Claude Sonnet 4.5

Anthropic's high-performance model balancing speed and intelligence for agents and coding.

AgentsCodingBalanced Performance

Context Window

200k tokens (1M beta with header)

Claude Sonnet 4.5

Max Output

64k tokens

MTok

Input

Output

$15

Model Codeclaude-sonnet-4-5

Playground

Model Code

claude-sonnet-4-5

Reference inputs

Reference Images0/5

Click or drag

Enter your prompt here...

Output

No output yet

Pricing

Plan	Context Window	Max Output	Input	Output	Cache Write	Cache Read
Claude Sonnet 4.5	200k tokens (1M beta with header)	64k tokens	$3	$15	5m: $3.75 1h: $6	$0.30

Official Anthropic pricing for Claude Sonnet 4.5 on the Claude API.

With the 1M beta context header, requests over 200k input tokens are billed at $6 input / $22.50 output per MTok.

Cache read or cached input pricing applies to reused prompt tokens.

README

Claude Sonnet 4.5 is Anthropic's model for complex agents and coding, designed to balance strong intelligence with faster latency and more accessible pricing than Opus-tier models.

Anthropic positions Claude Sonnet 4.5 as the best combination of speed and intelligence for many production workloads.
It is built for coding, complex agents, and broad professional tasks where teams need high quality without Opus-level cost.
Sonnet 4.5 supports a standard 200k context window, with 1M context support offered via beta header in the Claude API.

API

Use the API docs for request format, parameters, and integration details.

Anthropic's high-performance model balancing speed and intelligence for agents and coding.

Model Code

claude-sonnet-4-5

View API Docs

API

Endpoint

POST /v1/messages

Authentication

Authorization: Bearer YOUR_REACH_API_KEY
anthropic-version: 2023-06-01
Content-Type: application/json

Example

curl -X POST "https://direct.reachapi.ai/v1/messages" \
  -H "Authorization: Bearer YOUR_REACH_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {
        "role": "user",
        "content": "Introduce ReachAPI in one sentence."
      }
    ],
    "max_tokens": 512,
    "temperature": 0.2
  }'

Related Models

Other models from the same vendor

Claude Fable 5

Anthropic's most capable widely released model for next-generation intelligence and long-running agents.

Claude Opus 5

Anthropic's flagship model for deep reasoning, complex agentic coding, and long-horizon enterprise work.

Claude Sonnet 5

Anthropic's new Sonnet model for extended-context coding, agents, and enterprise production workflows.

Claude Opus 4.8

Anthropic's newest Opus-tier model for complex reasoning, long-horizon agentic coding, and high-autonomy enterprise work.

Claude Opus 4.7

Anthropic's premium Opus model for advanced coding, vision-heavy review, and long-running enterprise agents.

Claude Opus 4.6

Anthropic's most capable model for coding, agents, and high-stakes enterprise work.