What Claude Haiku costs per coding task
Claude Haiku 4.5 and 5.5 priced per modelled coding task. Useful for subagents and exploration.
List prices per million tokens
| Model | Input | Output | Cache write | Cache read |
|---|---|---|---|---|
| Claude Haiku 4.5 | $1 | $5 | $1.25 | $0.1 |
| Claude Haiku 5.5 | $0.1 | $0.5 | $0.125 | $0.01 |
First-party API list prices as of 2026-11-09. Cache write is the 5-minute write; OpenAI models have no write premium.
Claude Haiku 4.5 per task
Worked example · modelled, not measured| Task | Calls | Tidy | Messy |
|---|---|---|---|
| pull request | 38 | $0.45 | $0.58 |
| bug fix | 26 | $0.25 | $0.35 |
| refactor | 55 | $0.91 | $1.10 |
| test suite | 44 | $0.70 | $0.87 |
| migration | 80 | $1.58 | $1.84 |
| ticket | 32 | $0.35 | $0.46 |
Claude Haiku 5.5 per task
Worked example · modelled, not measured| Task | Calls | Tidy | Messy |
|---|---|---|---|
| pull request | 38 | $0.05 | $0.06 |
| bug fix | 26 | $0.03 | $0.03 |
| refactor | 55 | $0.09 | $0.11 |
| test suite | 44 | $0.07 | $0.09 |
| migration | 80 | $0.16 | $0.18 |
| ticket | 32 | $0.03 | $0.05 |
Which one should you use?
Per token, the top tier costs more, but a stronger model can finish in fewer calls and with fewer retry loops, and the number of calls drives the bill. Compare cost per finished task, not per token: itemize a few of your own sessions on each model and look at the receipts side by side.
Itemize your own session
Drop a Claude Code or Codex log. It is parsed in your browser, and you get your real numbers instead of a model.
Drop a session log here
Claude Code ~/.claude/projects/…/*.jsonl, a Codex rollout ~/.codex/sessions/…/rollout-*.jsonl, or the claude-code-action execution file.
Parsed in your browser. Your prompts and code never leave this tab.