NEWMEN
← back to all models

Mistral: Mistral Nemo

mistralai/mistral-nemo

Mistralopen-weight131K context4 providersIntelligence 54.0· est.

Cheapest provider

$0.02 / 1M

DeepInfra

Fastest provider (p95)

472 tok/s

DekaLLM

Intelligence (estimated)

54.0

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
DeepInfraq8· fp8$0.0200$0.0400321ms / 677ms43 / 62.4 tok/s99.67%99.4%
DekaLLMq8· fp8$0.0200$0.03001382ms / 5239ms9 / 472.4 tok/s97.35%98.0%
Novitaq8· fp8$0.0400$0.1700784ms / 4980ms21 / 68 tok/s71.43%96.0%
Mistralundisclosed$0.1500$0.1500291ms / 610ms77 / 132 tok/s99.74%100.0%

“—” 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 Mistral: Mistral Nemo

  • 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 Mistral: Mistral Nemo that’s currently DeepInfra at $0.02/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.