8,429 prices on 4,154 listings · last collected 11 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 8,429Per second of output 1,919Per minute 34Per video 486Per image 1,521Per megapixel 308Per million input tokens 982Per million output tokens 977Per million tokens 48Per million cached input tokens (read) 458Per million cache-write tokens 191Per thousand characters 64Per second of compute time 93Per run (default parameters) 1,023Other units (see the platform’s wording) 325
Showing 4601–4700 of 8,429
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| 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 | |
| APIMart | nano-banana-2 | $0.4/M in | Input $0.4 / Output $2.4 · 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. | |
| fal | Moondream3 Preview [Segment]Image input | $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 | |
| APIMart | gpt-4o-mini-realtime-preview-2024-12-17 | $0.48/M in | Input $0.48 / Output $1.92 · Per 1M tokens | |
| OpenRouter | Xiaomi: MiMo-V2.5-Pro | $0.48/M in | prompt: 0.00000048 / token | |
| kie.ai | Gemini 3.1 Pro | $0.5/M in | 100 credits per million tokens ($0.50)Claims fal charges $2/M in | |
| kie.ai | Gemini 3 Pro | $0.5/M in | 100 credits per million tokens ($0.50)Claims fal charges $2/M in | |
| OpenRouter | Anthropic: Claude Haiku 4.5 (batch) | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5Prompt > 100K | $0.5/M in | prompt: 0.0000005 / token (>100000) | |
| OpenRouter | ByteDance Seed: Seed 1.6Prompt > 128K | $0.5/M in | prompt: 0.0000005 / token (>128000) | |
| OpenRouter | ByteDance Seed: Seed 2.1 Turbo | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | ByteDance Seed: Seed-2.0-Code | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | ByteDance Seed: Seed-2.0-LitePrompt > 128K | $0.5/M in | prompt: 0.0000005 / token (>128000) | |
| OpenRouter | DeepSeek: R1 0528 | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview (batch)Audio input | $0.5/M in | audio: 0.0000005 / token | |
| OpenRouter | Google: Nano Banana 2 (Gemini 3.1 Flash Image) | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Google: Gemini 3.1 Flash LiteAudio input | $0.5/M in | audio: 0.0000005 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite PreviewAudio input | $0.5/M in | audio: 0.0000005 / token | |
| OpenRouter | Mistral: Mistral Large 3 2512 | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra Pro (batch) | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra (batch) | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Qwen: Qwen3.5 397B A17B | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Z.ai: GLM 4.6 | $0.5/M in | prompt: 0.0000005 / token | |
| OpenRouter | Anthropic: Claude Haiku LatestPrompt > 100K | $0.5/M in | prompt: 0.0000005 / token (>100000) | |
| Replicate | google/gemini-3-flash | $0.5/M in | $0.50 per million input tokens | |
| Replicate | google/gemini-3.8-flash-lite-tts | $0.5/M in | $0.50 per million input tokens | |
| Replicate | google/gemini-3.8-flash-tts | $0.5/M in | $0.50 per million input tokens | |
| APIMart | deepseek-v4-pro | $0.5143/M in | Input $0.5143 / Output $1.5429 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 128K | $0.52/M in | prompt: 0.00000052 / token (>128000) | |
| OpenRouter | MoonshotAI: Kimi K2.5 | $0.532/M in | prompt: 0.000000532 / token | |
| OpenRouter | MiniMax: MiniMax M1 | $0.55/M in | prompt: 0.00000055 / token | |
| OpenRouter | OpenAI: o3 Mini (batch) | $0.55/M in | prompt: 0.00000055 / token | |
| OpenRouter | OpenAI: o4 Mini (batch) | $0.55/M in | prompt: 0.00000055 / token | |
| OpenRouter | TheDrummer: Skyfall 36B V2 | $0.55/M in | prompt: 0.00000055 / token | |
| kie.ai | gpt-5.6-terra | $0.56/M in | 112 credits per million tokens ($0.56)Claims fal charges $2/M in | |
| OpenRouter | MoonshotAI: Kimi K2 0711 | $0.57/M in | prompt: 0.00000057 / token | |
| OpenRouter | Meta: Llama 3.3 70B Instruct | $0.59/M in | prompt: 0.00000059 / token | |
| APIMart | gemini-3.7-flash | $0.6/M in | Input $0.6 / Output $3 · Per 1M tokens | |
| APIMart | gemini-3.8-flash | $0.6/M in | Input $0.6 / Output $3 · Per 1M tokens | |
| APIMart | gpt-5.4-mini | $0.6/M in | Input $0.6 / Output $3.6 · Per 1M tokens | |
| kie.ai | gpt-6-1-sol | $0.6/M in | 120 credits per million tokens ($0.6)Claims fal charges $2/M in | |
| kie.ai | gpt-6-sol | $0.6/M in | 120 credits per million tokens ($0.60)Claims fal charges $2/M in | |
| OpenRouter | Elorian: Glimpse | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | MoonshotAI: Kimi K2 0905 | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | MoonshotAI: Kimi K2 Thinking | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | MoonshotAI: Kimi K2.7 Code | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | NVIDIA: Nemotron 3 Ultra | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | OpenAI: GPT Audio MiniAudio input | $0.6/M in | audio: 0.0000006 / token | |
| OpenRouter | OpenAI: GPT Audio Mini | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | Writer: Palmyra X5 | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | Z.ai: GLM 4.5 | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | Z.ai: GLM 4.5V | $0.6/M in | prompt: 0.0000006 / token | |
| OpenRouter | Z.ai: GLM 4.7 | $0.6/M in | prompt: 0.0000006 / token |
