Claude Fable 5.1

claude-fable-5.1

Use the Claude Fable 5.1 API for chat and reasoning. Send conversation messages and add tools on routes that support tool calling. Build an assistant that can answer questions and coordinate application actions. Compare the available provider routes, request examples, and usage prices on OpenAny.

Published price: From $9.655 / 1M tokens
Billing unit: / 1M tokens
Context / Max output: 1000K / 128K
Listed routes: 1

messages

Other parameters (17)

betaAnthropic beta header values to enable beta features.cache_controlTop-level cache control. Automatically applies a cache_control marker to the last cacheable block in the request.containerContainer identifier or container parameters for reuse across requests, especially for code execution and skills.context_managementControls how Claude manages context across requests, such as whether to clear tool results.diagnosticsRequest-level diagnostics.fallbackServer-side fallback models to try when the requested model declines for policy reasons.fallback_credit_tokenFallback credit token from a prior refusal stop_details. Must be redeemed under the documented constraints.inference_geoGeographic region for inference processing. If omitted, the workspace default inference geo is used.mcp_serversMCP servers to use in this request.metadataRequest metadata.output_configOutput configuration, including output format and effort settings.speedInference speed mode. fast enables higher output tokens per second.systemSystem prompt. Can be a string or an array of text blocks used to provide context, role, goals, or constraints.thinkingtool_choicetoolsuser_profile_idUser profile ID for attributing requests when acting on behalf of another party. Requires the user-profiles beta header.

Result preview

Anthropic · 2777ms

Response example. Run to see the actual response.

{
  "id": "msg_gwhb_mu29o1sv-1b487562fef5",
  "model": "claude-fable-5-1",
  "usage": {
    "input_tokens": 0,
    "total_tokens": 2,
    "output_tokens": 0,
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "input_tokens_details": null,
    "prompt_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "reasoning_tokens": 0
    },
    "claude_cache_creation_1_h_tokens": 0,
    "claude_cache_creation_5_m_tokens": 0
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OK",
        "reasoning_content": ""
      },
      "finish_reason": "stop"
    }
  ],
  "created": 1789452252,
  "openmodels_cost": 63
}

Base URL: https://api.openany.si/v1
POST: /v1/chat/completions
Authentication: Authorization: Bearer $OPENANY_API_KEY

Request parameters

Parameter	Type / range	Default value	Required	Description
`beta`	`array`	`—`	No	Anthropic beta header values to enable beta features.
`cache_control`	`object`	`—`	No	Top-level cache control. Automatically applies a cache_control marker to the last cacheable block in the request.
`container`	`object`	`—`	No	Container identifier or container parameters for reuse across requests, especially for code execution and skills.
`context_management`	`object`	`—`	No	Controls how Claude manages context across requests, such as whether to clear tool results.
`diagnostics`	`object`	`—`	No	Request-level diagnostics.
`fallback`	`array`	`—`	No	Server-side fallback models to try when the requested model declines for policy reasons.
`fallback_credit_token`	`string`	`—`	No	Fallback credit token from a prior refusal stop_details. Must be redeemed under the documented constraints.
`inference_geo`	`string`	`—`	No	Geographic region for inference processing. If omitted, the workspace default inference geo is used.
`mcp_servers`	`array`	`—`	No	MCP servers to use in this request.
`messages`	`array`	`—`	No	messages
`metadata`	`object`	`—`	No	Request metadata.
`output_config`	`object`	`—`	No	Output configuration, including output format and effort settings.
`speed`	`string · standard \| fast`	`—`	No	Inference speed mode. fast enables higher output tokens per second.
`system`	`array`	`—`	No	System prompt. Can be a string or an array of text blocks used to provide context, role, goals, or constraints.
`thinking`	`object`	`—`	No	thinking
`tool_choice`	`object`	`—`	No	tool_choice
`tools`	`array`	`—`	No	tools
`user_profile_id`	`string`	`—`	No	User profile ID for attributing requests when acting on behalf of another party. Requires the user-profiles beta header.

No required parameters returned.

Request example

curl 'https://api.openany.si/v1/chat/completions' \
  -H "Authorization: Bearer $OPENANY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "messages": [
    {
      "content": "Hello!",
      "role": "user"
    }
  ],
  "model": "claude-fable-5.1",
  "route_mode": "balanced"
}'

Response example

Configured response example · not a live result

{
  "id": "msg_gwhb_mu29o1sv-1b487562fef5",
  "model": "claude-fable-5-1",
  "usage": {
    "input_tokens": 0,
    "total_tokens": 2,
    "output_tokens": 0,
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "input_tokens_details": null,
    "prompt_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "reasoning_tokens": 0
    },
    "claude_cache_creation_1_h_tokens": 0,
    "claude_cache_creation_5_m_tokens": 0
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OK",
        "reasoning_content": ""
      },
      "finish_reason": "stop"
    }
  ],
  "created": 1789452252,
  "openmodels_cost": 63
}

Error handling

400Check the model ID and request fields.

429Retry with exponential backoff.

5xxRetry only temporary provider failures.

JSON Schema

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "beta": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Anthropic beta header values to enable beta features."
    },
    "speed": {
      "enum": [
        "standard",
        "fast"
      ],
      "type": "string",
      "description": "Inference speed mode. fast enables higher output tokens per second."
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "description": "Tool name."
          },
          "description": {
            "type": "string",
            "description": "Tool description. Strongly recommended to help the model decide when and how to call the tool."
          },
          "input_schema": {
            "type": "object",
            "description": "JSON Schema describing the tool input shape that the model should produce."
          }
        }
      }
    },
    "system": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string",
            "description": "System instruction text."
          },
          "type": {
            "enum": [
              "text"
            ],
            "type": "string",
            "description": "System content block type."
          }
        }
      },
      "description": "System prompt. Can be a string or an array of text blocks used to provide context, role, goals, or constraints."
    },
    "fallback": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string",
            "description": "Fallback model name."
          },
          "max_tokens": {
            "type": "integer",
            "description": "Maximum tokens for the fallback attempt."
          },
          "output_config": {
            "type": "object",
            "description": "Output configuration for the fallback attempt."
          }
        }
      },
      "description": "Server-side fallback models to try when the requested model declines for policy reasons."
    },
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "role",
          "content"
        ],
        "properties": {
          "role": {
            "enum": [
              "user",
              "assistant"
            ],
            "type": "string",
            "description": "Message role. The Messages API does not support a system role inside messages; use the top-level system parameter instead."
          },
          "content": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "items": {
                  "type": "object",
                  "required": [
                    "type"
                  ],
                  "properties": {
                    "type": {
                      "type": "string"
                    }
                  }
                }
              }
            ],
            "description": "Message content. Can be a string or an array of typed content blocks such as text, image, tool_result, or document blocks."
          }
        }
      }
    },
    "metadata": {
      "type": "object",
      "properties": {
        "user_id": {
          "type": "string",
          "description": "External user identifier associated with the request."
        }
      },
      "description": "Request metadata."
    },
    "thinking": {
      "type": "object",
      "properties": {
        "type": {
          "enum": [
            "enabled",
            "disabled",
            "adaptive"
          ],
          "type": "string",
          "description": "Thinking mode type."
        },
        "display": {
          "type": "object",
          "description": "Display configuration for thinking output when supported."
        },
        "budget_tokens": {
          "type": "integer",
          "minimum": 1024,
          "description": "Token budget for extended thinking when thinking is enabled."
        }
      }
    },
    "container": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string",
          "description": "Container ID to reuse."
        },
        "skills": {
          "type": "array",
          "items": {
            "type": "object"
          },
          "description": "Skills to load in the container."
        }
      },
      "description": "Container identifier or container parameters for reuse across requests, especially for code execution and skills."
    },
    "diagnostics": {
      "type": "object",
      "properties": {
        "previous_message_id": {
          "type": "string",
          "description": "Previous response ID for prompt-cache divergence reporting."
        }
      },
      "description": "Request-level diagnostics."
    },
    "mcp_servers": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "url": {
            "type": "string",
            "description": "MCP server URL."
          },
          "name": {
            "type": "string",
            "description": "MCP server name."
          },
          "type": {
            "type": "string",
            "description": "MCP server definition type."
          }
        }
      },
      "description": "MCP servers to use in this request."
    },
    "tool_choice": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string",
          "description": "Specific tool name when tool_choice.type is tool."
        },
        "type": {
          "enum": [
            "auto",
            "any",
            "tool",
            "none"
          ],
          "type": "string",
          "description": "Tool choice mode."
        },
        "disable_parallel_tool_use": {
          "type": "boolean",
          "description": "Whether to disable parallel tool use for applicable tool choice modes."
        }
      }
    },
    "cache_control": {
      "type": "object",
      "properties": {
        "ttl": {
          "type": "string",
          "description": "Cache time-to-live when supported."
        },
        "type": {
          "type": "string",
          "description": "Cache control type."
        }
      },
      "description": "Top-level cache control. Automatically applies a cache_control marker to the last cacheable block in the request."
    },
    "inference_geo": {
      "type": "string",
      "description": "Geographic region for inference processing. If omitted, the workspace default inference geo is used."
    },
    "output_config": {
      "type": "object",
      "properties": {
        "effort": {
          "type": "string",
          "description": "Output effort configuration when supported."
        },
        "format": {
          "type": "object",
          "description": "Structured output format configuration."
        },
        "task_budget": {
          "type": "integer",
          "description": "Task budget configuration when supported."
        }
      },
      "description": "Output configuration, including output format and effort settings."
    },
    "user_profile_id": {
      "type": "string",
      "description": "User profile ID for attributing requests when acting on behalf of another party. Requires the user-profiles beta header."
    },
    "context_management": {
      "type": "object",
      "properties": {
        "edits": {
          "type": "array",
          "items": {
            "type": "object"
          },
          "description": "Context management edits to apply."
        }
      },
      "description": "Controls how Claude manages context across requests, such as whether to clear tool results."
    },
    "fallback_credit_token": {
      "type": "string",
      "description": "Fallback credit token from a prior refusal stop_details. Must be redeemed under the documented constraints."
    }
  }
}

Request example

POST /v1/chat/completions

curl 'https://api.openany.si/v1/chat/completions' \
  -H "Authorization: Bearer $OPENANY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "messages": [
    {
      "content": "Hello!",
      "role": "user"
    }
  ],
  "model": "claude-fable-5.1",
  "route_mode": "balanced"
}'

Model API questions

How do I call Claude Fable 5.1 through OpenAny?

Use model ID claude-fable-5.1 with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.

How is Claude Fable 5.1 billed?

Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.

Are Community and Verified routes the same as an official publisher API?

No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.

Where do these prices come from, and when were they updated?

Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.

Use Claude Fable 5.1 with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.

Claude Fable 5.1

Provider

Request parameters

Result preview

Provider

Provider

Request example

Model API questions

Use Claude Fable 5.1 with your agent