | $0.24/M cache read | 48 credits per million tokens ($0.24)Claims fal charges $0.3/M cache read | |
| OpenRouter | OpenAI: o3 (batch) | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | TheDrummer: Skyfall 36B V2 | $0.25/M cache read | input_cache_read: 0.00000025 / token | |
| OpenRouter | OpenAI: o3 Mini (batch) | $0.275/M cache read | input_cache_read: 0.000000275 / token | |
| OpenRouter | OpenAI: o3 | $0.5/M cache read | input_cache_read: 0.0000005 / token |
Per million cache-write tokens45-min cache
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Google: Gemini 3 Flash Preview | $0.0833333/M cache writeCheapest | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash | $0.24375/M cache write | input_cache_write: 0.00000024375 / token | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 32K | $0.40625/M cache write | input_cache_write: 0.00000040625 / token (>32000) | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 128K | $0.65/M cache write | input_cache_write: 0.00000065 / token (>128000) |
Per second of compute time1
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| fal | LLaVA v1.6 34B | $0.00125/compute sCheapest | $0.00125 / compute seconds |
Per run (default parameters)22
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | OpenAI: o3Web search | $0.01/runCheapest | web_search: 0.01 | |
| OpenRouter | OpenAI: o3 Mini (batch)Web search | $0.01/runCheapest | web_search: 0.01 | |
| OpenRouter | OpenAI: o3 ProWeb search | $0.01/runCheapest | web_search: 0.01 | |
| OpenRouter | OpenAI: o3 (batch)Web search | $0.01/runCheapest | web_search: 0.01 | |
| OpenRouter | Google: Gemini 3 Flash PreviewWeb search | $0.014/run | web_search: 0.014 | |
| OpenRouter | Google: Gemini 3 Flash Preview (batch)Web search | $0.014/run | web_search: 0.014 | |
| fal | Hyper3D - Rodin V2.5 - Text to 3D - Fast | $0.1/run | $0.1 / generations | |
| fal | Hyper3D - Rodin V2.5 - Text to 3D | $0.4/run | $0.4 / generations | |
| fal | Meshy 6 Preview | $0.8/run | $0.8 / generations | |
| fal | Meshy 6 | $0.8/run | $0.8 / generations | |
| fal | Meshy T2.5 Text to 3D | $0.8/run | $0.8 / generations | |
| fal | Meshy T2 Text to 3D | $0.8/run | $0.8 / generations | |
| fal | Meshy 7.1 Text to 3D | $0.8/run | $0.8 / generations | |
| fal | V7 Text to 3D | $0.8/run | $0.8 / generations | |
| WaveSpeed | wavespeed-ai/hunyuan3d-v3/text-to-3d | $0.3/runFrom | base_price: 0.3 USD | |
| WaveSpeed | hyper3d/rodin-v2.5/text-to-3d | $0.48/runFrom | base_price: 0.48 USD | |
| WaveSpeed | tripo3d/p1/text-to-3d | $0.48/runFrom | base_price: 0.48 USD | |
| WaveSpeed | meshy/v6-lite/text-to-3d | $0.72/runFrom | base_price: 0.72 USD | |
| WaveSpeed | tripo3d/p2/text-to-3d | $1.32/runFrom | base_price: 1.32 USD | |
| WaveSpeed | meshy/v6/text-to-3d | $1.44/runFrom | base_price: 1.44 USD | |
| WaveSpeed | meshy/v7.1/text-to-3d | $1.44/runFrom | base_price: 1.44 USD | |
| WaveSpeed | meshy/v7/text-to-3d | $1.44/runFrom | base_price: 1.44 USD |
Other units (see the platform’s wording)4
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| fal | Sam 3 | $0.005/unitCheapest | $0.005 / units | |
| fal | Tripo P1 Text to 3D | $0.01/unit | $0.01 / credits | |
| fal | Tripo P2 Text to 3D | $0.01/unit | $0.01 / credits | |
| fal | Hunyuan3d V3 | $0.015/unit | $0.015 / units |