Qwen3 14B

Provider: Alibaba (Qwen) CN

Input price
$0.10
/ 1M tokens
Output price
$0.22
/ 1M tokens
Context
41K tokens
Max output 16K tokens

Overview

Alibaba's Qwen3 14B is a mid-tier dense 14.8B parameter model built for efficient dialogue and complex reasoning. It features a 40960-token context window with a 36864-token max output limit and no free tier.

Strengths

  • Dense 14.8B parameter architecture
  • Supports native function-calling and json-mode
  • Includes a dedicated thinking mode
  • Knowledge cutoff of March 2025

Best use cases

  • Structured data extraction tasks
  • Tool-integrated agent execution loops
  • Multi-step complex reasoning workloads
  • General conversational application backends

Pricing position

Priced at $0.10/M input and $0.22/M output, matching the input cost of GPT-5.4 Nano while offering a cheaper output rate.

Caveats

Context window is limited to 40960 tokens, significantly smaller than the 1M+ token capacity found on Flash or Scout variants.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
16K tokens
Knowledge cutoff
2025-03-31
Listed on OpenRouter
2025-04-28
Tracked since
2026-05-08
Last updated
2026-11-12

Features

Function callingJSON outputReasoning

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.02
1M (small app) 1 0.5 $0.21
10M (mid scale) 10 5 $2.10
100M (large) 100 50 $21.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3-14b)