Claude Sonnet 5 (batch)
anthropic/claude-sonnet-5:batch
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
Key facts
- Input price
- $1.00 / 1M tokens
- Output price
- $5.00 / 1M tokens
- Context window
- 1M tokens
- Max output
- 128K tokens
- Accepts
- Text, Images, Files
- Returns
- Text
Example: 1,000 requests with 1,000 input and 500 output tokens each would cost about $3.50 (1M input tokens × $1.00 + 0.5M output tokens × $5.00). Estimate your own usage.
Prices are the provider’s own per-token rates with zero markup, from our price list as of Oct 18, 2026. If a call has extra provider charges (images, audio, web search, cached prompts), you pay the reported cost.
Call it from your code
curl https://api.tokenctr.com/v1/chat/completions \
-H "Authorization: Bearer $TOKENCENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "anthropic/claude-sonnet-5:batch", "messages": [{"role": "user", "content": "Hello!"}]}'Works with any OpenAI-compatible SDK: set the base URL to https://api.tokenctr.com/v1. Quickstart
Benchmarks
Artificial Analysis
- Intelligence index
- 38.2
- Coding index
- 71.5
- Agentic index
- 43.6
Design Arena
| Category | Rank | Elo | Win rate |
|---|---|---|---|
| Agents: HTML slides | 5 | 1217 | 53.7% |
| Agents: Agentic game dev | 7 | 1226 | 52.3% |
| Agents: Android native | 9 | 1236 | 54.3% |
| Agents: Full-stack | 9 | 1249 | 53.7% |
| Agents: Web apps | 10 | 1238 | 53.3% |
| Agents: Godot game dev | 13 | 1225 | 54.4% |
| Agents: Mobile apps | 13 | 1210 | 50.9% |
| Agents: Slides (python-pptx) | 13 | 1216 | 50.1% |
| Models: ASCII art | 21 | 1210 | 51.4% |
| Models: Game dev | 22 | 1283 | 52.1% |
| Models: Websites | 24 | 1276 | 52.3% |
| Models: Code | 25 | 1278 | 52.7% |
| Models: UI components | 25 | 1279 | 53.9% |
| Models: 3D | 27 | 1262 | 54.1% |
| Models: SVG | 27 | 1193 | 49.8% |
| Models: Data visualization | 32 | 1251 | 52.9% |
Source: Artificial Analysis indexes and Design Arena results as published in OpenRouter’s model data, fetched Oct 15, 2026. Higher is better. Not measured by TokenCenter. See all rankings.