xAI — pricing & performance
Models served
5
of 947 tracked models
Mean output speed
192
tokens per second, averaged over
5 measured endpoints
5 measured endpoints
Mean latency
3.2s
time to first token, averaged over
5 measured endpoints
5 measured endpoints
Cheapest blended
$1.25
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on xAI
Median output tokens per second for all 5 models on xAI with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 5 of 5 models⇩
The Known Good
5 models on xAI
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
xAI: Grok 4.20
|
xAI | $1.25 | $2.50 | $1.56 | 198 | 0.3s | 2.00M |
|
xAI: Grok 4.20 Multi-Agent
|
xAI | $1.25 | $2.50 | $1.56 | 526 | 13.5s | 2.00M |
|
xAI: Grok 4.3
|
xAI | $1.25 | $2.50 | $1.56 | 65 | 0.8s | 1.00M |
|
xAI: Grok 4.5
|
xAI | $2.00 | $6.00 | $3.00 | 56 | 1.1s | 500k |
|
xAI: Grok Build 0.1
|
xAI | $1.00 | $2.00 | $1.25 | 113 | 0.3s | 256k |
The Known Good
Source. Prices, endpoint availability and throughput for xAI 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.