QQwen · Released Apr 28, 2025
Qwen3 30B A3B
Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
- Released
- Apr 28 2025
- Context window
- 41K 16K out
- Input / 1M tokens
- $0.12 from $0.051
- Output / 1M tokens
- $0.50 from $0.28
Where to run it
13 providers compared
Cheapest: Cloudflare Workers AI at $0.051 / $0.34 per 1M input / output tokens — 65% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Cloudflare Workers AI | $0.051 | $0.34 | — | 33K | 33K | — | Cheapest |
| Helicone | $0.08 | $0.29 | — | 41K | 41K | — | +9% |
| LLM Gatewayno tool calling | $0.095 | $0.28 | — | 8K | 4K | — | +17% |
| DevPass (LLM Gateway) | $0.095 | $0.28 | — | 33K | 16K | — | +17% |
| NanoGPTno tool calling | $0.10 | $0.30 | $0.05 | 41K | 33K | — | +23% |
| Jiekou.AIno tool calling | $0.09 | $0.45 | — | 41K | 20K | — | +48% |
| Qiniu | $0.11 | $0.43 | — | 40K | 4K | — | +56% |
| DeepInfraFP8 | $0.12 | $0.50 | — | 41K | 16K | 100%24h | +76% |
| Kilo Gateway | $0.12 | $0.50 | — | 41K | 16K | — | +76% |
| Vercel AI Gateway | $0.12 | $0.50 | — | 41K | 16K | — | +76% |
| Hugging Face | $0.12 | $0.50 | — | 41K | 16K | — | +76% |
| Merge Gateway | $0.11 | $1.08 | $0.022 | 131K | 33K | — | +187% |
| 302.AI | $0.11 | $1.08 | — | 128K | 8K | — | +189% |
Value
Price vs. performance
Qwen3 30B A3B Other Qwen Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
5 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Lech Mazur WritingWriting & content · Short stories weaving 10 required elements, judged 0–10 | 7.53/10 | #17of 27 | GPT-58.60/10 |
| Fiction.LiveBenchWriting & content · Understanding long creative writing (16k tokens) | 40.6% | #21of 24 | GPT-597.2% |
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 61.7% | #92of 122 | Gemini 4 Argon96.4% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 15.8% | #108of 123 | Claude Sonnet 5.568.3% |
| OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 | 62.8% | #89of 120 | Gemini 4 Argon100.0% |
Specs
Details
- Model ID
qwen/qwen3-30b-a3b- Developer
- Qwen
- Release date
- Apr 28, 2025 ·
- Context window
- 40,960 tokens
- Max output
- 16,384 tokens
- API price
- $0.12 / $0.50 per 1M input / output tokens
- Providers
- 13
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.