NEWMEN
← back to all models

MiniMax: MiniMax M2.5

minimax/minimax-m2.5

MiniMaxopen-weight205K context17 providersIntelligence 72.0· est.

Cheapest provider

$0.15 / 1M

AkashML

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (estimated)

72.0

Family + generation + popularity + price tier

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
AkashMLq8· fp8$0.1500$1.150099.19%
Chutesq8· fp8$0.1500$1.2000100.00%
DeepInfraq8· fp8$0.1500$1.150099.99%
Phalaundisclosed$0.2000$1.3800100.00%
Inceptronq8· fp8$0.2400$0.900098.18%
Baiduq8· fp8$0.2700$1.0800100.00%
AtlasCloudq8· fp8$0.2950$1.200098.13%
Friendliundisclosed$0.3000$1.2000
Maraundisclosed$0.3000$1.2000100.00%
Minimaxq8· fp8$0.3000$1.200097.33%
Novitaq8· fp8$0.3000$1.2000
Parasailq8· fp8$0.3000$1.2000100.00%
SiliconFlowq8· fp8$0.3000$1.2000
StreamLakeundisclosed$0.3000$1.2000
WandBq8· fp8$0.3000$1.2000
Veniceundisclosed$0.3400$1.1900
Minimaxq8· fp8$0.6000$2.4000

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence estimate

No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.

Want a curated score? File a benchmark report and we’ll add it to the next sync.

How Atlas routes MiniMax: MiniMax M2.5

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For MiniMax: MiniMax M2.5 that’s currently AkashML at $0.15/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.