Anthropic models: APIs and prices

Text generation14

• Claude Fable 5claude-fable-5

  Anthropic Fable 5, a Claude 5 variant for long-form writing and storytelling. 200K context. Supports the OpenAI Chat and Anthropic Messages protocols.

  Input 2.4264Credits/K4.044Credits·Output 12.132Credits/K20.22Credits
• Claude Fable 5.1claude-fable-5-1

  Anthropic Fable 5.1, Anthropic's most capable general model, built for the hardest reasoning and long-horizon agent tasks. 1M context. Supports the OpenAI Chat and Anthropic Messages protocols.

  Input 2.4264Credits/K4.044Credits·Output 12.132Credits/K20.22Credits
• Claude Haiku 4.5claude-haiku-4-5-20251001

  Anthropic Haiku 4.5. 200K context, the fastest and most economical Claude, for high-concurrency and low-latency workloads. Supports all three protocols.

  Input 0.2426Credits/K0.4044Credits·Output 1.2132Credits/K2.022Credits
• Claude Haiku 5.5claude-haiku-5-5

  Anthropic Haiku 5.5, the new lightweight Claude. 1M context, fast and economical; good for high concurrency, classification, extraction and sub-tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

  Input 0.0243Credits/K0.0404Credits·Output 0.1213Credits/K0.2022Credits
• Claude Opus 4.5claude-opus-4-5-20251101

  Anthropic Opus 4.5. 200K context, for reasoning, coding and agent tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

  Input 1.2132Credits/K2.022Credits·Output 6.066Credits/K10.11Credits
• Claude Opus 4.6claude-opus-4-6

  Anthropic Opus 4.6. 1M context, an all-rounder for reasoning, coding and multimodal work, suited to the hardest tasks. Supports the OpenAI Chat, Anthropic Messages and OpenAI Responses protocols.

  Input 1.2132Credits/K2.022Credits·Output 6.066Credits/K10.11Credits
• Claude Opus 4.7claude-opus-4-7

  Anthropic Opus 4.7. 1M context, an all-rounder for reasoning, coding and multimodal work. Supports the OpenAI Chat, Anthropic Messages and OpenAI Responses protocols.

  Input 1.2132Credits/K2.022Credits·Output 6.066Credits/K10.11Credits
• Claude Opus 4.8claude-opus-4-8

  Anthropic Opus 4.8. 1M context, the strongest Opus to date, an all-rounder for reasoning, coding and multimodal work, suited to the hardest tasks. Supports all three protocols.

  Input 1.2132Credits/K2.022Credits·Output 6.066Credits/K10.11Credits
• Claude Opus 5claude-opus-5

  Anthropic Opus 5, the new strongest Opus. 1M context, an all-rounder for reasoning, coding and multimodal work, suited to the hardest tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

  Input 1.2132Credits/K2.022Credits·Output 6.066Credits/K10.11Credits
• Claude Opus 5.5claude-opus-5-5

  Anthropic Opus 5.5, the successor to Opus 5. 1M context, stronger at long-horizon agentic coding and knowledge work. Supports the OpenAI Chat and Anthropic Messages protocols.

  Input 0.9706Credits/K1.6176Credits·Output 4.8528Credits/K8.088Credits
• Claude Sonnet 4.5claude-sonnet-4-5-20250929

  Anthropic Claude Sonnet 4.5: 200K context, reasoning, vision and tool calling.

  Input 0.7279Credits/K1.2132Credits·Output 3.6396Credits/K6.066Credits
• Claude Sonnet 4.6claude-sonnet-4-6

  Anthropic Sonnet 4.6. 1M context, the best value, balanced between reasoning and coding. Cached input costs 1/10 of the input price. Supports all three protocols.

  Input 0.7279Credits/K1.2132Credits·Output 3.6396Credits/K6.066Credits
• Claude Sonnet 5claude-sonnet-5

  Anthropic Sonnet 5, the new best-value flagship. 1M context, balanced between reasoning and coding. Supports the OpenAI Chat, Anthropic Messages and OpenAI Responses protocols.

  Input 0.4853Credits/K0.8088Credits·Output 2.4264Credits/K4.044Credits
• Claude Sonnet 5.5claude-sonnet-5-5

  Anthropic Sonnet 5.5, the successor to Sonnet 5. 1M context, balancing speed, cost and capability; strong at documents, code and agent tasks. Supports the OpenAI Chat and Anthropic Messages protocols.

  Input 0.1113Credits/K·Output 0.5566Credits/K

FAQ

How do I call Anthropic 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 Anthropic 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.