qwen Open weights Reasoning

Qwen3 14B pricing & benchmarks

Released Apr 28, 2025 · served by 3 providers

Input / 1M tokens$0.100
Output / 1M tokens$0.240
Context window131K
Cached input
Intelligence index10.4
Coding index13.8
Agentic index1.8
1M in + 300K out$0.17

What Qwen3 14B is

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...

Providers and prices for Qwen3 14B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
NextBitcheapest $0.100 $0.240 41K int4 99.7%
DeepInfra $0.120 $0.240 41K fp8 99.9%
Alibaba $0.228 $0.910 131K 95.1%

Cheaper models in the same class

Models scoring within 4 points of Qwen3 14B on the Intelligence Index, but with a lower output price.

FAQ

How much does the Qwen3 14B API cost?

$0.100 per 1M input tokens and $0.240 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.17.

Is Qwen3 14B free?

No. It is a paid model starting at $0.100 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3 14B?

NextBit at $0.100 input / $0.240 output per 1M tokens (int4 quantization).

Can I self-host Qwen3 14B?

Yes — weights are published as Qwen/Qwen3-14B on Hugging Face, so you can run it on your own hardware.