Claude Sonnet 5.5

Text

1M context; Sonnet 5 successor for everyday coding and agent work

Input $1.60 / 1M tokens | Output $8.00 / 1M tokens Claude Sonnet 5.5 API reference →

Model health Insufficient data

runapi.ai

# Base URL
https://runapi.ai

# Endpoints
POST /v1/messages

curl https://runapi.ai/v1/messages \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-5-5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements."
    }
  ]
}'

import anthropic

client = anthropic.Anthropic(
    base_url="https://runapi.ai",
    api_key="your-runapi-key"
)

message = client.messages.create(
    model="claude-sonnet-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements."}]
)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://runapi.ai",
  apiKey: "your-runapi-key"
});

const message = await client.messages.create({
  model: "claude-sonnet-5-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Review this pull request for security vulnerabilities, performance issues, and suggest concrete improvements." }]
});

https://runapi.ai 1 endpoint

15 versions available

OVERVIEW

What changes when you move to Claude Sonnet 5.5

Anthropic released Claude Sonnet 5.5 on September 28, 2026. It keeps the per-token input and output rates of Sonnet 5, and since October 7, 2026 its cache reads cost half of what Sonnet 5 charges. Anthropic aims it at well-scoped everyday work that has a clear definition of done, such as fixing bugs or producing documents, and recommends Opus 5.5 for open-ended problems.

Code written for Sonnet 5 needs a few request changes. Turning thinking off with thinking: {type: "disabled"} now returns a 400; send {type: "between_tools"} at high effort or below instead. Forced tool use, with tool_choice set to any or to a named tool, also returns a 400, so switch to auto and strict tool definitions. Sonnet 5.5 also rejects non-default temperature, top_p, or top_k values.

On RunAPI, claude-sonnet-5-5 is served through the Anthropic Messages endpoint (/v1/messages) only. RunAPI rejects requests for this model in the OpenAI Chat Completions, Responses, or Gemini formats, so call it from an Anthropic SDK or from Claude Code.

Model ID

claude-sonnet-5-5

Released

September 28, 2026

Context window

1M tokens

Max output

128K tokens

Knowledge cutoff

June 2026

Default effort (API)

high

Protocol on RunAPI

Anthropic Messages

Playground

Try Claude Sonnet 5.5

Pick any model and generate in seconds.

Specifications

Provider	Anthropic
Model ID	claude-sonnet-5-5
Modality	Text
Task types	Synchronous

API endpoint	/v1/messages
Billing unit	1K tokens
Catalog status	Operational

HOW IT WORKS

Use This Model in 3 Steps

Get Your Key

Sign up for free and create an API key for claude-sonnet-5-5 from the dashboard.
Send a Request

POST to /v1/messages with the claude-sonnet-5-5 model slug and your parameters.
Get Results

Read the completed claude-sonnet-5-5 response directly from the endpoint.

What this model offers

Endpoint coverage

Exposes 1 public endpoint(s): message.

Usage-based billing

Metered by 1K tokens with no subscription requirement.

Claude Sonnet 5.5 Pricing

Endpoint

Price

message

Input: $1.60 / 1M tokens Output: $8.00 / 1M tokens

Cache read: $0.08 / 1M tokens
Cache write 5m: $2.00 / 1M tokens
Cache write 1h: $3.20 / 1M tokens

API REFERENCE

Endpoint Specification

Endpoint: POST /v1/messages
Model ID: claude-sonnet-5-5
Task Types: message

Request parameters

No request parameters are published for this endpoint.

USE CASES

Customer support

Answer customer questions from a private knowledge base, reducing ticket volume.

Document analysis

Draft contract summaries and flag key clauses for attorney review.

Code generation

Auto-generate unit tests, code reviews, and refactoring suggestions in CI.

Trusted by developers

API Calls / Day

100.0%

Success Rate

2.1s

Avg Generation

Verified customer feedback is not available for this model yet.

FAQ

Frequently asked questions about Claude Sonnet 5.5

How much does the Claude Sonnet 5.5 API cost?

Sonnet 5.5 is billed per token for input, output, cache writes, and cache reads; the pricing table on this page shows RunAPI's current rate for each. Anthropic kept the Sonnet 5 input and output rates and, on October 7, 2026, cut the cache-read rate to half of Sonnet 5's. There is no long-context surcharge, so a 900K-token prompt pays the same per-token rate as a short one.

Is Claude Sonnet 5.5 cheaper than Sonnet 5?

Per token, input and output cost the same and cache reads cost half as much. Anthropic says a typical task costs up to 30% less because Sonnet 5.5 reaches an answer with fewer tokens. Token use depends on the effort level you set, so compare the usage field of your own requests before moving a large workload.

Should I use Sonnet 5.5 or Opus 5.5?

Anthropic recommends Sonnet 5.5 when the task has a clear spec and a way to check the result, and Opus 5.5 for complex, open-ended work. Both run on RunAPI under the same API key, so you can route each job by changing the model ID.

Which effort level should I use with Sonnet 5.5?

The API default is high. Anthropic suggests starting at medium for agentic coding and multi-step tool use with a clear spec, moving to high for hard tasks, and using medium or low for chat. Higher levels spend more thinking tokens, and thinking tokens are billed at the output rate.

Why does my Sonnet 5 code return a 400 error on Sonnet 5.5?

Sonnet 5.5 rejects three request shapes that Sonnet 5 accepted: thinking set to disabled (use between_tools at high effort or below), tool_choice set to any or to a named tool (use auto with strict tools), and non-default temperature, top_p, or top_k. Thinking blocks are also tied to the conversation that produced them, so replaying an edited history can fail.

Why did a request come back with stop_reason refusal?

Sonnet 5.5 runs Anthropic's safety classifiers. A declined request returns HTTP 200 with stop_reason set to refusal and a stop_details object that names the category. Check stop_reason before reading the content. RunAPI returns this response to you unchanged.

Can I call Claude Sonnet 5.5 with the OpenAI SDK on RunAPI?

No. RunAPI serves claude-sonnet-5-5 through the Anthropic Messages API only. Use the Anthropic SDK with ANTHROPIC_BASE_URL set to https://runapi.ai and your RunAPI key, or a Messages client such as Claude Code.

How do I select claude-sonnet-5-5?

Pass the model ID shown in the quickstart.

What's the rate limit on this variant?

Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.

Can I switch variants later?

Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.

Does it stream?

Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.

Where do I report quality issues?

Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.

Do I need a separate provider account?

No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.