Alibaba Qwen
Qwen3 Max
Released Sep 24, 2025 · 92B tokens this week · 3 providers
Overview
Alibaba's largest Qwen, a trillion-parameter-class mixture-of-experts served through hosted APIs. Excellent multilingual coverage, particularly across Asian languages, and competitive on agentic benchmarks. The top of the Qwen range for general quality.
Providers
Reference data — not yet measured from live traffic
| PROVIDER | MAX OUT | OUTPUT /M | QUANT | |||||
|---|---|---|---|---|---|---|---|---|
Together AICheapest | 262K | 33K | $1.20 | $6.00 | 195ms | 92 | 99.40% | Full |
Fireworks AI | 262K | 33K | $1.30 | $6.48 | 600ms | 105 | 99.50% | Full |
Novita AI | 262K | 33K | $1.34 | $6.72 | 700ms | 84 | 98.60% | Full |
Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.
Price comparison
Blended $ per 1M tokens
Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.
Call it
OpenAI-compatible — swap the base URL and go
curl https://model.cards/api/v1/chat/completions \
-H "Authorization: Bearer $MODELCARDS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3-max",
"messages": [
{ "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
]
}'