Claude Haiku 4.5
- Input price
- $1.00
- Per 1 million tokens (USD)
- Output price
- $5.00
- Per 1 million tokens (USD)
- Effort levels
- not supported
- Benchmark results
- 7total
- Benchmark types: 7
Model information
- API model ID
- claude-haiku-4-5
- release date
- Unknown
- effort
- not supported
- Effort source
- Not supported: Anthropic effort documentation (platform.claude.com/docs/en/build-with-claude/effort) confirms effort is not supported (researched 2026-11-12).
- Claude Code
- available
- Codex
- unavailable
- Availability notes
- `haiku` resolves to Haiku 4.5 on third-party providers. effort not supported. Codex's official model list (learn.chatgpt.com/docs/models) contains only OpenAI models, so codex is false (connections via a custom provider are not counted as official options).
- Availability source
- https://code.claude.com/docs/en/model-config
Price (USD per 1 million tokens)
Prices do not vary by effort; token consumption does.
| input | $1.00 |
|---|---|
| output | $5.00 |
| cache read | $0.10 |
| cache write | $1.25 |
cacheWritePerMTok is for a 5-minute cache write. 1h write $2. 200K context.
Claude Haiku 4.5 | $1 / MTok | $1.25 / MTok | $2 / MTok | $0.10 / MTok | $5 / MTokSource: https://platform.claude.com/docs/en/about-claude/pricing
Benchmark results
| Benchmark | effort | Score | Source cost (metric) | measured/reported by | source | Conditions and extraction method |
|---|---|---|---|---|---|---|
| Terminal-Bench 4.0not stated | not stated | 0.0% | $0.79Cost per attempt | Anthropic | Introducing Claude Haiku 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "Terminal-Bench 4.0 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); no effort because the source effort label "max" is not in the official effort listtranscribed from textSource excerptTerminal-Bench 4.0 — Accuracy vs. cost: "Haiku 4.5 · Max: 0.0% $0.79" |
| GDPval-AA v2.1not stated | not stated | 735 | $0.24Cost per task | Anthropic | Introducing Claude Haiku 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "GDPval-AA v2.1 / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); no effort because the source effort label "max" is not in the official effort listtranscribed from textSource excerptGDPval-AA v2.1 — Accuracy vs. cost: "Haiku 4.5 · Max: 735.0 $0.24" |
| AA-Briefcase v1.1(Elo)not stated | not stated | 614 | — | Anthropic | Introducing Claude Haiku 5.5official · Retrieved 2026-11-12 | Vendor-reported value. table note: see the Haiku 5.5 System Card (effort not stated)transcribed from tableSource excerpt614Location Table, AA-Briefcase v1.1 (Elo) row: 614 |
| Humanity's Last Exam (with tools)not stated | not stated | 18.7% | — | Anthropic | Introducing Claude Haiku 5.5official · Retrieved 2026-11-12 | Vendor-reported value. table note: see the Haiku 5.5 System Card (effort not stated)transcribed from tableSource excerpt18.7%Location Table, Humanity's Last Exam (with tools) row: 18.7 |
| Humanity's Last Exam (without tools)not stated | not stated | 10.2% | $0.09Cost per attempt | Anthropic | Introducing Claude Haiku 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "Humanity’s Last Exam (no tools) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); no effort because the source effort label "max" is not in the official effort listtranscribed from textSource excerptHumanity’s Last Exam (no tools) — Accuracy vs. cost: "Haiku 4.5 · Max: 10.2% $0.09" |
| OSWorld 2.1(offline subset)not stated | not stated | 15.7% | $1.45Cost per attempt | Anthropic | Introducing Claude Haiku 5.5official · Retrieved 2026-11-12 | Vendor-reported value. A point in the figure "OSWorld 2.1 (offline subset) / Accuracy vs. cost" on the Anthropic announcement page. values were taken from each point's aria-label (DOM); the page shows them only in the figure; value for its own model (announced by Anthropic); no effort because the source effort label "max" is not in the official effort listtranscribed from textSource excerptOSWorld 2.1 (offline subset) — Accuracy vs. cost: "Haiku 4.5 · Max: 15.7% $1.45" |
| Chartography (without tools)not stated | not stated | 6.4% | — | Anthropic | Introducing Claude Haiku 5.5official · Retrieved 2026-11-12 | Vendor-reported value. table note: see the Haiku 5.5 System Card (effort not stated)transcribed from tableSource excerpt6.4%Location Table, Chartography (no tools) row: 6.4 |
Related rankings
- Overall ranking (all models, records)
- Terminal-Bench 4.0 ranking by metric (all models, records)
- GDPval-AA v2.1 ranking by metric (all models, records)
- AA-Briefcase v1.1(Elo) ranking by metric (all models, records)
- Humanity's Last Exam (with tools) ranking by metric (all models, records)
- Humanity's Last Exam (without tools) ranking by metric (all models, records)
- OSWorld 2.1(offline subset) ranking by metric (all models, records)
- Chartography (without tools) ranking by metric (all models, records)
- Recommendations by role