Claude Sonnet 4.6 delivers strong reasoning, advanced coding, and native computer-use functionality. Supports text and image inputs with up to 1M token context. Token-based pricing: $1.80/M input tokens, $9.00/M output tokens. Two endpoints: standard async (/claude-sonnet-4-6) and live streaming (/claude-sonnet-4-6/stream) via SSE.
About this model
Claude Sonnet 4.6 is Anthropic's high-performance model combining strong reasoning, advanced coding, and native computer-use functionality. With an adaptive thinking mode and up to 1 million token context, it excels at building reliable AI agents, complex automation, and large-scale content workflows. Pricing is token-based: $1.80 per million input tokens and $9.00 per million output tokens — significantly below official Anthropic pricing.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $1.80/M input tokens, $9.00/M output tokens | Token-based billing. Minimum $0.00035 per call. ~60% of official Anthropic pricing. |
| Anthropic (official) | ~$3.00/M input tokens, ~$15.00/M output tokens | Official pricing via api.anthropic.com. |
| Fal.ai | Not available | Claude Sonnet 4.6 is not available on Fal.ai. |
Token-based billing. Minimum $0.00035 per call. ~60% of official Anthropic pricing.
Official pricing via api.anthropic.com.
Claude Sonnet 4.6 is not available on Fal.ai.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | The user message or instruction. | Explain the concept of recursion with a simple example. |
| Image URL | string | Optional image URL for multimodal requests. | undefined |
| System Prompt | string | Optional system-level instruction to guide model behavior. | You are a concise coding assistant. |
The user message or instruction.
Explain the concept of recursion with a simple example.Optional image URL for multimodal requests.
undefinedOptional system-level instruction to guide model behavior.
You are a concise coding assistant.Developer documentation
POST /api/v1/claude-sonnet-4-6 — returns request_id, poll for result via /api/v1/predictions/{id}/result.
POST /api/v1/claude-sonnet-4-6/stream — returns a live Server-Sent Events stream (Content-Type: text/event-stream). Each chunk has the format data: {"choices":[{"delta":{"content":"text"}}]}, ending with data: [DONE].
See Streaming Documentation for full code examples.
Frequently asked
Pricing is token-based: $1.80 per million input tokens and $9.00 per million output tokens. The minimum charge per call is $0.00035. Actual cost is deducted after each call based on token counts returned by the model.
/claude-sonnet-4-6 is async — you receive a request_id and poll for the result. /claude-sonnet-4-6/stream returns a live SSE stream. Use streaming for chat UIs; use the async endpoint for workflows and automation.
Yes. Pass an image_url in the request body to include an image as part of the user message.