Specs
On paper
| Claude Sonnet 4.6 | Gemini 3.1 Pro | |
|---|---|---|
| Modality | Chat | Chat |
| Context | 200K | 1M |
| Max output | 8K | 8K |
| Price | $0.034typical | $0.025typical |
| Metered input | $3.36/M tok | $2.24/M tok |
| Metered output | $16.80/M tok | $13.44/M tok |
| Providers | 1 | 1 |
| Streaming | ||
| JSON mode | ||
| Tool calling |
Live performance
On our traffic
Each curve is one model, measured on the same network, the same days.
Response latencymedian per day
Collecting live data — a point is recorded for every day of traffic.
Output speedtokens / second
Collecting live data — a point is recorded for every day of traffic.
Uptimesuccessful of gradable
Collecting live data — a point is recorded for every day of traffic.
Requests / dayvolume served
Collecting live data — a point is recorded for every day of traffic.
Claude Sonnet 4.6Gemini 3.1 Pro
Run both. Route to the winner.
One key serves every model here — swap the model string, keep your code.
Get an API key