Seedance 2.5 is coming soonLearn more
EvoLink.AIEvoLink.AI

Claude Sonnet 5 API

Claude Sonnet 5 is Anthropic's most capable Sonnet for coding and agentic work — a drop-in replacement for Sonnet 4.6, with its largest gains in coding and agent tasks. It ships with a 1M context window, 128K max output, and adaptive thinking on by default. Access it through EvoLink's unified API.
Model Type:
✓Claude Sonnet 5
Price: 

$2.700(~ 183.6 credits) per 1M input tokens; $13.500(~ 918 credits) per 1M output tokens

$3.375(~ 229.5 credits) per 1M cache write tokens; $0.271(~ 18.4 credits) per 1M cache read tokens

Web search tool charged separately per request.

Stable managed access for production workloads. Recommended when you need dashboard billing, API key control, and predictable integration behavior.

Use the same API endpoint for all versions. Only the model parameter differs.

Claude Sonnet 5 API — Anthropic's most capable Sonnet for coding and agents

Claude Sonnet 5 (Claude 5 Sonnet) delivers strong coding and agentic performance across terminals and browsers, with a 1M context window, up to 128K output tokens, and adaptive thinking on by default.

Claude Sonnet 5 API visualization

What can you build with the Claude Sonnet 5 API?

Agentic Coding Assistant

Sonnet 5 posts its largest gains over Sonnet 4.6 in coding — planning multi-step changes, running terminals, and iterating on results. With up to 128K output and a 1M context window, it handles large codebases and generates comprehensive diffs, test suites, and implementation plans in a single request.

Try coding
Coding capabilities

Autonomous Agents

Build agents that plan a sequence of steps, call tools, read the result, and keep going without a human nudge at every turn. Sonnet 5 is built for terminal and browser use and long-horizon runs, delivering reliable tool use across multi-step workflows.

Build agents
Agentic capabilities

Large-Context Analysis

Read very large documents, codebases, or long agent traces in a single request with the 1M context window, and let adaptive thinking apply deeper reasoning only when a task needs it — keeping cost predictable for research, planning, and technical strategy.

Explore analysis
Large-context analysis capabilities

Why teams choose the Claude Sonnet 5 API on EvoLink

Get Anthropic's most capable Sonnet with stable model IDs, prompt caching, and unified routing through EvoLink's single API key.

Opus-class coding and agents

Sonnet 5 is a drop-in replacement for Sonnet 4.6 with its biggest gains in coding and agentic tasks — strong coding and agent performance without moving to an Opus-class model.

128K max output and 1M context

Generate comprehensive code, documentation, and analysis in a single request, and read large codebases or long agent traces within the 1M context window.

Adaptive thinking, on by default

Sonnet 5 automatically scales reasoning to task difficulty — no manual thinking budgets to tune. Prompt caching further cuts repeat costs, with cache hits billed at 0.1x the base input rate.

How to integrate the Claude Sonnet 5 API

Connect through EvoLink, choose your model ID, and start building in minutes.

1

Step 1 — Create your EvoLink API key

Sign up for EvoLink to get a single API key that routes to Anthropic, Bedrock, or Google Cloud.

2

Step 2 — Select the model ID

Use `claude-sonnet-5` to access the latest Sonnet 5 model through EvoLink's unified API. It is a drop-in replacement for `claude-sonnet-4-6`.

3

Step 3 — Optimize quality and cost

Adaptive thinking is on by default and can be tuned with the effort parameter; use prompt caching for stable system prompts and repeated long context to lower repeat costs.

Claude Sonnet 5 API capabilities

Key specs and model features for production use

Context

1M Context Window

Read very large documents or codebases in a single request. 1M is both the default and the maximum context.

Capacity

128K Max Output

Generate long-form answers, plans, and code without early truncation.

Intelligence

Adaptive Thinking

Reasoning scales to task difficulty automatically, on by default — tune it with the effort parameter instead of manual thinking budgets.

Agents

Agentic Coding & Tool Use

Built for terminal and browser agents, reliable function calling, and long-horizon multi-step runs.

Multimodal

Vision + Multilingual Input

Accept text and image inputs with strong multilingual understanding.

Efficiency

Prompt Caching Rates

Cache writes and reads are priced separately; cache hits are billed at 0.1x the base input price.

All Claude API Models

EvoLink provides unified API access to the full Claude model family — Opus for flagship intelligence, Sonnet for everyday balance, and Haiku for speed and scale. All models share the same EvoLink API endpoint. Switch models with one parameter.

Explore Claude familyView Opus 4.8View Haiku 4.5

Claude Sonnet 5 API - FAQ

Everything you need to know about the product and billing.

Claude Sonnet 5 supports a 1M token context window — both the default and the maximum, with no smaller variant — and up to 128K output tokens in a single request, making it suitable for large codebases, long documents, and comprehensive generation tasks.
Use `claude-sonnet-5` through EvoLink's unified, OpenAI-compatible API to access the latest Sonnet 5 model with a single API key. It is a drop-in replacement for `claude-sonnet-4-6` — update the model ID and, if needed, review token budgets and thinking settings.
Sonnet 5 uses adaptive thinking, on by default, which scales reasoning to task difficulty. Manual extended thinking (setting `budget_tokens`) is no longer supported and returns a 400 error — use the effort parameter to guide reasoning depth instead. To turn thinking off, pass `thinking: {type: "disabled"}`.
Sonnet 5 is a drop-in replacement, but note three things: adaptive thinking is on by default, manual extended thinking returns a 400 error, and non-default sampling parameters (`temperature`, `top_p`, `top_k`) return a 400 error — remove them when migrating. Tool definitions and response shapes are unchanged.
Sonnet 5 uses a new tokenizer that produces roughly 30% more tokens for the same text. Per-token pricing is unchanged, but the cost and context capacity of an equivalent request can differ — recount your prompts and revisit `max_tokens` limits sized close to your expected output.
Standard pricing is $3 per million input tokens and $15 per million output tokens (MTok = one million tokens). Prompt caching is billed separately — cache writes at $3.75/MTok and cache hits at $0.30/MTok (0.1x the base input price). Provider pricing can differ on Bedrock or Google Cloud; see the EvoLink pricing on this page for current rates.
Sonnet 5 delivers Opus-class coding and agentic performance and is the right default for most production workloads. Opus 4.8 is the flagship for the hardest reasoning and agent tasks where top-tier quality matters most.
Claude Sonnet 5 is available via the Anthropic API, AWS Bedrock, Google Cloud (Vertex AI), and Microsoft Foundry (preview). EvoLink can route to the provider you choose.
Yes. Sonnet 5 supports text and image input with strong multilingual capabilities, so you can combine documents, screenshots, and visuals in one request.