Comparison · 2026-05-12
Gemini 2.5 Flash vs Claude Haiku 4.5 (latest)
Side-by-side comparison of pricing, context window and capabilities for Gemini 2.5 Flash (Google) and Claude Haiku 4.5 (latest) (Anthropic). Focus: cheap vs premium.
| Gemini 2.5 Flash | Claude Haiku 4.5 (latest) | |
|---|---|---|
| Vendor | Anthropic | |
| Input price / 1M tokens | $0.300 | $1.00 |
| Output price / 1M tokens | $2.50 | $5.00 |
| Total per 1M (in + out) | $2.80 | $6.00 |
| Context window | 1.05M | 200K |
| Max output tokens | 66K | 64K |
| Tool calling | ✓ Yes | ✓ Yes |
| Structured output | ✓ Yes | Unknown |
| Reasoning | ✓ Yes | ✓ Yes |
| Vision input | ✓ Yes | ✓ Yes |
| Open weights | ✗ No | ✗ No |
| Provider availability | 21 providers | 18 providers |
| Release date | 2025-06-17 | 2025-10-15 |
| Knowledge cutoff | 2025-01 | 2025-02-28 |
Quick takeaway
- Gemini 2.5 Flash is 2.1× cheaper per 1M tokens (input + output combined).
- Gemini 2.5 Flash has a larger context window (1.05M vs 200K).
- Only Gemini 2.5 Flash supports structured output / JSON mode.
- Gemini 2.5 Flash is more widely available across providers (21 vs 18).
Last updated:
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.