Qwen3 14B
Qwen instruction model for multilingual chat, reasoning, and tool use
Cheapest input
$0.06
$/MTok · LiteLLM
Cheapest output
$0.24
$/MTok
Context
131K
tokens
Offers
6
3 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| LiteLLMcheapestQwen/Qwen3-14B | — | $0.06 | $0.24 | $0.006 | — |
| models.devQwen/Qwen3-14B | SiliconFlow (China) | $0.07 | $0.28 | $0 | 131K |
| models.devQwen/Qwen3-14B | SiliconFlow | $0.07 | $0.28 | $0 | 131K |
| models.devqwen/qwen3-14b | NanoGPT | $0.08 | $0.24 | $0 | 41K |
| models.devqwen/qwen3-14b | Kilo Gateway | $0.2275 | $0.91 | $0 | 131K |
| OpenRouterqwen/qwen3-14b | OpenRouter | $0.2275 | $0.91 | $0 | 131K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2025-03-31Released: 2025-04-28Family: qwen
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence10.4
- AA coding13.8
- AA agentic1.8
Sources: Arena AI, Artificial Analysis. See /benchmarks.