tencent Open weights Reasoning

Hunyuan A13B Instruct pricing & benchmarks

Released Jul 8, 2025 · served by 1 provider

Input / 1M tokens$0.140
Output / 1M tokens$0.570
Context window131K
Cached input
1M in + 300K out$0.31

What Hunyuan A13B Instruct is

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

Providers and prices for Hunyuan A13B Instruct

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
SiliconFlowcheapest $0.140 $0.570 131K fp8 100.0%

FAQ

How much does the Hunyuan A13B Instruct API cost?

$0.140 per 1M input tokens and $0.570 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.31.

Is Hunyuan A13B Instruct free?

No. It is a paid model starting at $0.140 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Hunyuan A13B Instruct?

SiliconFlow at $0.140 input / $0.570 output per 1M tokens (fp8 quantization).

Can I self-host Hunyuan A13B Instruct?

Yes — weights are published as tencent/Hunyuan-A13B-Instruct on Hugging Face, so you can run it on your own hardware.