OpenAI models: APIs and prices

Text generation17

• GPT-5.6 Lunagpt-5.6-luna

  OpenAI GPT-5.6 frontier model (Luna tier). 1M context, adjustable reasoning effort, with web search and image generation ready to use.

  Input 0.0243Credits/K0.0809Credits·Output 0.1456Credits/K0.4853Credits
• GPT-5.6 Solgpt-5.6-sol

  OpenAI GPT-5.6 frontier model (Sol tier). 1M context, adjustable reasoning effort, with web search and image generation ready to use.

  Input 0.6066Credits/K2.022Credits·Output 3.6396Credits/K12.132Credits
• GPT-5.6 Terragpt-5.6-terra

  OpenAI GPT-5.6 frontier model (Terra tier). 1M context, adjustable reasoning effort, with web search and image generation ready to use.

  Input 0.6066Credits/K2.022Credits·Output 3.6396Credits/K12.132Credits
• GPT-5.6 Luna-bdgpt-5.6-luna-bd

  OpenAI GPT-5.6 Luna tier (bd line). 1.05M context, billed at OpenAI's list price. Adjustable reasoning effort; web search, image input, file input and tool calling; very long prompts are priced in a separate tier. OpenAI Chat and Responses protocols.

  Input 0.0809Credits/K·Output 0.4853Credits/K
• GPT-5.6 Sol-bdgpt-5.6-sol-bd

  OpenAI GPT-5.6 Sol tier (bd line). 1.05M context, billed at OpenAI's list price. Adjustable reasoning effort; web search, image input, file input and tool calling; very long prompts are priced in a separate tier. OpenAI Chat and Responses protocols.

  Input 1.6176Credits/K·Output 8.088Credits/K
• GPT-5.6 Terra-bdgpt-5.6-terra-bd

  OpenAI GPT-5.6 Terra tier (bd line). 1.05M context, billed at OpenAI's list price. Adjustable reasoning effort; web search, image input, file input and tool calling; very long prompts are priced in a separate tier. OpenAI Chat and Responses protocols.

  Input 0.8088Credits/K·Output 4.8528Credits/K
• GPT-6gpt-6

  OpenAI GPT-6 flagship. 1.05M context, adjustable reasoning effort, with web search and image generation ready to use; very long prompts are priced in a separate tier.

  Input 1.2132Credits/K4.044Credits·Output 6.066Credits/K20.22Credits
• GPT-6 Astragpt-6-astra

  OpenAI GPT-6 flagship (Astra tier). 1.05M context, adjustable reasoning effort, with web search and image generation ready to use; very long prompts are priced in a separate tier.

  Input 1.2132Credits/K4.044Credits·Output 6.066Credits/K20.22Credits
• GPT-6 Astra-bdgpt-6-astra-bd

  OpenAI GPT-6 flagship Astra tier (bd line). 1.05M context, billed at OpenAI's list price. Adjustable reasoning effort; web search, image input, file input and tool calling; very long prompts are priced in a separate tier. OpenAI Chat and Responses protocols.

  Input 4.044Credits/K·Output 20.22Credits/K
• GPT-6 Lunagpt-6-luna

  OpenAI GPT-6 Luna tier, the most economical of the series, for focused high-concurrency tasks. 1.05M context, adjustable reasoning effort, with web search and image generation ready to use; very long prompts are priced in a separate tier.

  Input 0.0121Credits/K0.0404Credits·Output 0.0607Credits/K0.2022Credits
• GPT-6 Luna-bdgpt-6-luna-bd

  OpenAI GPT-6 Luna tier, the most economical of the series (bd line). 1.05M context, billed at OpenAI's list price. Adjustable reasoning effort; web search, image input, file input and tool calling; very long prompts are priced in a separate tier. OpenAI Chat and Responses protocols.

  Input 0.0404Credits/K·Output 0.2022Credits/K
• GPT-6 Solgpt-6-sol

  OpenAI GPT-6 Sol tier, for complex coding and agent workflows. 1.05M context, adjustable reasoning effort, with web search and image generation ready to use; very long prompts are priced in a separate tier.

  Input 0.2426Credits/K0.8088Credits·Output 1.2132Credits/K4.044Credits
• GPT-6 Sol-bdgpt-6-sol-bd

  OpenAI GPT-6 Sol tier, for complex coding and agent workflows (bd line). 1.05M context, billed at OpenAI's list price. Adjustable reasoning effort; web search, image input, file input and tool calling; very long prompts are priced in a separate tier. OpenAI Chat and Responses protocols.

  Input 0.8088Credits/K·Output 4.044Credits/K
• GPT-6.1 Solgpt-6.1-sol

  OpenAI GPT-6.1 Sol: close to GPT-6 Astra on complex coding, computer use and professional work at a lower price. 1.05M context, adjustable reasoning effort, with web search and image generation ready to use; very long prompts are priced in a separate tier.

  Input 0.2426Credits/K0.8088Credits·Output 1.2132Credits/K4.044Credits
• GPT-6.1 Sol-bdgpt-6.1-sol-bd

  OpenAI GPT-6.1 Sol (bd line). 1.05M context, billed at OpenAI's list price. Adjustable reasoning effort; web search, image input, file input and tool calling; very long prompts are priced in a separate tier. OpenAI Chat and Responses protocols.

  Input 0.8088Credits/K·Output 4.044Credits/K
• GPT-6.1 Terragpt-6.1-terra

  OpenAI GPT-6.1 Terra, a fast and efficient new-generation model, strong at visual reasoning, precise computer use and clear, natural writing. 1.05M context, adjustable reasoning effort, with web search and image generation ready to use; very long prompts are priced in a separate tier.

  Input 0.1213Credits/K0.4044Credits·Output 0.6066Credits/K2.022Credits
• Codex Auto Reviewcodex-auto-review

  The review model behind Codex's "Approve for me": the kernel asks it whether each risky action is safe and only interrupts you when it judges an action dangerous. Officially marked as an internal model; 272K context, with tools, image input, web search and image generation ready to use.

  Input 0.0243Credits/K0.0809Credits·Output 0.1456Credits/K0.4853Credits

Image generation8

• GPT-Image 2gpt-image-2

  OpenAI GPT-Image 2 standalone image generation. Text-to-image and reference-image editing at any aspect ratio and custom sizes.

  per image 18Credits
• GPT-Image 2-bdgpt-image-2-bd

  OpenAI GPT-Image 2 (bd line). Text-to-image, reference-image editing and inpainting, with custom sizes and quality, billed at OpenAI's official token prices.

  Image output 9.7056Credits/K·Input image 2.5882Credits/K
• GPT-Image 2.5 Flaregpt-image-2.5-flare

  OpenAI GPT-Image 2.5, speed tier. Text-to-image, reference-image editing and sketch-to-finished-image, one image per request.

  per image 18Credits
• GPT-Image 2.5 Flare-bdgpt-image-2.5-flare-bd

  OpenAI GPT-Image 2.5 speed tier (bd line). Text-to-image, reference-image editing and inpainting, with custom sizes and quality, billed at OpenAI's official token prices.

  Image output 9.7056Credits/K·Input image 2.5882Credits/K
• GPT-Image 2.5 Sunburstgpt-image-2.5-sunburst

  OpenAI GPT-Image 2.5, refinement tier. Stronger editing precision and subject consistency with reference images; suited to sketch-to-finished-image and edits.

  per image 18Credits
• GPT-Image 2.5 Sunburst-bdgpt-image-2.5-sunburst-bd

  OpenAI GPT-Image 2.5 refinement tier (bd line). Text-to-image, reference-image editing and inpainting, with custom sizes and quality, billed at OpenAI's official token prices.

  Image output 9.7056Credits/K·Input image 2.5882Credits/K
• GPT-Image 2.6 Flaregpt-image-2.6-flare

  OpenAI GPT-Image 2.6, speed tier. Text-to-image and reference-image editing, and it can make animated GIFs; billed at OpenAI's official token prices.

  Image output 12.132Credits/K·Input image 3.2352Credits/K
• GPT-Image 2.6 Sunburstgpt-image-2.6-sunburst

  OpenAI GPT-Image 2.6, refinement tier. Better detail and subject consistency with reference images, and it can also make animated GIFs; billed at OpenAI's official token prices.

  Image output 12.132Credits/K·Input image 3.2352Credits/K

FAQ

How do I call OpenAI models?

Create an API key on XiaoZhan AIhub, point your SDK's base_url at https://api.dflop.top/v1 and put the model ID from the list above in the model field. The OpenAI, Anthropic and Gemini SDKs all work.

How are OpenAI models billed?

Each model is billed its own way: text models per input and output token, image models per image, video models per second or per token. Prices are in credits (60 credits = ¥1); each model page lists the full price.