Skip to content
CostPerPrompt

Claude 3 Haiku API Pricing

Anthropic · context window 200K · prices updated 2026-09-15

Input per 1M tokens
$0.25
Output per 1M tokens
$1.25
Cached input per 1M
$0.03
88% cheaper than fresh input

Where Claude 3 Haiku sits on price

At $1.25 per million output tokens, Claude 3 Haiku is a mid tier model — 1.7× cheaper than the median output price of $2.08, which puts it cheaper than 62% and pricier than 38% of the models we track. It is the cheapest of the 27 Anthropic models we track. Output costs 5.0× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
800,000
One full context fill
$0.05
Cheaper than
62% of tracked models

Cached input is 88% 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 3 Haiku

These three workloads are the ones teams actually run on a mid-priced model — a $1.25/1M 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. $0.003 $45.00
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0014 $413
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0003 $9.37

Model your exact traffic in the API cost calculator — it preloads Claude 3 Haiku with caching and batch options.

Claude 3 Haiku price history

Claude 3 Haiku's price has not moved since we began tracking it on Aug 2, 2026 — 44 days of stability in a market where 78 of the 334 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 Aug 2, 2026; intraday moves between snapshots are not captured).

Claude 3 Haiku vs Gemini 3.5 Flash Lite (batch)

The closest-priced alternative from another vendor is Gemini 3.5 Flash Lite (batch) (Google) — priced within a rounding error on output, with $0.1 less 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 Gemini 3.5 Flash Lite (batch) pricing →

Cheaper alternatives

More Anthropic models

Frequently asked questions

How much does the Claude 3 Haiku API cost?

Claude 3 Haiku costs $0.25 per million input tokens and $1.25 per million output tokens, with cached input at $0.03 per million (88% cheaper). That works out to roughly 800,000 output tokens per dollar.

What does the support chatbot workload cost on Claude 3 Haiku?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.003 per request and $45.00 per month on Claude 3 Haiku. Conversation history re-sent each turn — the classic prompt-caching win.

What does it cost to fill Claude 3 Haiku's 200K context window?

Sending 200K of input in a single request costs $0.05 at $0.25 per million tokens — before any output. With prompt caching that same fill drops to about $0.006 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is Claude 3 Haiku worth the price?

Claude 3 Haiku sits in the middle of the market (1 of 27 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.