Claude Haiku 5.5 API Pricing
Anthropic · context window 1M · prices updated 2026-10-24
Where Claude Haiku 5.5 sits on price
At $0.5 per million output tokens, Claude Haiku 5.5 is a mid tier model — 4.4× cheaper than the median output price of $2.20, which puts it cheaper than 81% and pricier than 19% of the models we track. It sits 2th cheapest of the 30 Anthropic models we track. Output costs 5.0× input, the usual spread — trim both, starting with the answer length.
Cached input is 90% cheaper. On an input-heavy workload you need roughly a 28% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on Claude Haiku 5.5
These three workloads are the ones teams actually run on a mid-priced model — a $0.5/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.0012 | $18.00 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.0006 | $165 |
| Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. | $0.027 | $162 |
Model your exact traffic in the API cost calculator — it preloads Claude Haiku 5.5 with caching and batch options.
Claude Haiku 5.5 price history
Claude Haiku 5.5's price has not moved since we began tracking it on Oct 8, 2026 — 16 days of stability in a market where 101 of the 369 models we track have repriced over the same period. Anthropic's lineup has held steady across the board.
Change-points from our daily price snapshots (tracking since Oct 8, 2026; intraday moves between snapshots are not captured).
Claude Haiku 5.5 vs Qwen3 30B A3B
The closest-priced alternative from another vendor is Qwen3 30B A3B (Alibaba (Qwen)) — priced within a rounding error on output, with $0.02 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Qwen3 30B A3B pricing →Cheaper alternatives
More Anthropic models
Frequently asked questions
› How much does the Claude Haiku 5.5 API cost?
Claude Haiku 5.5 costs $0.1 per million input tokens and $0.5 per million output tokens, with cached input at $0.01 per million (90% cheaper). That works out to roughly 2,000,000 output tokens per dollar.
› What does the support chatbot workload cost on Claude Haiku 5.5?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0012 per request and $18.00 per month on Claude Haiku 5.5. Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill Claude Haiku 5.5's 1M context window?
Sending 1M of input in a single request costs $0.1 at $0.1 per million tokens — before any output. With prompt caching that same fill drops to about $0.01 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Claude Haiku 5.5 worth the price?
Claude Haiku 5.5 sits in the middle of the market (2 of 30 by price within Anthropic). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.