8,429 prices on 4,154 listings · last collected 8 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 7,913Per second of output 1,911Per minute 34Per video 485Per 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) 516Other units (see the platform’s wording) 325
Showing 601–700 of 982
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| APIMart | gpt-5.2-codex | $1.4/M in | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMart | gpt-5.3-codex | $1.4/M in | Input $1.4 / Output $11.2 · Per 1M tokens | |
| APIMart | mai-image-2.6-flash | $1.4/M in | Input $1.4 · Per 1M tokens | |
| kie.ai | gpt-5.5 | $1.4/M in | 280 credits per million tokens ($1.4)Claims fal charges $5/M in | |
| kie.ai | gpt-5.6-sol | $1.4/M in | 280 credits per million tokens ($1.4)Claims fal charges $5/M in | |
| OpenRouter | Z.ai: GLM 5.1 | $1.4/M in | prompt: 0.0000014 / token | |
| kie.ai | claude-opus-4-5 | $1.425/M in | 285 credits per million tokens ($1.425)Claims fal charges $5/M in | |
| kie.ai | Claude-Opus-4-6 | $1.425/M in | 285 credits per million tokens ($1.425)Claims fal charges $5/M in | |
| kie.ai | Claude-Opus-4-7 | $1.425/M in | 285 credits per million tokens ($1.425)Claims fal charges $5/M in | |
| Replicate | deepseek-ai/deepseek-v3 | $1.45/M in | $1.45 per million input tokens | |
| OpenRouter | Qwen: Qwen3.7 Max | $1.475/M in | prompt: 0.000001475 / token | |
| APIMart | kimi-k2.7-code-highspeed | $1.4858/M in | Input $1.4858 / Output $6.1659 · Per 1M tokens | |
| OpenRouter | Anthropic: Claude Sonnet 4.5 (batch) | $1.5/M in | prompt: 0.0000015 / token | |
| OpenRouter | Anthropic: Claude Sonnet 4.6 (batch) | $1.5/M in | prompt: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3.5 Flash | $1.5/M in | prompt: 0.0000015 / token | |
| OpenRouter | Google: Gemini 3.5 Flash (batch)Audio input | $1.5/M in | audio: 0.0000015 / token | |
| OpenRouter | Google: Nano Banana 2.1 | $1.5/M in | prompt: 0.0000015 / token | |
| OpenRouter | Google: Gemini Omni 1.1 Flash | $1.5/M in | prompt: 0.0000015 / token | |
| OpenRouter | Google: Gemini Omni 1.2 Flash | $1.5/M in | prompt: 0.0000015 / token | |
| OpenRouter | Mistral: Mistral Medium 3.5 | $1.5/M in | prompt: 0.0000015 / token | |
| Replicate | google/gemini-3.5-flash | $1.5/M in | $1.50 per million input tokens | |
| APIMart | claude-sonnet-5 | $1.6/M in | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | claude-sonnet-5-5 | $1.6/M in | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | davinci-002 | $1.6/M in | Input $1.6 / Output $1.6 · Per 1M tokens | |
| APIMart | gemini-3-pro-preview | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gemini-3-pro-preview-thinking | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gemini-3.1-pro-preview | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gemini-3.1-pro-preview-thinking | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gemini-4-argon | $1.6/M in | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4.1 | $1.6/M in | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | gpt-4.1-2025-04-14 | $1.6/M in | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | gpt-5.6-terra | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | gpt-6-sol | $1.6/M in | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | gpt-6.1-sol | $1.6/M in | Input $1.6 / Output $8 · Per 1M tokens | |
| APIMart | grok-4.5 | $1.6/M in | Input $1.6 / Output $4.8 · Per 1M tokens | |
| APIMart | grok-4.6 | $1.6/M in | Input $1.6 / Output $4.8 · Per 1M tokens | |
| APIMart | grok-4.7 | $1.6/M in | Input $1.6 / Output $4.8 · Per 1M tokens | |
| APIMart | nano-banana-pro | $1.6/M in | Input $1.6 / Output $9.6 · Per 1M tokens | |
| APIMart | o3 | $1.6/M in | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | o3-2025-04-16 | $1.6/M in | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | o4-mini-deep-research | $1.6/M in | Input $1.6 / Output $6.4 · Per 1M tokens | |
| APIMart | o4-mini-deep-research-2025-06-26 | $1.6/M in | Input $1.6 / Output $6.4 · Per 1M tokens | |
| kie.ai | claude-opus-5-5 | $1.6/M in | 320 credits per million tokens ($1.60)Claims fal charges $4/M in | |
| OpenRouter | SpaceXAI: Grok 4.6 (batch) | $1.6/M in | prompt: 0.0000016 / token | |
| OpenRouter | SpaceXAI: Grok 4.7 (batch) | $1.6/M in | prompt: 0.0000016 / token | |
| OpenRouter | Microsoft AI: MAI-Image-2.6 Flashinput text | $1.75/M in | input_text: 0.00000175 USD / token | |
| OpenRouter | OpenAI: GPT-5.2 | $1.75/M in | prompt: 0.00000175 / token | |
| OpenRouter | OpenAI: GPT-5.2 Chat | $1.75/M in | prompt: 0.00000175 / token | |
| OpenRouter | OpenAI: GPT-5.2-Codex | $1.75/M in | prompt: 0.00000175 / token | |
| OpenRouter | OpenAI: GPT-5.3-Codex | $1.75/M in | prompt: 0.00000175 / token | |
| Replicate | openai/gpt-5.2 | $1.75/M in | $1.75 per million input tokens | |
| fal | Nano Banana 2.1Image input | $1.764/M in | Text/thinking tokens (per 1M): $1.764 input, $8.823 output. Image tokens (per 1M): $1.764 input, $35.294 output. Changing the resolution parameter significantly affects cost. See the description at the bottom of this page for more details on how much canonical image sizes cost. | |
| fal | Nano Banana 2.1input text | $1.764/M in | Text/thinking tokens (per 1M): $1.764 input, $8.823 output. Image tokens (per 1M): $1.764 input, $35.294 output. Changing the resolution parameter significantly affects cost. See the description at the bottom of this page for more details on how much canonical image sizes cost. | |
| fal | Nano Banana 2.1 EditImage editingImage input | $1.764/M in | Text/thinking tokens (per 1M): $1.764 input, $8.823 output. Image tokens (per 1M): $1.764 input, $35.294 output. Changing the resolution parameter significantly affects cost; by default we use 1K. See the description at the bottom of this page for more details on how much canonical image sizes cost. | |
| fal | Nano Banana 2.1 EditImage editinginput text | $1.764/M in | Text/thinking tokens (per 1M): $1.764 input, $8.823 output. Image tokens (per 1M): $1.764 input, $35.294 output. Changing the resolution parameter significantly affects cost; by default we use 1K. See the description at the bottom of this page for more details on how much canonical image sizes cost. | |
| fal | Gemini Omni FlashVideo input | $1.875/M in | Billing is based on total token consumption. Input tokens (text/audio/video) cost $1.875 per 1 million tokens. Output tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.13 per second of video. | |
| fal | Gemini Omni FlashImage to videoVideo input | $1.875/M in | Billing is based on total token consumption. Input tokens (text/audio/video) cost $1.875 per 1 million tokens. Output tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.13 per second of video. | |
| fal | Gemini Omni FlashImage to videoVideo input | $1.875/M in | Billing is based on total token consumption. Input tokens (text/audio/video) cost $1.875 per 1 million tokens. Output tokens cost $21.875 per 1 million tokens. For 720p video this costs approximately $0.13 per second of video. | |
| APIMart | GPT-4o | $2/M in | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4-32k | $2/M in | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4-32k-0613 | $2/M in | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4-vision-preview | $2/M in | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4o-2024-11-20 | $2/M in | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-4o-transcribe | $2/M in | Input $2 / Output $8 · Per 1M tokens | |
| APIMart | gpt-5.4 | $2/M in | Input $2 / Output $12 · Per 1M tokens | |
| kie.ai | Claude-Opus-4-8 | $2/M in | 400 credits per million tokens ($2)Claims fal charges $5/M in | |
| kie.ai | claude-opus-5 | $2/M in | 400 credits per million tokens ($2)Claims fal charges $5/M in | |
| OpenRouter | Anthropic: Claude Opus 5.5 (batch) | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5 | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Anthropic: Claude Sonnet 5.5 | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image)Audio input | $2/M in | audio: 0.000002 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image)Image inputvia Google AI Studio | $2/M in | input_image: 0.000002 USD / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image)Image inputvia Google Vertex | $2/M in | input_image: 0.000002 USD / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image) | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)Audio input | $2/M in | audio: 0.000002 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)Image inputvia Google AI Studio | $2/M in | input_image: 0.000002 USD / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image Preview) | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro PreviewAudio input | $2/M in | audio: 0.000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom ToolsAudio input | $2/M in | audio: 0.000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom Tools | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview (batch)Prompt > 200KAudio input | $2/M in | audio: 0.000002 / token (>200000) | |
| OpenRouter | Google: Gemini 3.1 Pro Preview (batch)Prompt > 200K | $2/M in | prompt: 0.000002 / token (>200000) | |
| OpenRouter | Google: Gemini 4 ArgonAudio input | $2/M in | audio: 0.000002 / token | |
| OpenRouter | Google: Gemini 4 Argon | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Mistral Large | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Mistral Large 2407 | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | Mistral: Mixtral 8x22B Instruct | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | MoonshotAI: Kimi K3.1 Pro | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-4.1 | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol Pro (batch) | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Sol (batch) | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra Pro | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-5.6 Terra Pro (batch)Prompt > 272K | $2/M in | prompt: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Terra (batch)Prompt > 272K | $2/M in | prompt: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-6 Sol Pro | $2/M in | prompt: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-6 Sol Pro (batch)Prompt > 272K | $2/M in | prompt: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Sol (batch)Prompt > 272K | $2/M in | prompt: 0.000002 / token (>272000) |
