Generate text con Claude Fable 5.1. Anthropic's flagship model con adaptive thinking, 1M context. Pruébalo gratis — pay per generación, sin suscripción.
Generate text con Claude Fable 5.1. Anthropic's flagship model con adaptive thinking, 1M context. Pruébalo gratis — pay per generación, sin suscripción.
Acerca de este modelo
Claude Fable 5.1 is Anthropic's newest flagship model, built fo long-horizon agentic coding, multistep research, y document, spreadsheet, y slide work. It runs con adaptive extended thinking always enabled (steerable via effort, de low up to max) y a 1 million token context window con up to 128K tokens of resultado. It accepts both text y imagen entradas — charts, tables, PDFs, y screenshots — fo multimodal analysis, y is a step up in reasoning depth de the earlier Claude Fable 5. El precio se calcula po tokens: $10.00 por millón entrada tokens y $50.00 por millón resultado tokens.
Análisis de costes
| Proveedor | Coste | Notas |
|---|---|---|
| muapiapp | $10.00/M input tokens, $50.00/M output tokens | Facturación po tokens at Anthropic's official published rate. Mínimo $0.0008 po llamada. |
| Fal.ai | No disponible | Claude Fable 5.1 no está disponible en Fal.ai. |
| Replicate | No disponible | Claude Fable 5.1 no está disponible en Replicate. |
Facturación po tokens at Anthropic's official published rate. Mínimo $0.0008 po llamada.
Claude Fable 5.1 no está disponible en Fal.ai.
Claude Fable 5.1 no está disponible en Replicate.
** Los precios de competidores son estimaciones basadas en arquitecturas de modelos y niveles de uso similares.
Esquema de configuración
| Parámetro | Tipo | Descripción | Por defecto |
|---|---|---|---|
| Prompt | string | . | Explain quantum entanglement in simple terms. |
| URL de imagen | string | imagen URL. | undefined |
| Prompt del sistema | string | , . | You are a concise and precise assistant. |
.
Explain quantum entanglement in simple terms.imagen URL.
undefined, .
You are a concise and precise assistant.Documentación para desarrolladores
POST /api/v1/claude-fable-5-1 — returns request_id, poll fo the result via /api/v1/predictions/{id}/result.
curl -X POST https://api.muapi.ai/api/v1/claude-fable-5-1 \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Summarize the key risks in this quarterly report and list follow-up questions.",
"image_url": "https://example.com/report-page-1.png",
"system_prompt": "You are a meticulous financial analyst."
}'
POST /api/v1/claude-fable-5-1/stream — returns a live Server-Sent Events stream (Content-Type: text/event-stream). Cada chunk has the format data: {"choices":[{"delta":{"content":"text"}}]}, ending con data: [DONE].
See Streaming Documentation fo full code examples.
Preguntas frecuentes
Claude Fable 5.1 is Anthropic's newest flagship language model, built fo long-horizon agentic coding, multistep research, y document, spreadsheet, y slide analysis, con a 1M-token context window y always-on adaptive extended thinking.
El precio se calcula po tokens: $10.00 por millón entrada tokens y $50.00 por millón resultado tokens. The minimum charge per call is $0.0008. Actual costo is deducted después de each call based on token counts returned by the model.
/claude-fable-5-1 is async — you receive a request_id y poll fo the result. /claude-fable-5-1/stream returns a live SSE stream. Usa streaming fo chat UIs; use the async endpoint fo workflows y automation.
Sí. Pass an imagen_url in the request body to include an imagen — such as a chart, table, PDF page, o screenshot — as part of the user message fo multimodal analysis.
Claude Fable 5.1 adds a larger 1M-token context window, always-on adaptive extended thinking (steerable via effort), y stronger long-horizon agentic y research performance compared to [Claude Fable 5](/playground/claude-fable-5).
Extended thinking is always enabled y cannot be turned off, but its depth is adaptive to the task — harder, multistep requests automáticamente get more esfuerzo de razonamiento.