Claude Sonnet 4.6

anthropic/claude-sonnet-4.6
VisionToolsJSONReasoning
by Anthropic · 2026-02-17

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

ctx1M tokens
Max output64K
Inputtext + image + file
Outputtext
p50 TTFT7.84 s
INPUT$3.00/ 1M tokens
OUTPUT$15.00/ 1M tokens
p50 TTFT7.84 s7d
p95 TTFT10.00 s7d
TRAFFIC2.2Mtokens / 7d

Claude Sonnet 4.6 is an AI model from Anthropic that processes text, images, and files. It has a context window of 1,000,000 tokens and a maximum output of 64,000 tokens. The model is accessed…

What is Claude Sonnet 4.6?

Who should use Claude Sonnet 4.6?

Key specifications at a glance

How does Claude Sonnet 4.6 fit into Anthropic's model family?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Anthropic SDKhttps://api.orcarouter.ai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.6",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_tokens
  • output_config
  • reasoning
  • response_format
  • stop
  • stream
  • structured_outputs
  • temperature
  • thinking
  • tool_choice
  • tools
  • top_p

Pricing

Input / 1M tokens$3.00
Output / 1M tokens$15.00
Cache read / 1M$0.300
Cache write / 1M$3.75
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $66.00 · With prompt caching $56.55

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.007560

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
7.84 s
Output speed
58.5 tok/s
p95 TTFT
10.00 s
Error rate
2.2%

Public benchmarks

46.4
AA Coding
Better than 60% of models compared
#42 of 106
44.4
AA Intelligence
Better than 50% of models compared
#55 of 110
GPQA Diamond
79.9
Humanity's Last Exam
13.2
IFBench
41.2
Long-Context Recall
57.7
SciCode
46.9
TerminalBench Hard
46.2
τ²-Bench
79.5
Source: artificialanalysis.ai

How it compares

Claude Sonnet 4.6Claude Fable 5Claude Opus 4.7Claude Opus 4.8
Input $/M$3.00$10.00$5.00$5.00
Output $/M$15.00$50.00$25.00$25.00
Context1.0M1.0M1.0M1.0M
Quality8/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the pricing for Claude Sonnet 4.6 on OrcaRouter?
Pricing is $3.00 per 1 million input tokens and $15.00 per 1 million output tokens. This is the provider rate with zero markup. You pay exactly that; OrcaRouter does not add any fees.
What is the context window size?
The context window is 1,000,000 tokens. The maximum output is 64,000 tokens per request.
What are the model's main strengths?
Based on available data, strengths include a 79.9 score on GPQA Diamond (graduate-level reasoning), support for text, image, and file inputs, and a 1M token context window for long documents.
How does Claude Sonnet 4.6 compare to smaller models?
Claude Sonnet 4.6 is more capable on complex reasoning and long-context tasks, but it costs more per token. For simple tasks, a cheaper model may be more economical.
How does data handling work when using OrcaRouter?
OrcaRouter routes your requests to the provider. Data is transmitted over HTTPS. Refer to OrcaRouter's privacy policy and Anthropic's data usage terms for details on data retention and processing.
How do I call Claude Sonnet 4.6 via an OpenAI-compatible API?
Set the base URL to https://api.orcarouter.ai/v1 and the model ID to "anthropic/claude-sonnet-4.6". Use standard OpenAI SDKs or direct HTTP requests with your OrcaRouter API key.
What input modalities does this model support?
It supports text, image, and file inputs. You can include images as base64 or URLs, and files as text or binary data in the messages array.
Is there a limit on file size or number of images?
The provider may have limits. Check Anthropic's documentation. Generally, images should be reasonably sized, and files are processed as text if possible. OrcaRouter passes the input as-is.
Can I use streaming and function calling?
Yes, streaming is supported via the stream parameter. Function calling (tools) is also supported. These work through OrcaRouter's OpenAI-compatible endpoint.
What should I do if my task is not a good fit for Claude Sonnet 4.6?
OrcaRouter offers many other models at different price points and capabilities. Try a smaller or cheaper model for simple tasks, or a more powerful one for cutting-edge reasoning. You can switch model IDs easily.

Embed this badge

Anthropic: Claude Sonnet 4.6$3.00/M in7839ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/anthropic/claude-sonnet-4.6" target="_blank"> <img src="https://www.orcarouter.ai/embed/anthropic/claude-sonnet-4.6.svg" alt="Anthropic: Claude Sonnet 4.6 on OrcaRouter" /> </a>
Markdown [![Anthropic: Claude Sonnet 4.6](https://www.orcarouter.ai/embed/anthropic/claude-sonnet-4.6.svg)](https://www.orcarouter.ai/models/anthropic/claude-sonnet-4.6)

Model card as data

GET /api/public/models/anthropic/claude-sonnet-4.6Open
Machine-readable:/llms.txt/llms-full.txt