11,195 prices on 4,854 listings · last collected 7 h ago · 442 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on ten 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.
Platform
Unit price
All 11,195Per second of output 2,701Per minute 34Per video 674Per image 1,827Per megapixel 326Per million input tokens 1,298Per million output tokens 1,235Per million tokens 47Per million cached input tokens (read) 641Per million cache-write tokens 227Per thousand characters 75Per second of compute time 98Per run (default parameters) 1,784Other units (see the platform’s wording) 228
Showing 6601–6700 of 11,195
Per million input tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| ReplicateOfficial partner | openai/gpt-4o-mini-transcribe | $3/M in | $3 per million input tokens | |
| ReplicateOfficial partner | openai/gpt-image-2.6-flaresvg-gpt-5.4 | $3/M in | $0.000003 Input tokens (svg-gpt-5.4) | |
| ReplicateOfficial partner | openai/gpt-image-2.6-sunburstsvg-gpt-5.4 | $3/M in | $0.000003 Input tokens (svg-gpt-5.4) | |
| RunwareNot disclosed | Claude Sonnet 4.6 | $3/M in | $0.000003 / inputToken | |
| RunwareNot disclosed | MiniMax H3 Image HighspeedImage input | $3/M in | $0.000003 / inputToken · Image input | |
| RunwareNot disclosed | Kimi K3 | $3/M in | $0.000003 / inputToken | |
| APIMartNot disclosed | claude-opus-5-5 | $3.2/M in | Input $3.2 / Output $16 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5.6 | $3.2/M in | Input $3.2 / Output $16 · Per 1M tokens | |
| OpenRouterOfficial | SpaceXAI: Grok 4.6 (batch)Prompt > 200K | $3.2/M in | prompt: 0.0000032 / token (>200000; endpoint xai) | |
| OpenRouterOfficial | SpaceXAI: Grok 4.7 (batch)Prompt > 200K | $3.2/M in | prompt: 0.0000032 / token (>200000; endpoint xai) | |
| AibermNot disclosed | Claude Opus 4.5 | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23Claims official price $5/M in | |
| AibermNot disclosed | Claude Opus 4.5 Thinking | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23Claims official price $5/M in | |
| AibermNot disclosed | Claude Opus 4.6 | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23Claims official price $5/M in | |
| AibermNot disclosed | Claude Opus 4.6 Thinking | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23Claims official price $5/M in | |
| AibermNot disclosed | Claude Opus 4.7 | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23Claims official price $5/M in | |
| AibermNot disclosed | Claude Opus 4.8 | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23Claims official price $5/M in | |
| AibermNot disclosed | Claude Opus 5 | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23Claims official price $5/M in | |
| AibermNot disclosed | Claude Opus Test | $3.68/M in | model_ratio 8 × $2/M · group default ×0.23 | |
| ReplicatePlatform-hosted | deepseek-ai/deepseek-r1 | $3.75/M in | $3.75 per million input tokens | |
| APIMartNot disclosed | chatgpt-4o-latest | $4/M in | Input $4 / Output $12 · Per 1M tokens | |
| APIMartNot disclosed | claude-opus-4-5-20251101 | $4/M in | Input $4 / Output $20 · Per 1M tokens | |
| APIMartNot disclosed | claude-opus-4-5-20251101-thinking | $4/M in | Input $4 / Output $20 · Per 1M tokens | |
| APIMartNot disclosed | claude-opus-4-6 | $4/M in | Input $4 / Output $20 · Per 1M tokens | |
| APIMartNot disclosed | claude-opus-4-6-thinking | $4/M in | Input $4 / Output $20 · Per 1M tokens | |
| APIMartNot disclosed | claude-opus-4-7 | $4/M in | Input $4 / Output $20 · Per 1M tokens | |
| APIMartNot disclosed | claude-opus-4-8 | $4/M in | Input $4 / Output $20 · Per 1M tokens | |
| APIMartNot disclosed | claude-opus-5 | $4/M in | Input $4 / Output $20 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4o-2024-05-13 | $4/M in | Input $4 / Output $12 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4o-realtime-preview | $4/M in | Input $4 / Output $16 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4o-realtime-preview-2024-10-01 | $4/M in | Input $4 / Output $16 · Per 1M tokens | |
| APIMartNot disclosed | gpt-4o-realtime-preview-2024-12-17 | $4/M in | Input $4 / Output $16 · Per 1M tokens | |
| APIMartNot disclosed | gpt-5.5 | $4/M in | Input $4 / Output $24 · Per 1M tokens | |
| APIMartOfficial | gpt-image-1-officialText input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| APIMartOfficial | gpt-image-1.5-officialText input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| APIMartOfficial | gpt-image-2-officialText input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| APIMartNot disclosed | gpt-image-2.5-flareText input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| APIMartNot disclosed | gpt-image-2.5-sunburstText input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| APIMartNot disclosed | gpt-image-2.6-flareText input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| APIMartNot disclosed | gpt-image-2.6-sunburstText input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| APIMartNot disclosed | mai-image-2.6Text input | $4/M in | 40 Credits/M ~$4/MClaims official price $5/M inMember tiers: platinum $3.8 · diamond $3.6 | |
| KIENot disclosed | Claude-fable-5 | $4/M in | 800 credits per 1M tokens ($4)Claims official or Fal price $10/M in | |
| OpenRouterOfficial | Anthropic: Claude Fable 5.2 (batch) | $4/M in | prompt: 0.000004 / token (endpoint anthropic) | |
| OpenRouterOfficial partner | Anthropic: Claude Opus 5.5via Amazon Bedrock | $4/M in | prompt: 0.000004 / token (endpoint amazon-bedrock) | |
| OpenRouterOfficial | Google: Gemini 3.1 Pro PreviewPrompt > 200KAudio inputvia Google · global | $4/M in | audio: 0.000004 / token (>200000; endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.1 Pro PreviewPrompt > 200Kvia Google · global | $4/M in | prompt: 0.000004 / token (>200000; endpoint google-vertex/global) | |
| OpenRouterOfficial | Google: Gemini 3.1 Pro Preview Custom ToolsPrompt > 200KAudio input | $4/M in | audio: 0.000004 / token (>200000; endpoint google-ai-studio) | |
| OpenRouterOfficial | Google: Gemini 3.1 Pro Preview Custom ToolsPrompt > 200K | $4/M in | prompt: 0.000004 / token (>200000; endpoint google-ai-studio) | |
| OpenRouterThird-party | Meta: Muse Wondervia Google · global | $4/M in | prompt: 0.000004 / token (endpoint google-vertex/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Solvia Amazon Bedrock · global | $4/M in | prompt: 0.000004 / token (endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Sol Provia Azure | $4/M in | prompt: 0.000004 / token (endpoint azure) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Sol Pro (batch)Prompt > 272K | $4/M in | prompt: 0.000004 / token (>272000; endpoint openai) | |
| OpenRouterOfficial | OpenAI: GPT-5.6 Sol (batch)Prompt > 272K | $4/M in | prompt: 0.000004 / token (>272000; endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 TerraPrompt > 272Kvia Azure | $4/M in | prompt: 0.000004 / token (>272000; endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-5.6 Terra ProPrompt > 272Kvia Azure | $4/M in | prompt: 0.000004 / token (>272000; endpoint azure) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 SolPrompt > 272Kvia Amazon Bedrock · global | $4/M in | prompt: 0.000004 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6 Sol ProPrompt > 272Kvia OpenAI | $4/M in | prompt: 0.000004 / token (>272000; endpoint openai) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 SolPrompt > 272Kvia Amazon Bedrock · global | $4/M in | prompt: 0.000004 / token (>272000; endpoint amazon-bedrock/global) | |
| OpenRouterOfficial partner | OpenAI: GPT-6.1 Sol ProPrompt > 272Kvia Azure | $4/M in | prompt: 0.000004 / token (>272000; endpoint azure) | |
| OpenRouterOfficial | Qwen: Qwen3.8 Max Prime | $4/M in | prompt: 0.000004 / token (endpoint alibaba) | |
| OpenRouterOfficial | SpaceXAI: Grok 4.5Prompt > 200Kvia xAI · zdr | $4/M in | prompt: 0.000004 / token (>200000; endpoint xai/zdr) | |
| OpenRouterOfficial partner | SpaceXAI: Grok 4.6Prompt > 200Kvia xAI · zdr | $4/M in | prompt: 0.000004 / token (>200000; endpoint xai/zdr) | |
| OpenRouterOfficial partner | SpaceXAI: Grok 4.7Prompt > 200Kvia Amazon Bedrock · global | $4/M in | prompt: 0.000004 / token (>200000; endpoint amazon-bedrock/global) | |
| OpenRouterNot disclosed | Anthropic: Claude Opus Latest | $4/M in | prompt: 0.000004 / token | |
| OpenRouterNot disclosed | OpenAI: GPT Sol LatestPrompt > 272K | $4/M in | prompt: 0.000004 / token (>272000) | |
| OpenRouterNot disclosed | xAI: Grok LatestPrompt > 200K | $4/M in | prompt: 0.000004 / token (>200000) | |
| ReplicateOfficial partner | anthropic/claude-opus-5.5 | $4/M in | $4 per million input tokens | |
| ReplicateOfficial partner | google/gemini-3-pro> 200 · 000 | $4/M in | $4 per million input tokens (input token > 200,000) | |
| ReplicateOfficial partner | google/gemini-3.1-pro> 200 · 000 | $4/M in | $4 per million input tokens (input token > 200,000) | |
| RunwareNot disclosed | Claude Opus 5.5 | $4/M in | $0.000004 / inputToken | |
| RunwareNot disclosed | Gemini 3.1 Pro>200k | $4/M in | $0.000004 / inputToken · >200k | |
| RunwareNot disclosed | Gemini 4 ArgonFrom Dec 1 · 2026 | $4/M in | $0.000004 / inputToken · From Dec 1, 2026 | |
| RunwareNot disclosed | GPT-5.6 Sol | $4/M in | $0.000004 / inputToken | |
| RunwareNot disclosed | GPT-6.1 Sol> 272K context | $4/M in | $0.000004 / inputToken · > 272K context | |
| RunwareNot disclosed | GPT-6 Sol> 272K context | $4/M in | $0.000004 / inputToken · > 272K context | |
| RunwareNot disclosed | Grok 4.7≥ 200K context | $4/M in | $0.000004 / inputToken · ≥ 200K context | |
| OpenRouterOfficial | Xiaomi: MiMo-V2.6-Pro-UltraSpeed | $4.35/M in | prompt: 0.00000435 / token (endpoint xiaomi/fp8) | |
| KIENot disclosed | gpt-image-2-6-flareText to imageImage to image & editingText Input | $4.5/M in | 900 credits per million tokens ($4.5)Claims official or Fal price $5/M in | |
| KIENot disclosed | gpt-image-2-6-sunburstText to imageImage to image & editingText Input | $4.5/M in | 900 credits per million tokens ($4.5)Claims official or Fal price $5/M in | |
| FalOfficial partner | GPT-Image 1.5input text | $5/M in | Your request will cost different amounts based on the number of images, quality, and size. - You will be charged $0.005 per 1,000 input text tokens. Token counts vary with the text; you are charged for actual token usage. - You will be charged $0.010 per 1,000 output text tokens. The model will consume tokens reasoning about your prompt based on its complexity. - For low quality, you will be | |
| FalOfficial partner | GPT-Image 1.5Image to image & editinginput text | $5/M in | Your request will cost different amounts based on the number of images, quality, and size. - You will be charged $0.005 per 1,000 input text tokens. Token counts vary with the text; you are charged for actual token usage. - You will be charged $0.008 per 1,000 input image tokens. One 1024x1024 image is roughly 135 tokens in low fidelity mode, or 3,050 tokens in high fidelity mode. - You will | |
| FalOfficial partner | GPT Image 2 APIinput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.5 Flare EditImage to image & editinginput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.5 Flare Text to ImageText to imageinput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.5 Sunburst Edit Image to image & editinginput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.5 Sunburst Text to ImageText to imageinput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.6 Flare EditImage to image & editinginput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.6 Flare Text to ImageText to imageinput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.6 Sunburst EditImage to image & editinginput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2.6 Sunburst Text to ImageText to imageinput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| FalOfficial partner | GPT Image 2 APIImage to image & editinginput text | $5/M in | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| OpenRouterOfficial | Anthropic: Claude Fable 5.1 (batch) | $5/M in | prompt: 0.000005 / token (endpoint anthropic) | |
| OpenRouterOfficial | Anthropic: Claude Fable 5 (batch) | $5/M in | prompt: 0.000005 / token (endpoint anthropic) | |
| OpenRouterOfficial partner | Anthropic: Claude Opus 4.5via Claude Platform on AWS | $5/M in | prompt: 0.000005 / token (endpoint claude-on-aws) | |
| OpenRouterOfficial partner | Anthropic: Claude Opus 4.6via Claude Platform on AWS | $5/M in | prompt: 0.000005 / token (endpoint claude-on-aws) | |
| OpenRouterOfficial partner | Anthropic: Claude Opus 4.7via Claude Platform on AWS | $5/M in | prompt: 0.000005 / token (endpoint claude-on-aws) | |
| OpenRouterOfficial partner | Anthropic: Claude Opus 4.8via Claude Platform on AWS | $5/M in | prompt: 0.000005 / token (endpoint claude-on-aws) | |
| OpenRouterOfficial partner | Anthropic: Claude Opus 5via Claude Platform on AWS | $5/M in | prompt: 0.000005 / token (endpoint claude-on-aws) | |
| OpenRouterOfficial | Microsoft AI: MAI-Image-2.5input text | $5/M in | input_text: 0.000005 USD / token | |
| OpenRouterOfficial | Microsoft AI: MAI-Image-2.5 Proinput text | $5/M in | input_text: 0.000005 USD / token | |
| OpenRouterOfficial | Microsoft AI: MAI-Image-2.6input text | $5/M in | input_text: 0.000005 USD / token |
