Hy3-FP8
Tencent's 295B-parameter Mixture-of-Experts reasoning model with just 21B active parameters — rivalling flagship open models that carry 2-5x more weights.
Quantization
FP8
MoE
Context Window
131K
Tokens
Intelligence
41
AA Index
Parameters
295B
21B active
Flagship quality, sparse compute
Hy3 is a 295B-parameter Mixture-of-Experts model with 21B active parameters, developed by the Tencent Hy Team. It outperforms similarly sized models and holds its own against flagship open-source releases carrying 2-5x more parameters.
Because only a small slice of the network fires per token, Hy3 is unusually cheap to serve — which makes it a strong default for reasoning-heavy async and batch workloads where you care about cost per million tokens as much as answer quality.
295B total · 21B active per token
Best for cost-sensitive reasoning at volume
Efficient Reasoning
Only 21B parameters active per token, so you get flagship-class reasoning quality at a fraction of the serving cost.
High-Volume Pipelines
Cheap enough to run across millions of documents, tickets, or records in async and batch jobs.
Tool & Agent Steps
Reliable instruction following makes Hy3 a strong workhorse for routing, extraction, and multi-step agent stages.
Knowledge Work
131K context handles long reports, transcripts, and codebase excerpts in a single call.
Flexible pricing tiers
Choose the optimal balance of speed and cost for your workflow. Prices are per 1M tokens.
| Tier | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| Batch | $0.07 | $0.29 |
| Async | $0.11 | $0.44 |
| Realtime | $0.14 | $0.58 |
Context window natively supported up to 131,072 tokens. Released 4 Jul 2026.
Start building in minutes
Hy3-FP8 is accessible via OpenAI-compatible endpoints — swap the model string and keep your existing client.
from openai import OpenAI
client = OpenAI(
api_key="your-api-key-here",
base_url="https://api.doubleword.ai/v1"
)
response = client.chat.completions.create(
model="tencent/Hy3-FP8",
messages=[
{"role": "user", "content": "Summarise this contract and list every obligation."}
],
temperature=0.7,
top_p=0.95,
)
print(response.choices[0].message.content)💡 Pro tip
Hy3's sparse MoE design makes it one of the cheapest reasoning models in the catalog — pair it with the Async or Batch tier for large evaluation, extraction, and classification runs.