Alibaba Qwen

Qwen3 32B

131K ctxText Tools Reasoning

Released Apr 29, 2025 · 54B tokens this week · 4 providers

Overview

A dense 32B Qwen that fits comfortably on two GPUs. Balanced quality across chat, translation and code at a very low hosted price. A good fine-tuning base when you need predictable dense-model behaviour.

translationprogrammingroleplay

Providers

Reference data — not yet measured from live traffic

PROVIDER		MAX OUT		OUTPUT /M				QUANT
DeepInfraCheapest	131K	33K	$0.10	$0.30	380ms	145	98.90%	fp8
Novita AI	131K	33K	$0.11	$0.32	420ms	125	98.50%	fp8
Groq	33K	33K	$0.12	$0.34	209ms	660	99.80%	Full
Cerebras	66K	33K	$0.12	$0.36	180ms	1700	99.60%	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

Qwen3 32B$0.25

DeepSeek V3.2$0.37

Gemini 3 Flash$1.95

GPT-5.2$10.94

Claude Sonnet 4.5$12.00

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/qwen3-32b",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'