The Known Good Updated 23 Oct 2026 Subscribe
Providers· First-party endpoint· 10 tracked models

Minimax — pricing & performance

Compare models All providers Data sources
Models served
10
of 1,299 tracked models
Mean output speed
50
tokens per second, averaged over
10 measured endpoints
Mean latency
1.4s
time to first token, averaged over
10 measured endpoints
Cheapest blended
$0.000
per 1M tokens at a 3:1
input:output blend
Output speed on Minimax

Output tokens per second for all 10 models on Minimax with published throughput telemetry, the most recent figure OpenRouter publishes for each host. Higher is better. We do not run these measurements ourselves.

All 10 of 10 models⇩
79
64
63
56
54
43
43
42
36
23
The Known Good
10 models on Minimax
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
MiniMax: MiniMax M1 MiniMax $0.40 $2.20 $0.85 63 0.9s 1.00M
MiniMax: MiniMax M2 MiniMax $0.26 $1.02 $0.45 54 1.4s 205k
MiniMax: MiniMax M2-her MiniMax $0.30 $1.20 $0.53 43 0.7s 66k
MiniMax: MiniMax M2.1 MiniMax $0.30 $1.20 $0.53 42 1.7s 205k
MiniMax: MiniMax M2.5 MiniMax $0.30 $1.20 $0.53 36 1.5s 205k
MiniMax: MiniMax M2.7 MiniMax $0.30 $1.20 $0.53 43 1.2s 205k
MiniMax: MiniMax M3 MiniMax $0.30 $1.20 $0.53 79 1.2s 524k
MiniMax: MiniMax M3.1 Flash MiniMax $0.15 $0.60 $0.26 56 1.8s 1.05M
MiniMax: MiniMax M3.1 Flash (free) MiniMax $0.000 $0.000 $0.000 64 2.3s 1.00M
MiniMax: MiniMax-01 MiniMax $0.20 $1.10 $0.42 23 0.9s 1.00M
The Known Good
Source. Prices, endpoint availability and throughput for Minimax 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.