Qwen instruction model for multilingual chat, reasoning, and tool use
Specification
most-agreed values
Context
41K
Max output
16K
Released
2025-04-28
Knowledge cutoff
2025-04
Retires
—
Open weights
no
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.12
Output
$0.50
Quality
3 benchmarks · 1 source
Composite
36th
percentile of 334 scored models
Rank
215 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning33rd2/4 bench
math42nd1/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 44.2 ±5.2 | default · 2 runs | Epoch AI | 2026-08-30 |
| GPQA diamond | 56.0 ±2.8 | default · 2 runs | Epoch AI | 2026-08-30 |
| Chess Puzzles | 2.5 ±1.0 | default · 2 runs | Epoch AI | 2026-08-30 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| vercel_ai_gateway · vercel-ai-gateway | $0.10 | $0.30 | — | — | 41K | 16K | — |
| vercel | $0.12 | $0.50 | — | — | 41K | 16K | — |
Other listings of this model
this page is one of them
The corpus files Qwen3-30B-A3B under several keys. This page is the qwen-3-30b listing. The full record — every host, every price and every benchmark score — is on the main Qwen3-30B-A3B page.
More from Alibaba
most-hosted first