Claude Haiku 5.5 — pricing, limits & comparison
Generated 2026-11-03 03:53 UTC · JSON
Claude Haiku 5.5 scores 76.5 for agentic coding (LLM model APIs). Agent-friction 90/100.
Pricing
| Plan | Base / mo | Included | Overage |
|---|---|---|---|
| API (per-token) | $0 | — | $0.10/1 input_mtok, $0.50/1 output_mtok |
Cost at scale — LLM model APIs
| Coding (50M in / 10M out) | Bulk extract (100M in / 5M out) |
|---|---|
| $10 | $12.50 |
Agent-friction breakdown — 90/100
| Check | Points | Pass |
|---|---|---|
| Test credentials without a credit card | 20 | ✓ |
| Sandbox or test mode | 15 | ✓ |
| Setup with no human-only steps | 15 | ✓ |
| Official CLI | 10 | × |
| Official MCP server | 10 | ✓ |
| Markdown docs, current with the SDK | 10 | ✓ |
| Typed SDK for main languages | 10 | ✓ |
| Error messages that name the fix | 10 | ✓ |
Official SDKs
TypeScript (@anthropic-ai/sdk) · Python (anthropic) · Go (github.com/anthropics/anthropic-sdk-go) · Java (com.anthropic) · Ruby (anthropic)
Health & reliability — 100/100
| Incidents (90 days) | 0 · status page |
| Changelog entries (90 days) | 1 |
| Deprecations (90 days) | 0 |
| Downloads trend | +7.5% (@anthropic-ai/sdk on npm) |
| Last release | 2026-11-02 |
| Ownership events (90 days) | 0 |
Sources: www.npmjs.com · status.claude.com. Captured 2026-11-02.