The Known Good Updated 22 Nov 2026 Subscribe
Providers· Inference host· 4 tracked models

Unbiased — pricing & performance

Compare models All providers Data sources
Models served
4
of 1,313 tracked models
Mean output speed
61
tokens per second, averaged over
4 measured endpoints
Mean latency
2.4s
time to first token, averaged over
4 measured endpoints
Cheapest blended
$1.40
per 1M tokens at a 3:1
input:output blend
Output speed on Unbiased

Output tokens per second for all 4 models on Unbiased with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 4 of 4 models⇩
The Known Good
4 models on Unbiased
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Pareto unbiased $2.50 $7.50 $3.75 38 3.1s 262k
Pareto 26.10 unbiased $0.80 $3.20 $1.40 50 3.0s 1.05M
Pareto 26.10 Preview unbiased $0.80 $3.20 $1.40 85 1.4s 1.05M
Pareto 26.9 unbiased $2.50 $7.50 $3.75 70 2.0s 262k
The Known Good
Source. Prices, endpoint availability and throughput for Unbiased 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.