Direct API pricing comparison
Claude Sonnet 5 vs Gemini 3.5 Flash-Lite
Compare current direct API token prices and estimated monthly workload costs for Claude Sonnet 5 and Gemini 3.5 Flash-Lite.
2direct models
Pricing only.Gemini 3.5 Flash-Lite is cheaper in 4 of 4 comparable standard workload presets below. This is a pricing comparison only; it does not rank model quality.
| Model | Input | Cached | Output | Context | Max output | Source |
|---|---|---|---|---|---|---|
Claude Sonnet 5Anthropic · Direct API | $2 | $0.2 | $10 | 1M | 128K | Direct ↗ |
Gemini 3.5 Flash-LiteGoogle · Direct API | $0.3 | $0.03 | $2.5 | 1.05M | 66K | Direct ↗ |
Same workload, different API bill
These four presets use 30 active days, standard direct rates, no retries, no reasoning-token add-on, no cache writes, and the cached-input percentage shown in each row.
| Standard workload | Claude Sonnet 5 | Gemini 3.5 Flash-Lite | Lower monthly estimate |
|---|---|---|---|
| Chat10,000/day · 2,000 in · 500 out · 25% cached | $2,430 | $514.5 | Gemini 3.5 Flash-Lite by $1,915.5 / mo |
| Coding2,000/day · 12,000 in · 1,800 out · 55% cached | $1,807.2 | $379.08 | Gemini 3.5 Flash-Lite by $1,428.12 / mo |
| Agent1,200/day · 32,000 in · 2,500 out · 65% cached | $1,856.16 | $368.42 | Gemini 3.5 Flash-Lite by $1,487.74 / mo |
| Documents400/day · 180,000 in · 2,000 out · 15% cached | $3,976.8 | $620.52 | Gemini 3.5 Flash-Lite by $3,356.28 / mo |
The main calculator includes batch mode, long-context rules, retries, reasoning tokens, cache writes, and other model-specific pricing logic that a static comparison cannot fully capture.