tencent
Tencent: Hunyuan A13B Instruct
tencent/hunyuan-a13b-instruct
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
tencent/hunyuan-a13b-instruct is Tencent's instruction-tuned Hunyuan-A13B text model, described as a Mixture-of-Experts system with 80B total and 13B active parameters. The model documentation reports switchable fast and slow reasoning, tool calling, and long-context support; OpenRouter lists a 131,072-token text-in/text-out endpoint with structured-output controls. Vendor benchmarks report broad competitive results, but independent verification was not supplied.[1][2]
Strengths
- The MoE design uses 13B active parameters out of 80B total and is presented by Tencent as a way to reduce inference overhead while retaining capacity.[2]
- Hybrid reasoning lets callers choose slower chain-of-thought-style reasoning or a faster direct answer; the Transformers guidance defaults to slow thinking.[2]
- Documentation describes tool-call parsing and agent tuning, while OpenRouter exposes structured-output and reasoning request controls.[1][2]
Limitations
- Context limits are deployment-dependent: Tencent describes 256K native support but a 32K default configuration, whereas OpenRouter lists 131,072 tokens.[1][2]
- Benchmark claims come from Tencent's supplied tables; the source pack contains no independent measurements, and one table is explicitly labeled for base models.[2]
- Use requires reviewing Tencent's custom tencent-hunyuan-a13b license, and the OpenRouter listing includes a dated expiration that should be checked before relying on endpoint availability.[1][2]
Where to use it
- May suit general chat, drafting, and summarization where an MoE model with fewer active parameters is desirable.[2]
- May fit agent or function-calling prototypes, given the documented tool parsing and vendor-reported agent benchmark results.[2]
- Could be evaluated for long-document analysis after confirming whether the chosen deployment offers 32K, 131,072, or 256K context.[1][2]
Sources
- [1] OpenRouter catalog · Tencent: Hunyuan A13B InstructSources checked: Nov 13, 2026
- [2] Model documentation · Tencent: Hunyuan A13B InstructSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- tencent/hunyuan-a13b-instruct
- Creator
- tencent
- Added to OpenRouter
- 08.07.2025
- Context length
- 131,072
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.140 / out $0.570
- Knowledge cutoff
- 31.03.2025
- Expiration date
- 15.11.2026
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| SiliconFlowfp8 | 131,072 | $0.140 | $0.570 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.