Claude Sonnet 5.5

Claude Sonnet 5.5 combines Sonnet-class speed with strong coding, agent, and long-context capabilities. Call it through AnyFast’s Anthropic Messages API at POST /v1/messages using the model ID claude-sonnet-5-5.

Key capabilities

1M context window — Supports up to 1M context tokens and 128K output tokens according to Anthropic’s model specification
Adaptive thinking — On by default; use output_config.effort to control depth
Coding and agents — Suited to multi-step implementation, tool use, and analysis
Text and vision — Accepts text and image inputs and returns text
Model ID — Use claude-sonnet-5-5 in requests

Quick example

curl https://www.anyfast.ai/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5",
    "max_tokens": 4096,
    "output_config": {"effort": "medium"},
    "messages": [
      {"role": "user", "content": "Review this rollout plan and identify its three highest-risk assumptions."}
    ]
  }'

import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai",
)

message = client.messages.create(
    model="claude-sonnet-5-5",
    max_tokens=4096,
    output_config={"effort": "medium"},
    messages=[{"role": "user", "content": "Review this rollout plan."}],
)

for block in message.content:
    if block.type == "text":
        print(block.text)

import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai",
)

with client.messages.stream(
    model="claude-sonnet-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize the rollout risks."}],
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Must be `claude-sonnet-5-5`.
`messages`	array	Yes	User and assistant turns with text, image, or tool-result content.
`max_tokens`	integer	Yes	Maximum output tokens across thinking and visible text; up to 128,000.
`output_config`	object	No	Set `effort` to `low`, `medium`, `high`, `xhigh`, or `max`; default `high`.
`thinking`	object	No	Adaptive by default. `between_tools` is available with effort up to `high`.
`tools`	array	No	Tool definitions for model-selected calls.
`tool_choice`	object	No	Use `auto` or `none`.
`stream`	boolean	No	Enable SSE streaming; default `false`.

At low, medium, or high effort, thinking: {"type":"between_tools"} skips thinking before the first tool call while allowing it between calls. Sonnet 5.5 does not support thinking.type values disabled or manual enabled, or forced tool_choice modes any and named tool; AnyFast returned 400 for any in a live test. Omit custom temperature, top_p, and top_k values. Replay thinking blocks unchanged when continuing a tool conversation.

In a tested AnyFast text response, the request ID claude-sonnet-5-5 appeared as model: "claude-sonnet-5.5". The response also included request_id, billing.billed_cost_usd as a string, and usage.service_tier. Keep using the hyphen-form ID in requests; read response content blocks by type.

API Reference

Review the Claude Sonnet 5.5 request and response fields.

​Key capabilities

​Quick example

​Parameters

API Reference

Key capabilities

Quick example

Parameters