Anthropic
anthropic/claude-sonnet-5.5
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
Only tracked on Vercel AI Gateway.
Vercel AI Gateway share of tokens, by day.
Claude Sonnet 5.5 holds 3.12% today, up from 0.13% at the start of the visible window.
Claude Sonnet 5.5's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-11-22, Claude Sonnet 5.5 holds 3.1% of Vercel AI Gateway token share, up 0.88pp over 30 days. Data: Vercel AI Gateway as of 2026-11-22. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Claude Sonnet 5.5 is served by 5 tracked endpoints on OpenRouter. The cheapest output price is $10.00 per million tokens from Google, and the most expensive is $10.00 from Anthropic. The largest context window offered is 1000k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| $2.00 | $10.00 | 1000k | 100.00% | |
| Amazon Bedrock | $2.00 | $10.00 | 1000k | 100.00% |
| Azure | $2.00 | $10.00 | 1000k | 100.00% |
| Claude Platform on AWS | $2.00 | $10.00 | 1000k | 100.00% |
| Anthropic | $2.00 | $10.00 | 1000k | 100.00% |
Median dollars spent on one Claude Sonnet 5.5 session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns | 50+ turns |
|---|---|---|---|---|
| Kilo Code | $0.069 | $0.207 | $0.745 | $4.10 |
| Hermes Agent | $0.029 | $0.083 | $0.516 | $3.47 |
| Claude Code | $0.044 | $0.117 | $0.486 | $3.48 |
| Codex | $0.035 | $0.107 | $0.472 | — |