Specs
On paper
| GPT-OSS 120B | Claude Haiku 4.5 | |
|---|---|---|
| Modality | Chat | Chat |
| Context | 131K | 200K |
| Max output | 131K | 4K |
| Price | $0.002typical | $0.011typical |
| Metered input | $0.30/M tok | $1.15/M tok |
| Metered output | $0.75/M tok | $5.60/M tok |
| Providers | 5 | 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.
GPT-OSS 120BClaude Haiku 4.5
Run both. Route to the winner.
One key serves every model here — swap the model string, keep your code.
Get an API key