Question 1

What is Hunyuan A13B Instruct?

Accepted Answer

Hunyuan A13B Instruct is a model from Tencent, released on Jun 27, 2025. 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 performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).

Question 2

How much does Hunyuan A13B Instruct cost?

Accepted Answer

On the Respan gateway, input starts at $0.14 per 1M tokens on OpenRouter, and output starts at $0.57 per 1M tokens on OpenRouter, after gateway discounts.

Question 3

Which providers serve Hunyuan A13B Instruct on Respan?

Accepted Answer

Hunyuan A13B Instruct is served by OpenRouter.

Question 4

What is Hunyuan A13B Instruct's context window?

Accepted Answer

Hunyuan A13B Instruct accepts up to 131K tokens of context.

Question 5

How do I use Hunyuan A13B Instruct with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "hunyuan-a13b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Hunyuan A13B Instruct?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 22 tokens per second, and the lowest response latency was 2.7 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Hunyuan A13B Instruct score on benchmarks?

Accepted Answer

Hunyuan A13B Instruct has 15 published benchmark scores, including Livecodebench 63.9%, BFCL v3 78.3%, and BBH 89.1%. Each score links to where it was published; the data is collected by llmmetric.com.

Hunyuan A13B Instruct

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Certified where it counts.

Coding2

Agents2

Reasoning3

Math3

Other5

Apps