Hy3 preview
Tencent · released Apr 13, 2026 · tencent/Hy3-preview
- Type
- Open weightsCustom licence
- Params
- 299B
- Context
- 262K
about 197K words of context · download allowed, licence restricts use
Our take
Written Aug 2, 2026Hy3 preview is a 299-billion-parameter text-only model from Tencent with a 262,144-token request limit and a custom licence. It is a leaderboard-tested coding specialist with a narrow provider market and no price competition between its two hosts.
Pick this for long-context coding tasks where 262,144 tokens are needed and leaderboard-tested coding quality is enough. Use it when budget-sensitive inference matters and only two providers are acceptable, or when Tencent ecosystem integration makes the custom licence negotiable. Skip it if you need creative writing or web-development strength, a permissive licence, or a choice of providers with competing prices.
The case for it
- Strong measured coding performance relative to its overall text score: its Arena Coding Elo is 46.9 points above its overall Arena Text Elo.
- Large request limit of 262,144 tokens at a mid-market price point.
- Consistent coding scores across multiple evaluation dates, with the same Arena Coding Elo on both 2026-07-27 and 2026-07-30.
The case against it
- Creative writing and web development are relative soft spots, with both scores more than 55 points below its Arena Coding score.
- Only two tracked offers, identically priced, so there is no price competition or alternative pricing.
- Custom licence is not permissive; throughput is uncertain, with one host unverified in our data and the other at 45 tokens per second.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)69th of 143 · 1412.2
CodingWriting and fixing code on its own
Arena Coding64th of 143 · 1459.5
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Hy3 preview for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Hy3 preview placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 188.1 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.063 in / $0.21 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.063 / $0.21 | 262K | not measured | Unknown | Unknown | Unknown |
| GMICloudbf16 | $0.063 / $0.21 | 262K | 41 tok/s | No | Yesunknown period | Unknown |
| Baidufp8 | $0.066 / $0.26 | 262K | 63 tok/s | No | Yesunknown period | Unknown |
BaiduAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| GMICloudbf16 | ✓ | ✗ | ✗ |
| Baidufp8 | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 1 of 3 listings says yes, 2 say no. Strict schema: 1 of 3 listings says yes, 2 say no.
When we formed this view
Dates behind this page
Prices last checked 35h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- tencent/Hy3-preview
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- tencent-hy3-preview