Claude Haiku 3
Pricing & Specs
Anthropic · $0.25 input / $1.25 output per 1M tokens · 200K context window
The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on Claude Haiku 3 costs about $0.0009 — roughly $0.88 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.
Claude Haiku 3 API Pricing
| Tokens | Price |
|---|---|
| Input | $0.25 / 1M tokens |
| Output | $1.25 / 1M tokens |
| Cached input | $0.03 / 1M tokens |
50% discount available for batch API requests. Batch API pricing is available for this model at 50%. Cache writes and cache hits or refreshes are billed separately.
What that means in practice
Claude Haiku 3 Specs
| Spec | Value |
|---|---|
| Context window | 200K tokens |
| Max output tokens | 4.096K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Latency (measured by OpenMark) | ~494ms median response |
| Reasoning model | No |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | Yes |
Capabilities
FAQ
How much does Claude Haiku 3 cost?
Claude Haiku 3 costs $0.25 per 1M input tokens and $1.25 per 1M output tokens ($0.03 per 1M cached input tokens).
What is Claude Haiku 3's context window?
Claude Haiku 3 has a 200K-token context window. Maximum output is 4.096K tokens.
Can I test Claude Haiku 3 on my own task?
Yes. OpenMark lets you benchmark Claude Haiku 3 against 100+ models on your own task with real API calls — no API keys needed, free tier available.
Is Claude Haiku 3 the right model for YOUR task?
Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.