Intelligence
Index v5.0
Claude Sonnet 5.5 overview
Claude Sonnet 5.5 by Anthropic
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.
Claude Sonnet 5.5 specs
- Model ID
anthropic/claude-sonnet-5.5- Developer
- Anthropic
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input
- Image, Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What Is Claude Sonnet 5.5 API?
Claude Sonnet 5.5 is Anthropic's Sonnet-class model, released on 28 September 2026 as a direct successor to Claude Sonnet 5. It is built for well-scoped everyday work rather than the hardest frontier problems, and it carries a 1,000,000-token context window with always-on adaptive thinking.
Anthropic positions it close to Opus 5.5 on agentic coding and knowledge work while remaining the cheaper, faster tier. On the vendor's own figures it beats Opus 5.5 on Terminal-Bench 4.0 and sits within two points of it on GDPval-AA.
Technical Reference
| Developer | Anthropic |
|---|---|
| Model ID | anthropic/claude-sonnet-5.5 |
| Release Date | September 28, 2026 |
| Context Window | 1,000,000 tokens (~1M) |
| Max Output Tokens | 128,000 tokens |
| Modalities | Image, Text → Text |
| Capabilities | reasoning, streaming, tool/function calling, vision |
What Claude Sonnet 5.5 Brings to the Table
A large jump in agentic coding
Anthropic reports 70.6% on Terminal-Bench 4.0, against 10.3% for Claude Sonnet 5 on the same evaluation, and 55.5% on CursorBench 4.0 against 34.1%.
Computer use
80.1% on OSWorld 2.1 (partial credit), against 57.0% for Sonnet 5.
Reading charts and screenshots
61.6% on Chartography without tools, against 15.6% for Sonnet 5. Anthropic notes it is the first Sonnet model to finish Pokémon Red working only from screenshots.
Long-context work
The 1M-token window is available at standard pricing on AI/ML API, with prompt caching billed separately.
Benchmarks Anthropic Published at Release
- Terminal-Bench 4.0: 70.6%, above Opus 5.5 at 66.4%
- FrontierCode 1.1 (Main): 46.2% at Max effort
- Humanity's Last Exam: 64.5% with tools
- GDPval-AA v2.1: 1844, and AA-Briefcase v1.1: 1811, both measured by Artificial Analysis rather than by Anthropic
Where Claude Sonnet 5.5 Makes the Most Sense
Agentic coding and long-running tasks
The Terminal-Bench and CursorBench gains over Sonnet 5 are the largest Anthropic reports for this release, and they are the tasks the model is aimed at.
Computer-use agents
80.1% on OSWorld 2.1 puts it within two points of Opus 5.5 at a lower price per token.
Work over very large inputs
A 1M-token window suits whole-repository review, long transcripts and large document sets.
Claude Sonnet 5.5 vs the Alternatives
Claude Sonnet 5
The model this one replaces. Sonnet 5.5 is ahead on every benchmark Anthropic published for both, by wide margins on the agentic ones.
Claude Opus 5.5
The frontier tier. Opus leads on CursorBench 4.0 (57.8% vs 55.5%) and FrontierCode, ties on GDPval-AA (1846 vs 1844), and trails on Terminal-Bench 4.0 (66.4% vs 70.6%). Sonnet 5.5 is the cheaper choice where that gap does not matter.
Source: https://www.anthropic.com/claude-sonnet-5-5
Capabilities
- Reasoning
- Streaming
- Function calling
- Vision
Claude Sonnet 5.5 benchmarks by 
Artificial Analysis
See how Claude Sonnet 5.5 compares in intelligence, generation speed and cost per task. Data retrieved Nov 3, 2026.
Benchmark results
Compare 5 models available on AI/ML API across 4 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
Terminal-Bench 4.0
Agentic tasks completed in a command-line environment.
AA-LCR
Reasoning across long documents of about 100k tokens.
SciCode
Python coding tasks drawn from scientific research.
Claude Sonnet 5.5 API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $2 | 1M tokens |
| Output | $10 | 1M tokens |
| Cached input | $0.2 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Claude Sonnet 5.5 vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Claude Sonnet 5.5 | $2 | $10 |
| Claude Haiku 5.5 | $0.1 | $0.5 |
| Claude Opus 5.5 | $4 | $20 |
| Claude Opus 5 | $5 | $25 |
| Claude Fable 5.1 | $10 | $50 |
How to use the Claude Sonnet 5.5 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "anthropic/claude-sonnet-5.5",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "anthropic/claude-sonnet-5.5",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "anthropic/claude-sonnet-5.5",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Claude Sonnet 5.5
Claude Sonnet 5.5 FAQ
How much does Claude Sonnet 5.5 cost?
Claude Sonnet 5.5 costs $2 input and $10 output per 1M tokens on AI/ML API, billed as you go with no subscription.
What is Claude Sonnet 5.5 on AI/ML API best for?
It is built for coding, agents, and professional work at scale. It is also described as suitable for reasoning, streaming, tools, and vision.
Does Claude Sonnet 5.5 support reasoning?
Yes. Adaptive thinking is always on for Claude Sonnet 5.5, and reasoning is listed among its capabilities on AI/ML API. Anthropic reports 64.5% on Humanity's Last Exam with tools.
Can Claude Sonnet 5.5 use tools?
Yes. Tool and function calling are supported. Anthropic reports 70.6% on Terminal-Bench 4.0 and 80.1% on OSWorld 2.1, both of which measure tool and computer use.
Does Claude Sonnet 5.5 support vision?
Yes. Claude Sonnet 5.5 accepts image input alongside text. Anthropic reports 61.6% on Chartography without tools, and says it is the first Sonnet model to finish Pokemon Red working only from screenshots.
Can Claude Sonnet 5.5 stream responses?
Yes. Response streaming is supported through the standard chat completions endpoint on AI/ML API.
What kinds of tasks fit Claude Sonnet 5.5?
Anthropic positions it for coding, multi-step workflows and autonomous agents, and reports its largest gains over Claude Sonnet 5 on agentic evaluations such as Terminal-Bench 4.0 and CursorBench 4.0. The 1M-token context window also suits long documents and whole-repository work.
Is Claude Sonnet 5.5 suitable for multi-file coding work?
Yes. Anthropic says it is designed to navigate real codebases, land multi-file changes, and carry longer debugging and refactoring tasks through to completion.
Does Claude Sonnet 5.5 work with text and images?
Yes. It accepts text and image input and returns text, with a 1,000,000-token context window and up to 128,000 output tokens.
Is Claude Sonnet 5.5 an agentic model?
Yes. It is built for agentic work, and the largest gains Anthropic reports over Claude Sonnet 5 are on agentic evaluations: 70.6% against 10.3% on Terminal-Bench 4.0, and 55.5% against 34.1% on CursorBench 4.0.