Anthropic
Claude Haiku 4.5
anthropic/claude-haiku-4.5
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Only tracked on Vercel AI Gateway.
Claude Haiku 4.5 usage over time
Vercel AI Gateway share of tokens, by day.
Claude Haiku 4.5 holds 2.70% today, down from 3.13% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
Claude Haiku 4.5'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 2026-09-02, Claude Haiku 4.5 holds 0.0% of Vercel AI Gateway token share, down 2.70pp over 30 days. Source: Tidelines (Vercel AI Gateway).
Cost per session
Median dollars spent on one Claude Haiku 4.5 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 |
|---|---|---|---|---|
| Hermes Agent | $0.024 | $0.045 | $0.221 | $1.48 |
| Claude Code | $0.0099 | $0.046 | $0.212 | $1.24 |
| Kilo Code | $0.0035 | — | — | — |
Where to run it
Claude Haiku 4.5 pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Claude Haiku 4.5 is served by 6 tracked endpoints on OpenRouter. The cheapest output price is $5.00 per million tokens from Azure, and the most expensive is $5.50 from Google · 200k. The largest context window offered is 200k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| Azure | $1.00 | $5.00 | 200k | 99.76% |
| Amazon Bedrock · 200k | $1.00 | $5.00 | 200k | 99.97% |
| Google · 200k | $1.00 | $5.00 | 200k | 100.00% |
| Anthropic | $1.00 | $5.00 | 200k | 99.99% |
| Amazon Bedrock · 200k | $1.10 | $5.50 | 200k | — |
| Google · 200k | $1.10 | $5.50 | 200k | — |