Google Vertex Anthropic
Claude Sonnet 5
Everyday Claude agent model for coding, planning, browsing, and general work
Cheapest input
$2
$/MTok · models.dev
Cheapest output
$10
$/MTok
Context
1M
tokens
Offers
4
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestclaude-sonnet-5@default | Vertex (Anthropic) | $2 | $10 | $0.2 | 1M |
| models.devclaude-sonnet-5@default | Google Vertex AI | $2 | $10 | $0.2 | 1M |
| LiteLLMclaude-sonnet-5@default | — | $2 | $10 | $0.2 | — |
| LiteLLMvertex_ai/claude-sonnet-5@default | — | $2 | $10 | $0.2 | — |
Capabilities
- Reasoning
- Tool calling
- Attachments
- In: text
- In: image
- In: pdf
- Out: text
Knowledge cutoff: 2026-01-31Released: 2026-06-30Family: claude-sonnet
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- Arena agent (net improvement)8.57
- Arena agent net improvement8.57
- Arena agent confirmed success7.95
- AA intelligence53.4
- AA coding71.5
- AA agentic46.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.