Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for qwen

Qwen: Qwen3 14B

qwen/qwen3-14b

Model weights
Compare

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 tasks like math, programming, and logical inference, and a "non-thinking" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Modalities

In / Out Price

$0.10 / $0.22per 1M

Context

131K

Released

Apr 28, 2025

Knowledge Cutoff

Mar 2025

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), Floor (cheapest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for Qwen: Qwen3 14B (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisQwen3 14B (Non-reasoning) GPQA Diamond47.0%
Artificial AnalysisQwen3 14B (Non-reasoning) HLE4.1%
Artificial AnalysisQwen3 14B (Non-reasoning) IFBench23.9%
Artificial AnalysisQwen3 14B (Non-reasoning) τ²-Bench Telecom32.2%
Artificial AnalysisQwen3 14B (Non-reasoning) AA-LCR0.0%
Artificial AnalysisQwen3 14B (Non-reasoning) CritPt0.0%
Artificial AnalysisQwen3 14B (Non-reasoning) Terminal-Bench Hard5.3%
Artificial AnalysisQwen3 14B (Non-reasoning) AA-Omniscience Accuracy13.3%
Artificial AnalysisQwen3 14B (Non-reasoning) AA-Omniscience Non-Hallucination Rate7.7%
Artificial AnalysisQwen3 14B (Reasoning) Coding Index13.8
Artificial AnalysisQwen3 14B (Reasoning) Agentic Index0.9
Artificial AnalysisQwen3 14B (Reasoning) GPQA Diamond60.4%
Artificial AnalysisQwen3 14B (Reasoning) HLE4.5%
Artificial AnalysisQwen3 14B (Reasoning) IFBench40.5%
Artificial AnalysisQwen3 14B (Reasoning) τ²-Bench Telecom34.5%
Artificial AnalysisQwen3 14B (Reasoning) AA-LCR0.0%
Artificial AnalysisQwen3 14B (Reasoning) GDPval-AA0.0%
Artificial AnalysisQwen3 14B (Reasoning) CritPt0.0%
Artificial AnalysisQwen3 14B (Reasoning) SciCode30.7%
Artificial AnalysisQwen3 14B (Reasoning) Terminal-Bench Hard3.8%
Artificial AnalysisQwen3 14B (Reasoning) AA-Omniscience Accuracy15.3%
Artificial AnalysisQwen3 14B (Reasoning) AA-Omniscience Non-Hallucination Rate24.2%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking

Frequently asked questions

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 tasks like math, programming, and logical inference, and a "non-thinking" mode for general-purpose conversation.

Qwen3 14B costs $0.10/M input tokens and $0.22/M output tokens.

Qwen3 14B has a 131,072 token context window. It supports up to 40,960 completion tokens.

Yes. Qwen3 14B accepts tools and tool_choice for function calling on 2 of the 3 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

Qwen3 14B is served by 3 providers on OpenRouter: NextBit, DeepInfra, and Alibaba Cloud Int.. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Qwen3 14B was released on April 28, 2025. Its knowledge cutoff is March 31, 2025.