Models/Anthropic/Text to Text API

Live13 models

Anthropic API — Every Claude Model (Fable, Opus, Sonnet, Haiku)

The Anthropic API on Muapi gives you programmatic access to every live Claude model line in one place — Claude Fable, Claude Opus, Claude Sonnet, and Claude Haiku — through one Muapi API key, one request shape, and both standard async and live-streaming endpoints.Every model accepts the same prompt / image_url / system_prompt request body, so switching between Claude families and generations is a one-line model-name change. Flagship tiers are billed at Anthropic's own published rate with no Muapi markup.

Get Anthropic API Key Try Claude in Playground

Claude Fable 5.1

Anthropic's most capable widely released model — 1M-token context, long-horizon agentic work1 models

Text GenerationNewFeatured

Claude Fable 5.1

Anthropic's most capable widely released model — 1M-token context window for the most demanding reasoning and long-horizon agentic work.

Text + Image in

$10.00/M in · $50.00/M out

Try Model

Claude Fable 5

Prior-generation Fable tier, 1M-token context1 models

Text GenerationClassic

Claude Fable 5

Prior-generation Fable tier with 1M-token context, still fully supported for existing integrations.

Text + Image in

$8.00/M in · $40.00/M out

Try Model

Claude Opus 5.5

Anthropic's newest Opus tier — official Anthropic pricing, no Muapi markup1 models

Text GenerationNew

Claude Opus 5.5

Anthropic's newest Opus model — top-tier coding, long-context reasoning, and agentic workflows at a lower price than Opus 5, billed at official Anthropic rates.

Text + Image in

$4.00/M in · $20.00/M out

Try Model

Claude Opus 5

Current-generation flagship reasoning and coding model1 models

Text GenerationLive

Claude Opus 5

Anthropic's current-generation flagship model for complex coding, long-context reasoning, and agentic workflows.

Text + Image in

$3.00/M in · $15.00/M out

Try Model

Claude Opus 4.8

Prior-generation flagship, still fully supported1 models

Text GenerationLive

Claude Opus 4.8

Prior-generation Opus flagship — complex coding, long-context reasoning, and agentic workflows.

Text + Image in

$3.00/M in · $15.00/M out

Try Model

Claude Opus 4.7

Prior-generation flagship, still fully supported1 models

Text GenerationClassic

Claude Opus 4.7

Prior-generation Opus flagship, still fully supported for existing integrations.

Text + Image in

$3.00/M in · $15.00/M out

Try Model

Claude Opus 4.6

Prior-generation flagship, still fully supported1 models

Text GenerationClassic

Claude Opus 4.6

Prior-generation Opus flagship, still fully supported for existing integrations.

Text + Image in

$3.00/M in · $15.00/M out

Try Model

Claude Opus 4.5

Earliest live Opus tier on Muapi, for existing integrations1 models

Text GenerationClassic

Claude Opus 4.5

The earliest live Opus tier on Muapi, kept available for existing integrations.

Text + Image in

$3.00/M in · $15.00/M out

Try Model

Claude Sonnet 5.5

Anthropic's newest balanced model — 30%+ faster than Sonnet 5 at official pricing, for everyday coding, agents, and knowledge work1 models

Text GenerationNew

Claude Sonnet 5.5

Faster, more cost-efficient upgrade to Sonnet 5 for everyday coding, well-scoped agents, knowledge work, and visual understanding — at official Anthropic pricing.

Text + Image in

$2.00/M in · $10.00/M out

Try Model

Claude Sonnet 5

Anthropic's balanced flagship — cost and performance for coding and reasoning1 models

Text GenerationLive

Claude Sonnet 5

Anthropic's flagship balanced model — the optimal combination of cost and state-of-the-art performance for coding, complex reasoning, and multimodal analysis.

Text + Image in

$3.00/M in · $15.00/M out

Try Model

Claude Sonnet 4.6

Prior-generation balanced model with native computer-use support1 models

Text GenerationClassic

Claude Sonnet 4.6

Strong reasoning, advanced coding, and native computer-use functionality, with up to 1M-token context.

Text + Image in

$1.80/M in · $9.00/M out

Try Model

Claude Sonnet 4.5

Prior-generation balanced model, still fully supported1 models

Text GenerationClassic

Claude Sonnet 4.5

High intelligence, speed, and efficiency for code generation, writing, and logical analysis.

Text + Image in

$1.80/M in · $9.00/M out

Try Model

Claude Haiku 4.5

Anthropic's fastest, most cost-effective model — high-frequency queries and simple tasks1 models

Text GenerationLive

Claude Haiku 4.5

Anthropic's fastest and most cost-effective model, designed for high-frequency queries, simple tasks, and near-instant response times.

Text + Image inFast

$0.60/M in · $3.00/M out

Try Model

What is the Anthropic API?

Anthropic builds the Claude family of models across four lines: Claude Fable (the most capable, for the hardest reasoning and long-horizon agentic work), Claude Opus (flagship coding and reasoning), Claude Sonnet (the balanced cost/performance tier), and Claude Haiku (fastest and cheapest, for high-volume simple tasks). Submit a prompt — optionally alongside a reference image and a system prompt to steer tone and behavior — and get back a text response.

Muapi exposes every live Claude model across all four lines through the same request shape, so upgrading, downgrading, or comparing generations and price tiers is a one-line model-name change. Each model is available as a standard asynchronous submit-and-poll endpoint or a Server-Sent Events streaming endpoint for live chat UIs.

Key Capabilities

Every Claude Line, One API

Call Fable, Opus, Sonnet, or Haiku through the same request shape and the same Muapi API key — no separate Anthropic account or SDK per line.

Official Anthropic Pricing on Flagship Tiers

Claude Fable 5.1 and Claude Opus 5.5 are billed at Anthropic's own published rates with no Muapi markup.

A Model for Every Budget

From Claude Haiku 4.5 at $0.60/M input tokens for high-volume simple tasks up to Claude Fable 5.1 for the hardest reasoning and agentic work.

Multimodal Input

Pass an optional image_url alongside your prompt so Claude can reason about charts, diagrams, screenshots, and stack traces, not just text.

System Prompt Control

Set a system_prompt to steer tone, persona, or output format across a request.

Async or Streaming

Use the standard submit-and-poll endpoint for batch jobs and workflows, or the SSE streaming endpoint to render tokens live in a chat interface.

Pricing

Endpoint	Input	Output	Price	Best For
claude-fable-5-1	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$10.00/M in · $50.00/M out	Anthropic's most capable model, hardest reasoning and agentic work
claude-fable-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$8.00/M in · $40.00/M out	Prior-generation Fable tier, existing integrations
claude-opus-5-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$4.00/M in · $20.00/M out	The newest Opus tier, at official Anthropic pricing
claude-opus-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$3.00/M in · $15.00/M out	Current-generation flagship reasoning and coding
claude-opus-4-8	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$3.00/M in · $15.00/M out	Prior-generation flagship, existing integrations
claude-opus-4-7	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$3.00/M in · $15.00/M out	Prior-generation flagship, existing integrations
claude-opus-4-6	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$3.00/M in · $15.00/M out	Prior-generation flagship, existing integrations
claude-opus-4-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$3.00/M in · $15.00/M out	Earliest live Opus tier, existing integrations
claude-sonnet-5-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$2.00/M in · $10.00/M out	Fast everyday coding, agents, and knowledge work
claude-sonnet-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$3.00/M in · $15.00/M out	Balanced cost and state-of-the-art performance
claude-sonnet-4-6	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$1.80/M in · $9.00/M out	Balanced tier with native computer-use support
claude-sonnet-4-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$1.80/M in · $9.00/M out	Prior-generation balanced tier, existing integrations
claude-haiku-4-5	Prompt + optional image_url, system_prompt	Complete text response (poll for result)	$0.60/M in · $3.00/M out	High-frequency queries and simple tasks

Minimum $0.0006 per call across every Claude model. Actual cost is deducted after each call based on token counts returned by the model. Every model also exposes a /stream endpoint at the same price.

How to Call the Anthropic API

Submit a JSON request with your Muapi API key, save the request ID, and poll the shared result endpoint — or call the /stream variant for a live SSE token feed. The request shape is identical across every Claude model.

1. Submit a prompt to Claude Fable 5.1

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":"Research and compare three architectures for this system, citing tradeoffs.","system_prompt":"You are a precise principal engineer."}'

# Response: {"request_id":"REQUEST_ID"}

Call claude-fable-5-1 with a prompt, and optionally a system_prompt and image_url.

2. Poll the result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

# Poll until status is completed, then read the generated text from outputs.

Poll until the task is completed, then read the generated text from outputs.

3. Stream the response instead

curl -X POST https://api.muapi.ai/api/v1/claude-fable-5-1/stream \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Walk through a long-horizon plan for this migration, step by step."}'

# Response: a stream of SSE chunks, one per line:
# data: {"choices":[{"delta":{"content":"Here"}}]}
# data: {"choices":[{"delta":{"content":" is"}}]}
# data: [DONE]

Call claude-fable-5-1/stream with the same fields to receive SSE chunks as the model generates them, ending in a [DONE] marker.

4. Or call Claude Opus 5.5

curl -X POST https://api.muapi.ai/api/v1/claude-opus-5-5 \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Review this pull request diff for correctness and suggest a safer approach.","image_url":"https://example.com/diff-screenshot.png"}'

# Response: {"request_id":"REQUEST_ID"}

Same request shape on Anthropic's flagship coding tier.

5. Poll the result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

# Poll until status is completed, then read the generated text from outputs.

Same shared result endpoint, regardless of which model submitted the task.

6. Stream Claude Opus 5.5

curl -X POST https://api.muapi.ai/api/v1/claude-opus-5-5/stream \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Plan a multi-file refactor for this module and list the follow-up questions."}'

# Response: a stream of SSE chunks, one per line:
# data: {"choices":[{"delta":{"content":"Here"}}]}
# data: {"choices":[{"delta":{"content":" is"}}]}
# data: [DONE]

Call claude-opus-5-5/stream for live SSE token output.

7. Or call Claude Sonnet 5.5

curl -X POST https://api.muapi.ai/api/v1/claude-sonnet-5-5 \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Review this pull request diff and flag risky changes.","image_url":"https://example.com/diff-screenshot.png"}'

# Response: {"request_id":"REQUEST_ID"}

Same request shape on Anthropic's newest balanced tier.

8. Poll the result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

# Poll until status is completed, then read the generated text from outputs.

Same shared result endpoint.

9. Stream Claude Sonnet 5.5

curl -X POST https://api.muapi.ai/api/v1/claude-sonnet-5-5/stream \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Explain this stack trace and suggest a fix."}'

# Response: a stream of SSE chunks, one per line:
# data: {"choices":[{"delta":{"content":"Here"}}]}
# data: {"choices":[{"delta":{"content":" is"}}]}
# data: [DONE]

Call claude-sonnet-5-5/stream for live SSE token output.

10. Or call Claude Sonnet 5

curl -X POST https://api.muapi.ai/api/v1/claude-sonnet-5 \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Write a unit test suite for this function.","image_url":"https://example.com/function-screenshot.png"}'

# Response: {"request_id":"REQUEST_ID"}

Same request shape on Anthropic's balanced flagship tier.

11. Poll the result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

# Poll until status is completed, then read the generated text from outputs.

Same shared result endpoint.

12. Stream Claude Sonnet 5

curl -X POST https://api.muapi.ai/api/v1/claude-sonnet-5/stream \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Explain this error message and how to fix it."}'

# Response: a stream of SSE chunks, one per line:
# data: {"choices":[{"delta":{"content":"Here"}}]}
# data: {"choices":[{"delta":{"content":" is"}}]}
# data: [DONE]

Call claude-sonnet-5/stream for live SSE token output.

13. Or call Claude Haiku 4.5

curl -X POST https://api.muapi.ai/api/v1/claude-haiku-4-5 \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Classify this support ticket by urgency and category."}'

# Response: {"request_id":"REQUEST_ID"}

Same request shape on Anthropic's fastest, cheapest tier.

14. Poll the result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

# Poll until status is completed, then read the generated text from outputs.

Same shared result endpoint.

15. Stream Claude Haiku 4.5

curl -X POST https://api.muapi.ai/api/v1/claude-haiku-4-5/stream \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Give a one-sentence summary of this paragraph."}'

# Response: a stream of SSE chunks, one per line:
# data: {"choices":[{"delta":{"content":"Here"}}]}
# data: {"choices":[{"delta":{"content":" is"}}]}
# data: [DONE]

Call claude-haiku-4-5/stream for live SSE token output.

Frequently Asked Questions

What models does the Anthropic API include?

Muapi exposes every live Claude model across all four Anthropic lines: Claude Fable (5.1, 5), Claude Opus (5.5, 5, 4.8, 4.7, 4.6, 4.5), Claude Sonnet (5, 4.6, 4.5), and Claude Haiku (4.5) — 12 models in total, all as standard REST APIs.

Which Claude model should I use?

Use Claude Fable 5.1 for the hardest reasoning and long-horizon agentic work, Claude Opus for flagship coding and reasoning, Claude Sonnet for the best balance of cost and performance, and Claude Haiku 4.5 for high-volume, low-latency, simple tasks.

How much does the Anthropic API cost?

Pricing ranges from $0.60/M input and $3.00/M output tokens on Claude Haiku 4.5 up to $10.00/M input and $50.00/M output tokens on Claude Fable 5.1. Flagship tiers (Fable 5.1, Opus 5.5) are billed at Anthropic's own official rate with no Muapi markup. Every model has a $0.0006 minimum per call.

Can Claude understand images?

Yes, on every model. Pass an image_url alongside your prompt and Claude will reason about both the text and the image together — including charts, diagrams, screenshots, and stack traces.

What's the difference between the async and streaming endpoints?

POST /api/v1/{model} is asynchronous: it returns a request_id you poll via /api/v1/predictions/{id}/result. Adding /stream to any model's path returns Server-Sent Events chunks in real time, ending in a data: [DONE] line, for live chat interfaces.

Do I need an Anthropic account to use this API?

No. Muapi exposes every Claude model as standard REST endpoints. Create a Muapi API key, submit JSON, and either poll the returned request ID or read the SSE stream.

Is there a dedicated page for just Claude Opus or Claude Fable?

Yes — see the Claude Opus API and Claude Fable API pages linked below for a deeper dive into each line's tiers, including per-tier pricing and use-case guidance.

Deep Dive: Claude Opus API →All six live Opus tiers (5.5, 5, 4.8, 4.7, 4.6, 4.5), pricing, and endpoint details.Deep Dive: Claude Fable API →Anthropic's most capable model line — Claude Fable 5.1 and Claude Fable 5, with 1M-token context.Browse every LLM on Muapi →Compare Claude against Gemini, GPT, Grok, DeepSeek, and every other language model in the Muapi catalog.

Ready to build with Claude?

Create one Muapi API key and connect every live Claude model — Fable, Opus, Sonnet, and Haiku — to your product through a plain REST call or a live SSE stream.

Get an API Key Try Claude in Playground