claude-haiku-5-5
Google Vertex
claude-haiku-5-5
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window. It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.
Provider pricing
The same model is offered by several providers. Prices below are per provider; select a row to switch provider.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache creation / 1M | Context | Max output |
|---|---|---|---|---|---|---|
Current | $0.10 | $0.50 | $0.01 | $0.125 | 1M | 128,000 |
Pricing
Tiered by context window; prices below are from the current provider, per 1M tokens.
| Token range | Input / 1M | Output / 1M | Cache read / 1M | Cache creation / 1M |
|---|---|---|---|---|
0 < Token ≤ 100K | $0.10 | $0.50 | $0.01 | $0.125 |
100K < Token ≤ 1000K | $0.50 | $2.50 | $0.05 | $0.625 |
Performance
Data for this section is coming soon.
Uptime
Data for this section is coming soon.