QQwen · Released Apr 28, 2025
Qwen3 14B
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
- Released
- Apr 28 2025
- Context window
- 41K 16K out
- Input / 1M tokens
- $0.12 from $0.07
- Output / 1M tokens
- $0.24 from $0.22
Where to run it
10 providers compared
Cheapest: LLM Gateway, DevPass (LLM Gateway) at $0.076 / $0.23 per 1M input / output tokens — 81% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| LLM Gateway | $0.076 | $0.23 | — | 16K | 8K | — | Cheapest |
| DevPass (LLM Gateway) | $0.076 | $0.23 | — | 33K | 33K | — | Cheapest |
| NanoGPT | $0.08 | $0.24 | $0.04 | 41K | 33K | — | +5% |
| SiliconFlow | $0.07 | $0.28 | — | 131K | 131K | — | +7% |
| NextBitINT4 · no tool calling | $0.10 | $0.22 | — | 41K | 37K | 99.7%24h | +14% |
| SiliconFlow (China) | $0.075 | $0.30 | — | 131K | 131K | — | +15% |
| DeepInfraFP8 | $0.12 | $0.24 | — | 41K | 16K | 100%24h | +32% |
| Kilo Gateway | $0.12 | $0.24 | — | 41K | 16K | — | +32% |
| Alibaba (China) | $0.14 | $0.57 | — | 131K | 8K | — | +121% |
| Alibaba | $0.35 | $1.40 | — | 131K | 8K | — | +437% |
Value
Price vs. performance
Qwen3 14B 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
6 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| SciCodeSoftware engineering · Research-coding problems from the natural sciences | 31.6% | #94of 102 | Claude Opus 5.566.9% |
| Fiction.LiveBenchWriting & content · Understanding long creative writing (16k tokens) | 62.5% | #15of 24 | GPT-597.2% |
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 63.8% | #91of 122 | Gemini 4 Argon96.4% |
| CritPtReasoning & knowledge · Open-ended, research-level physics problems | 0.0% | #92of 111 | GPT-5.6 Sol32.3% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 18.2% | #97of 123 | Claude Sonnet 5.568.3% |
| OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 | 66.4% | #86of 120 | Gemini 4 Argon100.0% |
Specs
Details
- Model ID
qwen/qwen3-14b- Developer
- Qwen
- Release date
- Apr 28, 2025 ·
- Context window
- 40,960 tokens
- Max output
- 16,384 tokens
- API price
- $0.12 / $0.24 per 1M input / output tokens
- Providers
- 10
- 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.