Anthropic: Claude Haiku 4.5 (batch) API Pricing
Anthropic: Claude Haiku 4.5 (batch) costs $0.500 per 1M input tokens and $2.50 per 1M output tokens (cache reads: $0.050). Context window: 200K. Prices verified 2026-10-21 · source
Alternatives to consider
97% cheaper with nearly identical quality (20.1 vs 16.9)
+21.1 quality points for 5% more
Cheapest anthropic model — 90% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
From our own daily snapshot archive — independent of provider announcements.
Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $0.500 | — |
| Cache read | $0.050 | −90% |
| Cache write (5m) | $0.625 | +25% |
| Cache write (1h TTL) | $1.00 | +100% |
| Output | $2.50 | — |
| Web search tool | $10/1k searches | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
Higher effort = deeper thinking = more reasoning tokens billed as output.
What would Anthropic: Claude Haiku 4.5 (batch) cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $14.00 |
| Coding agent | 5,000 | 8,000 / 2,000 | $45.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $97.50 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $25.00 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About Anthropic: Claude Haiku 4.5 (batch)
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Compare Anthropic: Claude Haiku 4.5 (batch) with
- 4.5 (batch) vs OpenAI: GPT-5.6 Terra Pro
- 4.5 (batch) vs Anthropic: Claude Fable 5
- 4.5 (batch) vs Anthropic: Claude Opus 5
- 4.5 (batch) vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does Anthropic: Claude Haiku 4.5 (batch) cost?
Anthropic: Claude Haiku 4.5 (batch) costs $0.500 per 1M input tokens and $2.50 per 1M output tokens; cached input tokens cost $0.050 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
200K tokens, with up to 64K output tokens per response. That's roughly 250 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.050/1M, about 90% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
ScaleDown: Summarize saves about 97% on a typical workload with comparable quality.
Official resources
- Anthropic: Claude Haiku 4.5 (batch) on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- Anthropic model docs → — first-party model specifications and limits.
- LMArena leaderboard → — independent human-preference rankings.
- Shred your current bill — paste a CSV and see if switching saves money.