Claude Sonnet 5

anthropic/claude-sonnet-5
NewFeatured
VisionToolsJSONReasoning
by Anthropic · 2026-06-30

Claude Sonnet 5 is Anthropic's most capable Sonnet-class model — frontier-level performance across coding, agentic workflows, and professional knowledge work, at a fraction of the cost of the Opus tier. It serves a 1M-token context window with up to 128K output tokens, accepts text, image, and file inputs with text output, and supports adaptive thinking with selectable reasoning effort (low, medium, high, max) so callers can dial the intelligence / latency / cost tradeoff per request. Built as Anthropic's most agentic Sonnet yet, it posts large gains over Sonnet 4.6 on agentic coding and computer-use and closes much of the gap to Opus 4.8 — 63.2% on SWE-bench Pro, 80.4% on Terminal-Bench 2.1, and 81.2% on OSWorld-Verified — while pricing well below Opus 4.8, GPT-5.5, and Gemini 3.1 Pro. It is a strong default for cost-sensitive agents, coding assistants, and high-volume production workloads that still demand frontier reasoning.

ctx1M tokens
Max output128K
Inputtext + image + file
Outputtext
p50 TTFT1.75 s
INPUT$2.00/ 1M tokens
OUTPUT$10.00/ 1M tokens
p50 TTFT1.75 s7d
p95 TTFT7.55 s7d
TRAFFIC78.9Mtokens / 7d

Claude Sonnet 5 is an Anthropic model designed for long-context, multimodal tasks. It supports up to 1,000,000 input tokens—enough to cover entire codebases, lengthy documents, or multiple data…

What is Claude Sonnet 5 and who is it for?

What input modalities does it support?

How does OrcaRouter's zero-markup pricing work for this model?

What is the context window and max output?

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-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • stop
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Pricing

Input / 1M tokens$2.00
Output / 1M tokens$10.00
Cache read / 1M$0.200
Cache write / 1M$2.50
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $44.00 · With prompt caching $37.70

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.005040

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

Performance

p50 TTFT
1.75 s
Output speed
93.6 tok/s
p95 TTFT
7.55 s
Error rate
0.29%

Public benchmarks

Humanity's Last Exam (no tools)
43.2
Humanity's Last Exam (with tools)
57.4
OSWorld-Verified
81.2
SWE-bench Pro
63.2
Terminal-Bench 2.1
80.4
Source: anthropic.com

How it compares

Claude Sonnet 5Claude Fable 5Claude Opus 4.7Claude Opus 4.8
Input $/M$2.00$10.00$5.00$5.00
Output $/M$10.00$50.00$25.00$25.00
Context1.0M1.0M1.0M1.0M
Quality9/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use Claude Sonnet 5 on OrcaRouter?
Pricing is $2.00 per 1 million input tokens and $10.00 per 1 million output tokens, billed at Anthropic's provider rate with zero markup. There are no additional fees.
What is the context window of Claude Sonnet 5?
It supports up to 1,000,000 tokens of input and can generate up to 128,000 tokens of output.
What are Claude Sonnet 5's main strengths?
Large context window, high output limit, multimodal inputs (text, image, file), strong OS-level reasoning (81.2 OSWorld-Verified), and transparent pricing.
How does Claude Sonnet 5 compare to other Claude models?
It is a mid-tier model with a larger context and output than Sonnet 4, and lower per-token cost. It trades off some reasoning depth compared to Claude Opus but offers better cost efficiency for long-context tasks.
Does OrcaRouter support data privacy for Claude Sonnet 5?
OrcaRouter acts as a proxy and does not store your prompts or responses beyond the duration needed to fulfill the request. Anthropic's data handling policies apply; review Anthropic's privacy policy for details.
How do I call Claude Sonnet 5 via the OrcaRouter API?
Set the base URL to https://api.orcarouter.ai/v1, use the model ID "anthropic/claude-sonnet-5", and structure your request in OpenAI's chat completions format. API keys are obtained from OrcaRouter.
What languages and frameworks are supported for the API call?
Any language with an HTTP client or an OpenAI SDK can be used. The endpoint is fully compatible with OpenAI's Python, Node.js, Java, and other client libraries.
Is the pricing for image and file inputs the same as text?
Yes. Images and files are tokenized by Anthropic and billed at the same input token rate of $2.00 per 1M tokens. OrcaRouter does not add any extra charges for multimodal inputs.
Can I use Claude Sonnet 5 for streaming responses?
Yes. Set the stream parameter to true in your API call. OrcaRouter supports streaming of token chunks in the same format as OpenAI's streaming responses.
What happens if my input exceeds 1,000,000 tokens?
OrcaRouter will return an HTTP 400 error with a message indicating the context length is exceeded. You must truncate or shorten your input before retrying.

Embed this badge

Anthropic: Claude Sonnet 5$2.00/M in1755ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/anthropic/claude-sonnet-5" target="_blank"> <img src="https://www.orcarouter.ai/embed/anthropic/claude-sonnet-5.svg" alt="Anthropic: Claude Sonnet 5 on OrcaRouter" /> </a>
Markdown [![Anthropic: Claude Sonnet 5](https://www.orcarouter.ai/embed/anthropic/claude-sonnet-5.svg)](https://www.orcarouter.ai/models/anthropic/claude-sonnet-5)

Model card as data

GET /api/public/models/anthropic/claude-sonnet-5Open
Machine-readable:/llms.txt/llms-full.txt