NEWMEN
← back to all models

Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507

Alibaba (Qwen)open-weight262K context12 providersIntelligence 71.0· est.

Cheapest provider

$0.07 / 1M

DeepInfra

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (estimated)

71.0

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$0.0710$0.100093.31%
Novitaq8· fp8$0.0900$0.580099.98%
Parasailq8· fp8$0.1000$0.600099.90%
WandBfull· bf16$0.1000$0.100099.96%
Alibabaundisclosed$0.1495$0.5980100.00%
AtlasCloudq8· fp8$0.2000$0.880099.94%
Friendliundisclosed$0.2000$0.800093.90%
Togetherundisclosed$0.2000$0.600095.55%
Googleundisclosed$0.2200$0.880099.66%
Googleundisclosed$0.2500$1.000099.93%
StreamLakeundisclosed$0.2800$1.120091.87%
Cerebrasfull· fp16$0.6000$1.2000100.00%

“—” 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 Qwen: Qwen3 235B A22B Instruct 2507

  • 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 Qwen: Qwen3 235B A22B Instruct 2507 that’s currently DeepInfra at $0.07/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.