Mara — pricing & performance
Models served
4
of 947 tracked models
Mean output speed
121
tokens per second, averaged over
4 measured endpoints
4 measured endpoints
Mean latency
2.2s
time to first token, averaged over
4 measured endpoints
4 measured endpoints
Cheapest blended
$0.30
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Mara
Median output tokens per second for all 4 models on Mara with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 4 of 4 models⇩
The Known Good
4 models on Mara
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
DeepSeek: DeepSeek V3.1
|
DeepSeek | $0.60 | $1.70 | $0.88 | 46 | 2.5s | 131k |
MiniMax: MiniMax M2.5
|
MiniMax | $0.24 | $0.96 | $0.42 | 212 | 0.9s | 197k |
|
MiniMax: MiniMax M2.7
|
MiniMax | $0.24 | $0.96 | $0.42 | 80 | 1.8s | 197k |
OpenAI: gpt-oss-120b
|
OpenAI | $0.15 | $0.75 | $0.30 | 146 | 3.5s | 131k |
The Known Good
Source. Prices, endpoint availability and throughput for Mara 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.