Upstage — pricing & performance
Models served
3
of 1,191 tracked models
Mean output speed
69
tokens per second, averaged over
3 measured endpoints
3 measured endpoints
Mean latency
1.1s
time to first token, averaged over
3 measured endpoints
3 measured endpoints
Cheapest blended
$0.087
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Upstage
Output tokens per second for all 3 models on Upstage with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.
All 3 of 3 models⇩
The Known Good
3 models on Upstage
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
Upstage: Solar Mini 4
|
Upstage | $0.050 | $0.20 | $0.087 | 57 | 2.2s | 524k |
|
Upstage: Solar Pro 3
|
Upstage | $0.15 | $0.60 | $0.26 | 95 | 0.3s | 131k |
|
Upstage: Solar Pro 4
|
Upstage | $0.090 | $0.36 | $0.16 | 55 | 0.9s | 524k |
The Known Good
Source. Prices, endpoint availability and throughput for Upstage are ingested from OpenRouter;
model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint —
it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this
site; see methodology. Quality scores are not provider-specific:
a model scores the same wherever it is hosted, so quality lives on the
model pages.