z-ai
Claude Sonnet 5 vs GLM 5.3
76.1 overall · $0.862 / 1M
// anthropic
Claude Sonnet 5
anthropic/claude-sonnet-5
reasoningtool callingimage inputfile inputprompt caching
Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens with a 1M-token context window.
A reasoning, tool-calling model from anthropic, released Jun 30, 2026. On LiveBench it scores 76.0 overall — #24 of 55 benchmarked models — and ranks highest in agentic coding (#11).
- Input / 1M
- $2.00
- Output / 1M
- $10.00
- Context
- 1M
- LiveBench overall
- 76.0 · #24
Specs and pricing
| Input price USD per 1M prompt tokens | $2.00 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $10.00 |
| Blended price 3:1 input:output — #53 most expensive of 343 listed models | $4.00 |
| Cached input read Blank means not priced separately — not free | $0.200 |
| Cache write | $2.50 |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Input modalities | text, image, file |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Jun 30, 2026 |
Also listed as anthropic/claude-sonnet-5:batch ($2.00 blended)— the same model at a different price or rate limit.
Benchmarks by category
LiveBench scores out of 100, with Claude Sonnet 5's rank among the 55 benchmarked models listed here. Run: claude-sonnet-5-xhigh-effort.
Language#41 of 55
75.0
$0.0850 measured per point
What Claude Sonnet 5 costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,150/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,480/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,392/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,660/mo |
| Bulk classification 500 in / 20 out × 5M requests | $5,100/mo |
Compare Claude Sonnet 5 with
The benchmarked models closest to it on overall score.
anthropic
Claude Sonnet 5 vs Claude Opus 4.8
76.2 overall · $10.00 / 1M
Claude Sonnet 5 vs Gemini 3.8 Flash
75.8 overall · $1.50 / 1M
x-ai
Claude Sonnet 5 vs SpaceXAI: Grok 4.5
75.8 overall · $3.00 / 1M
anthropic
Claude Sonnet 5 vs Claude Opus 4.7
76.5 overall · $10.00 / 1M
deepseek
Claude Sonnet 5 vs DeepSeek V4 Flash Vision Exp
76.8 overall · $0.330 / 1M
Claude Sonnet 5 FAQ
How much does Claude Sonnet 5 cost?
Claude Sonnet 5 lists at $2.00 per 1M input tokens and $10.00 per 1M output tokens, with cached input reads at $0.200 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $1,480 at list price.
What is the context window of Claude Sonnet 5?
Claude Sonnet 5 accepts up to 1,000,000 tokens of context and can return up to 128,000 output tokens per response.
Does Claude Sonnet 5 support tool calling?
Yes — Claude Sonnet 5 supports tool (function) calling and exposes extended reasoning. It accepts text, image, file input.
How does Claude Sonnet 5 score on benchmarks?
On LiveBench release 2026-06-25 (run: claude-sonnet-5-xhigh-effort), Claude Sonnet 5 scores 76.0 overall, ranking #24 of 55 benchmarked models.
What is the API model ID for Claude Sonnet 5?
On OpenRouter the model ID is "anthropic/claude-sonnet-5". It was listed on Jun 30, 2026.
More from anthropic
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.