Claude Haiku 3.5 API Pricing

Anthropic — status + migration path, stamped 2026-09-07.

Retired. Retired on the Claude API (still on Bedrock + Google Cloud).
Input per 1M tokens$0.8
Output per 1M tokens$4
Cache read per 1M tokens
Statusretired
Sourceofficial pricing page · verified 2026-09-07

Example costs

  • One request (2,000 in / 500 out): $0.0036
  • 100K such requests/month: $360
  • 1M input + 1M output tokens: $4.8

Compare against other models →

How Claude Haiku 3.5 compares on rate

Claude Haiku 3.5 runs $0.8 input / $4 output per MTok — a combined $4.8 for 1M tokens each way. The cheapest active model in our table, Gemini 2.5 Flash-Lite at $0.1/$0.4 (combined $0.5), is about 90% cheaper on combined rate (verified 2026-09-07).

Per-token rate is not per-task cost — tokenizers differ between model families, so benchmark with your own payloads before switching.

What real volumes cost at Claude Haiku 3.5 rates

Straight rate-card math at the verified $0.8/$4 per-MTok prices, assuming a 75% input / 25% output token split — no caching or batch discounts applied.

VolumeSplitCost at Claude Haiku 3.5 rates
100K tokens in a day75,000 in + 25,000 out$0.1600
That pace over a 30-day month (3M tokens)2.25M in + 750K out$4.80
1M tokens in a month750,000 in + 250,000 out$1.60
Heavy month — 12M tokens9M in + 3M out$19.20

Change the split or volume in the calculator — same verified rates, your numbers. Method + the corrections that make estimates real: how to estimate LLM API costs.

Frequently asked questions

What does Claude Haiku 3.5 cost per million tokens?

Claude Haiku 3.5 costs $0.8 per 1M input tokens and $4 per 1M output tokens on the Anthropic API (verified 2026-09-07).

How much does 100K tokens a day cost on Claude Haiku 3.5?

At a 75% input / 25% output split, 100K tokens costs about $0.1600 at Claude Haiku 3.5 rates — about $4.80 over a 30-day month. That is straight rate-card math, before any caching or batch discounts.

Is there a cheaper model than Claude Haiku 3.5?

Yes — the cheapest active model we track is Gemini 2.5 Flash-Lite at $0.1/$0.4 per MTok, a combined $0.5 against Claude Haiku 3.5's $4.8 — about 90% less on combined rate (verified 2026-09-07). Tokenizers differ between families, so benchmark per-task cost with your own payloads.

Is Claude Haiku 3.5 still available?

Claude Haiku 3.5 is retired. Retired on the Claude API (still on Bedrock + Google Cloud). The prices shown are its last verified list rates (2026-09-07).

Related models