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 301–400 of 866
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| 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 | |
| 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: 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 |
