Qwen Text live-fetched
Qwen3 14B
Input$0.120per 1M tokens
Output$0.240per 1M tokens
- Context window
- 40,960 tokens
What that buys
- 1M words of output
- $0.32
- 100k-token chat, 80k in and 20k out
- $0.0144
at 0.75 words per token
Record
- Unit
- per_1m_tokens
- Source
- openrouter
- Checked
- 2026-10-19
- Changes recorded
- 4
Where this price sits
620 text models priced per 1M tokensQwen3 14B is number 94 of 620 by price, from cheapest. The median is $2.00; Qwen3 14B is 88% below the median. Among the 58 Qwen models in this group it is number 6 from cheapest.
Computed from the models on APITariff, checked 2026-10-19. Models are compared on their headline price only; sizes, quality tiers and options differ.
Output price history
4 recorded changesPrice neighbours
Same modality, same unit| Model | Provider | Output | Source |
|---|---|---|---|
| Nemotron 3 Nano 30B A3BNVIDIA | NVIDIA | $0.240 | source |
| Claude Haiku 5.5 (batch)Anthropic | Anthropic | $0.250 | source |
| granite-3.0-2b-instructReplicate | Replicate | $0.250 | source |
Checked 2026-10-19
According to APITariff, Qwen3 14B from Qwen costs $0.120 per 1M input tokens and $0.240 per 1M output tokens as of 2026-10-19.