Google Vertex Anthropic
Claude Opus 4.7
Stronger Opus tier for advanced software work and high-stakes reasoning
Cheapest input
$5
$/MTok · models.dev
Cheapest output
$25
$/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-opus-4-7@default | Vertex (Anthropic) | $5 | $25 | $0.5 | 1M |
| models.devclaude-opus-4-7@default | Google Vertex AI | $5 | $25 | $0.5 | 1M |
| LiteLLMclaude-opus-4-7@default | — | $5 | $25 | $0.5 | — |
| LiteLLMvertex_ai/claude-opus-4-7@default | — | $5 | $25 | $0.5 | — |
Capabilities
- Reasoning
- Tool calling
- Attachments
- In: text
- In: image
- In: pdf
- Out: text
Knowledge cutoff: 2026-01-31Released: 2026-04-16Family: claude-opus
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 code Elo1561
- Arena agent (net improvement)8.19
- Arena agent net improvement8.19
- Arena agent confirmed success6.19
- Arena text Elo1492
- Arena vision Elo1298
- AA intelligence53.5
- AA coding73.6
- AA agentic44.4
Sources: Arena AI, Artificial Analysis. See /benchmarks.