Directory · Model comparison
Claude Haiku 4.5 vs Gemini 3.5 Flash
Side-by-side API economics and benchmarks. Per-1M input and output rates, context window, and verified metrics.
Tale of the tape
Head-to-head specs pulled from each model profile.
| Metric | Claude Haiku 4.5 | Gemini 3.5 Flash |
|---|---|---|
| Input cost / 1M | $1.00 | $1.50 |
| Output cost / 1M | $5.00 | $9.00 |
| Context window | 200,000 tokens | 1,048,576 tokens |
| MMLU score | — | — |
Cost verdict
Enter monthly input and output volumes to see total cost savings.
Claude Haiku 4.5
- Input: 1M × $1.00 = $1.00
- Output: 1M × $5.00 = $5.00
- Total
- $6.00
Gemini 3.5 Flash
- Input: 1M × $1.50 = $1.50
- Output: 1M × $9.00 = $9.00
- Total
- $10.50
Total cost savings
$4.50
Claude Haiku 4.5 saves $4.50 per month vs the other model at this volume.
Model routing savings
Uses this page's verified rates. Gemini 3.5 Flash is the premium route (higher combined per-1M cost); Claude Haiku 4.5 handles routine traffic.
All premium
Gemini 3.5 Flash
$525.00
100% of input and output on the premium route
Routed stack
80% → Claude Haiku 4.5
20% → Gemini 3.5 Flash
$345.00
- Routine slice
- $240.00
- Premium slice
- $105.00
Monthly savings
$180.00
34.3% lower
Rates pulled from this page's model database entries (gemini-3-5-flash, claude-haiku-4-5) — same per-1M input/output figures as Tale of the tape. Production routing needs quality gates and monitoring.
Related comparisons
More head-to-head model matchups.