All models
Tencent
Hunyuan A13B Instruct fastruns locally
tencent/hunyuan-a13b
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...
Input / 1M
$0.14
USD per million tokens
Output / 1M
$0.57
USD per million tokens
Est. cost / token
$0.000000248
$0.25 per 1M, 3:1 mix
Context window
131K
max output 118K
Major features
Open weightsReasoningJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic1
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 38.8 GB |
| Q3_K_M | fair | 44.7 GB |
| Q4_K_Mrecommended | good | 55 GB |
| Q5_K_M | very good | 63.5 GB |
| Q6_K | excellent | 72.7 GB |
| Q8_0 | near-lossless | 93.1 GB |
| F16 | lossless | 172 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.14 | $0.57 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.14
- Output
- $0.57
- Blended (3:1)
- $0.25
Details
- Company
- Tencent
- Version
- —
- Family
- Hunyuan
- Released
- 2025-07-08
- Parameters
- 80.4B (13B active)
- Max output
- 118K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 46 min ago