Anthropic
Anthropic’s efficiency-oriented model with adaptive thinking, image input, a 1M-token context and medium effort by default.
At a glance
API model ID: claude-haiku-5-5
Capabilities & boundaries
Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
Adaptive thinking is enabled by default. Set output_config.effort to choose the tradeoff. Thinking can be disabled at low, medium or high, but disabling it at xhigh or max returns a 400 error. The older enabled/budget_tokens configuration is not accepted.
Put it to work
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Keep a short, repeatable classification task grounded in policy.
Classify these support messages using only the categories and policy excerpts I provide. Return message ID, category, urgency, supporting phrase and whether a human review is required. Do not invent missing account facts or promise refunds. Put ambiguous cases in needs review and keep the customer-facing reply under 80 words.
Workflow 02
Use visible evidence without guessing hidden behavior.
Inspect this settings screenshot against the checklist below. Record the visible label, displayed value, evidence location and any mismatch. Mark obscured values as unreadable. Separate observations from interaction tests, and propose the smallest next check for each unresolved item.
Workflow 03
Make code assistance focused and easy to verify.
Review this patch against the stated behavior. Look for concrete regressions and edge cases, cite the affected lines, and suggest only minimal changes. Finish with three targeted tests and their expected outcomes. Do not claim to have executed tests or modify unrelated code.
Developer reference
These are provider API reference prices, not EZ Ai Assist subscription prices.
View EZ Ai Assist plans| Token type | ≤ 100,000input tokens | > 100,000input tokens |
|---|---|---|
| Input | $0.10 | $0.50 |
| Output | $0.50 | $2.50 |
| Cache write · 5 minutes | $0.125 | $0.625 |
| Cache write · 1 hour | $0.20 | $1.00 |
| Cache read | $0.01 | $0.05 |
Common questions
The Claude API uses claude-haiku-5-5, a fixed ID without a dated suffix or separate alias. Other platforms can use their own identifier formats.
Yes at low, medium or high effort. At xhigh and max, use adaptive thinking. Lower effort reduces thinking but is not a substitute for testing instruction-following quality.
No. Haiku 5.5 applies a higher price tier above 100,000 input tokens, well below its context ceiling. Tokenization also differs from Haiku 4.5.
No shutdown date is established here. Anthropic lists it as active; the not-sooner-than date is a minimum availability commitment, not a retirement announcement.
No. A catalog entry and provider capability reference do not establish current app access, enabled tools or available settings. Check the model selector and controls in your workspace.
No. Provider API rates are developer references. Your subscription and any limits shown in the app are separate; use the website pricing page for plans.
Provide the relevant evidence and acceptance criteria, ask for source references or reproducible checks, and review the result. Distinguish a proposed tool action from a tool action actually executed.
Check the source
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.
Same provider
Anthropic
Anthropic model for coding and everyday professional work, with adaptive thinking, image input, and a 1M-token context window.
Anthropic
Claude Opus 5.5 is Anthropic’s model for demanding coding and analysis, with always-on adaptive thinking and optional API Fast Mode.
Anthropic
Anthropic’s active legacy Opus model for complex coding and analysis, with adaptive thinking and a 1M-token context window.
Anthropic
Anthropic’s active legacy Sonnet model for coding and general work, with adaptive thinking and a 1M-token context window.