Skip to content
NewTry RouterPlus with free creditsTry playground →
RouterPlus
Book a demo

Qwen3 14B API

Open in consoleI need inference
  • 131KContext
  • 8.2KMax output
  • $0.2275/ $0.91From, per 1M in / out
  • 1Provider
Providers
  • Inference.net

Pricing

ProviderInput / 1MCached / 1MOutput / 1M
Inference.net$0.2275–$0.91

USD, as of October 27, 2026. Live prices

Cost

WorkloadInference.net
1,000 chat replies2K in, 500 out each$0.91
1,000 agent tasks50K in, 5K out each$15.93
Monthly batch job500M in, 50M out$159.25

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-14b",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

FAQ

How much does the Qwen3 14B API cost?

On RouterPlus, Qwen3 14B costs $0.2275 per million input tokens and $0.91 per million output tokens at Inference.net, the lowest listed prices and the provider where routing starts. Prices as of October 27, 2026.

Which providers serve Qwen3 14B?

Inference.net serves Qwen3 14B on RouterPlus today.

What is the Qwen3 14B model ID?

Use "qwen/qwen3-14b" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.

What is the Qwen3 14B context window?

131K tokens of context and up to 8.2K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.

Is Qwen3 14B open weights?

Yes. Qwen publishes Qwen3 14B as an open-weight model, which is why several independent providers can host it.

Do any Qwen3 14B providers retain prompts?

None of the 1 providers serving Qwen3 14B on RouterPlus list prompt retention.

Can I reserve capacity for Qwen3 14B?

Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.

More Qwen

All Qwen modelsAll models

Need Qwen3 14B at volume?

Open in consoleI need inference