Choosing between Claude Haiku 4.5 (Anthropic) and Gemini 2.5 Flash (Google)? This is a side-by-side of their API pricing, context windows, and real cost on a sample workload — so you can pick on the numbers, not the marketing.
Claude Haiku 4.5 vs Gemini 2.5 Flash: pricing & specs
| Claude Haiku 4.5 | Gemini 2.5 Flash | |
|---|---|---|
| Vendor | Anthropic | |
| Input / 1M tokens | $1.00 | $0.30 |
| Output / 1M tokens | $5.00 | $2.50 |
| Cached input / 1M | $0.10 | — |
| Context window | 200K tokens | 1M tokens |
Gemini 2.5 Flash: Text/image/video input; audio input is billed higher.
Cost example: 1M input + 1M output tokens
For a workload of 1M input plus 1M output tokens, Claude Haiku 4.5 costs $6.00 and Gemini 2.5 Flash costs $2.80 — Gemini 2.5 Flash is about 53% cheaper on this mix. Your real ratio of input to output tokens shifts the math; plug in your own numbers with the token cost calculator.
Which should you choose?
- Lower cost: Gemini 2.5 Flash is cheaper on output tokens ($2.50 vs $5.00 / 1M), which usually dominates spend on generation-heavy workloads.
- Larger context window: Gemini 2.5 Flash fits more in one prompt (1M tokens) — better for long documents or big RAG context.
- Ecosystem: pick the provider whose SDK, rate limits, and tooling fit your stack — see Anthropic rate limits and Google rate limits.
Full specs: Claude Haiku 4.5 · Gemini 2.5 Flash. Thinking of switching providers? See the migration guides.
Prices as of June 2026 and change often — verify before relying on them.