text model comparison
Hy4 vs Hy4 flash
Hy4 and Hy4 flash are both current text models, from Tencent. Hy4 flash is 92% cheaper per 1M input tokens than Hy4, $0.07 vs $0.834. In Tencent's Hy4 flash launch table, Hy4 scores 74.9% on DeepSWE v1.1 and Hy4 flash 64.6%. Both accept 1,048,576 tokens of context.
- Lower price per 1M input tokens
- Hy4 flash$0.07 against $0.834
- Newer release
- Hy4 flashNov 16, 2026 against Nov 4, 2026
Data verified November 17, 2026 · Dataset 2026-11-17
Side by side
Hy4 and Hy4 flash, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | Hy4 | Hy4 flash |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $0.834 | $0.07 (better) |
| Price per 1M output tokens | $2.501 | $0.281 (better) |
| Specs | ||
| Provider | Tencent | Tencent |
| Release date | November 4, 2026 | November 16, 2026 |
| Access | API only | API only |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
| Max output | 65,536 tokens | 65,536 tokens |
| Input | text, image | text, image |
| Output | text | text |
Provider results
What the labs report
Results tables a lab published with one of its models, where it lists both Hy4 and Hy4 flash. These are the lab's own figures, not independent measurements, and each table is read on its own: labs run benchmarks with different harnesses and budgets.
Tencent, Hy4 flash launch table, November 16, 2026Tencent · 2026-11-17
| Benchmark | Hy4 | Hy4 flash |
|---|---|---|
| DeepSWE v1.1 | 74.9% (better) | 64.6% |
| ProgramBenchalmost solved | 30.0% (better) | 16.0% |
| Terminal-Bench 4.0Claude Code harness | 44.4% (better) | 19.2% |
| APEX-Agents v1.1pass@1 | 75.2% (better) | 63.1% |
| AutomationBench v1.0.6 | 56.2% (better) | 52.2% |
| HLE-Fullwith tools | 59.1% (better) | 55.2% |
| OSWorld 2.1full, partial score | 78.9% (better) | 68.1% |
| MMMU-Pro | 78.6% (better) | 75.8% |
| ZeroBench mainwith tools, pass@5 | 55.4% (better) | 45.8% |
Tencent's appendix to the Hy4 flash announcement, every model at its highest available reasoning setting and run by Tencent. DeepSeek-V4.1-Flash is the 1017 build. Tencent's Hy4 table gives DeepSeek-V4.1-Flash 51.0% on ZeroBench, this one 16.5%. Left out here: Tencent's internal WorkIndex benchmarks, the cost per task in yuan and the Hy4 preview column.
Charts
Against every current text model
Where Hy4 and Hy4 flash land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
No independent benchmark has scored either model yet, so the tiles rank their prices among the current models of their task.
Price and context
Price per 1M input tokens
Hy4:#25of 60
$0.834 · cheaper than 59%
Hy4 flash:#1of 60
$0.07 · cheaper than 100%
Price per 1M output tokens
Hy4:#24of 60
$2.501 · cheaper than 61%
Hy4 flash:#2of 60
$0.281 · cheaper than 98%
Context window
Hy4:#12of 71
1.05M tokens · longer than 60%
Hy4 flash:#12of 71
1.05M tokens · longer than 60%
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
For 10M input and 2M output tokens, Hy4 costs 11 times as much as Hy4 flash, at each provider's listed rates.
10M input and 2M output tokens
Hy4 costs 11× as much
- Hy4
- $13.34
- Hy4 flash
- $1.26
The same, with 9M of the input tokens cached
Hy4 costs 9.4× as much
- Hy4
- $6.21
- Hy4 flash
- $0.66
| Workload or rate | Hy4 | Hy4 flash |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $13.34 | $1.26 (better) |
| The same, with 9M of the input tokens cached | $6.21 | $0.66 (better) |
| Other listed rates | ||
| 1M input tokens, cached | $0.042 | $0.003 (better) |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
Hy4
Where it leads
No measured lead over Hy4 flash in this data.
Best for
- Agents that work across terminals, desktop apps and browsers on a tight budget
- Finance and office work: research reports, spreadsheets and slides
Watch out for
- API only for now: Tencent says it will publish the weights and a system card later, and only Hy4 preview (August 2026, Apache 2.0) is open today
- In Tencent's own table it scores 44.4% on Terminal-Bench 4.0 against 66.8% for Kimi K3.1 Pro, and Tencent says a clear gap remains to top proprietary models on research-level math, long-horizon coding and hard visual questions
- Tencent Cloud TokenHub serves it with a 1M-token context but caps a request at 960K input and 64K output tokens, and no independent benchmark score is recorded here yet
Hy4 flash
Where it leads
- Lower input and output prices, $0.07 and $0.281 vs $0.834 and $2.501 per 1M tokens
- Cheaper cached input, $0.003 vs $0.042 per 1M tokens
Best for
- High-volume everyday office work: deep search, documents, slides and simple front-end demos
- Cheap computer-use and agent steps where speed and cost per task matter more than peak accuracy
Watch out for
- In Tencent's own table it trails Hy4 on all nine public benchmarks and DeepSeek-V4.1-Flash on eight, most on Terminal-Bench 4.0 (19.2% against 44.4% and 40.0%)
- API only for now: Tencent plans open weights without giving a date, and recommends Hy4 instead for long-horizon software engineering
- No independent benchmark score is recorded here yet; Tencent's other evidence is internal: its WorkIndex and a blind test by 85 of its own WorkBuddy users, in which satisfaction came close to Claude Haiku 5.5
From benchmark to production
Building on Hy4 or Hy4 flash?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150
FAQ
Hy4 vs Hy4 flash FAQ
Which is cheaper, Hy4 or Hy4 flash?
Hy4 flash is 92% cheaper per 1M input tokens than Hy4, $0.07 vs $0.834. For 10M input and 2M output tokens, Hy4 costs $13.34 and Hy4 flash $1.26 at standard rates.
Which is cheaper with prompt caching, Hy4 or Hy4 flash?
Hy4 charges $0.042 per 1M cached input tokens, 95% below its standard input rate, and Hy4 flash $0.003, 96% below. With 9M of 10M input tokens cached and 2M output tokens, Hy4 costs $6.21 and Hy4 flash $0.66.
How do Hy4 and Hy4 flash compare in Tencent's own results?
In the Hy4 flash launch table (November 16, 2026), Hy4 leads on DeepSWE v1.1, 74.9% to 64.6%; Hy4 leads on ProgramBench (almost solved), 30.0% to 16.0%; Hy4 leads on Terminal-Bench 4.0 (Claude Code harness), 44.4% to 19.2%. These are Tencent's figures, not independent measurements.
Which has the larger context window, Hy4 or Hy4 flash?
Both accept 1,048,576 tokens of context. Both return up to 65,536 tokens per response.
AI Model Brief
The AI models worth knowing, once a week
What shipped, how it scores on independent benchmarks, what it costs per million tokens and what was deprecated, from the data behind our AI model benchmarks.
We use your address only to send the brief. See our privacy policy.
See this week’s briefFurther reading
More on Hy4 and Hy4 flash
Production evaluation
Choosing between Hy4 and Hy4 flash?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty
