Qwen3 14B
- Input / output
- $0.096 / $0.192
- Providers
- 2
- Spread
- 1.88×
- 7 days
- −7.7%
- 30 days
- −7.7%
- Context
- 40K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp8 | $0.096 | $0.192 | $0.12 | ref | |||
| int4 | $0.10 | $0.22 | $0.13 | +8.3% | |||
| fp8 | $0.12 | $0.24 | $0.15 | +25% | |||
DeepInfrafp8/priority fp8 | $0.18 | $0.36 | $0.225 | +88% |
- DeepInfraCheapestfp8/flex$0.12$0.096 in · $0.192 outref vs ref40K ctx100% uptimefp8
- $0.13$0.10 in · $0.22 out+8.3% vs ref40K ctx100% uptimeint4
- $0.15$0.12 in · $0.24 out+25% vs ref40K ctx97.6% uptimefp8
- fp8/priority$0.225$0.18 in · $0.36 out+88% vs ref40K ctx99.5% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.12 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Changes
About
The cheapest provider for Qwen3 14B is DeepInfra at $0.12 per 1M tokens (blended), charging $0.096 per 1M input and $0.192 per 1M output tokens. 2 providers serve it; the most expensive charges 1.88× the typical price. Its best price fell 7.7% over the last 30 days. Context window: 40K tokens. Prices tracked since Oct 3, 2026.
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
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3-14b-04-28
- Weights
- Qwen/Qwen3-14B