Claude Sonnet 5
Anthropic's new Sonnet model for extended-context coding, agents, and enterprise production workflows.
Context Window
1M tokens
claude-sonnet-5
Max Output
-
1M tokens
Input
$1.8$2
10% off1M tokens
Output
$9$10
10% off1M tokens
claude-sonnet-5Playground
claude-sonnet-5Click or drag
No output yet
Pricing
| Plan | Context Window | Max Output | Input | Output | Cache Write | Cache Read |
|---|---|---|---|---|---|---|
claude-sonnet-5 | 1M tokens | - | $1.8$210% off 1M tokens | $9$1010% off 1M tokens | $2.25$2.5010% off 1M tokens | $0.18$0.210% off 1M tokens |
1h Cache Write · $3.6 · 1M tokens
Cache read or cached input pricing applies to reused prompt tokens.
README
- Claude Sonnet 5 extends the Sonnet line with a 1M-token context window and 128k-token maximum output, making it better suited for large repositories, multi-document analysis, and long-running agent sessions.
- The model is positioned for coding, tool use, enterprise automation, and other workflows where teams need reliable reasoning over substantial context without moving every request to an Opus-tier model.
- ReachAPI exposes the model through the `claude-sonnet-5` model code so teams can route new Sonnet workloads through the same API surface used by existing Claude models.
API
Anthropic's new Sonnet model for extended-context coding, agents, and enterprise production workflows.
Model Code
claude-sonnet-5
API
Endpoint
POST /v1/messagesAuthentication
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
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 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.
Claude Sonnet 4.6
Anthropic's high-performance daily driver for coding, agents, and professional workflows at scale.
