Qwen 3 14B API

Alibaba's Qwen 3 14B, through an OpenAI-compatible API. 2 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send qwen3-14b as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: qwen3-14b
Maker: Alibaba
Context window: 16.4K · 32.8K tokens
Input price: $0.087 to $0.087 per million tokens
Output price: $0.0048 to $0.262 per million tokens
Providers: 2 independent providers
Regions: eu-central, us

Providers

Pera: us, $0.087 input and $0.0048 output per million tokens, $0.087 cache read per million tokens, $0.000079 fee for each request, 32.8K tokens of context
Greenference: eu-central, $0.087 input and $0.262 output per million tokens, $0.044 cache read per million tokens, 16.4K tokens of context

Scores

HLE: 4.1, #226 of 273
GPQA: 47.0, #218 of 250
AA-LCR: 0.0, #231 of 237
Terminal-Bench Hard: 5.3, #144 of 166
LiveCodeBench: 28.0, #95 of 130
AIME 2025: 58.0, #42 of 100
MMLU-Pro: 67.5, #100 of 133
τ²-Bench: 32.2, #133 of 169
IFBench: 23.9, #171 of 178
SimpleQA Verified: 20.3, #93 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-14b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwen 3 14B?: Qwen 3 14B is a model from Alibaba.
How much does Qwen 3 14B cost?: Offers now ask $0.087 to $0.087 per million input tokens and $0.0048 to $0.262 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Qwen 3 14B?: The largest offer takes 32,768 input tokens. One job can generate up to 16,384 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Qwen 3 14B do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Qwen 3 14B support?: Text → Text.
Which providers serve Qwen 3 14B?: 2 independent providers quote it now, with 2 offers. The table above ranks them by the cost of a typical job.
How do I call Qwen 3 14B?: Send "qwen3-14b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwen 3 14B listed?: The exchange first listed it on 10/8/2026. This is not its release date.