Qwen3 14B
Qwen released 2025-04-28
$0.150 per million tokens, balanced
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +41.4 higher and costs 30% less ($0.105/M against $0.150/M) on this workload — and it does everything this model does.
Every price dimension
| Input | $0.120/M |
|---|---|
| Output | $0.240/M |
Independent scores
| Intelligence | 10.4 |
|---|---|
| Coding | 13.8 |
| Agentic | 1.9 |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 131K |
|---|---|
| Max output | 16K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Knowledge cutoff | 2025-03-31 |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
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...