AI model comparison
Hy3 vs Step 3.5 Flash
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Tencent
Hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use.
- Input / 1M
- $0.08
- Output / 1M
- $0.33
- Context
- 262K
StepFun
Step 3.5 Flash
Step 3.5 Flash is StepFun's most capable open-source foundation model.
- Input / 1M
- $0.10
- Output / 1M
- $0.30
- Context
- 262K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Hy3
1.1x cheaper for a typical chat
Higher intelligence score
Hy3
25.3 vs 17 on Artificial Analysis
Larger context window
Tie
262K vs 262K tokens
Newer release
Hy3
Released July 6, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Coding index
Agentic index
Pricing
Hy3 vs Step 3.5 Flash API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | ||
|---|---|---|
| Input tokensPer 1M tokens | $0.08 | $0.10 |
| Output tokensPer 1M tokens | $0.33 | $0.30 |
| Cached input (read)Per 1M tokens | $0.02 | Not available |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Coding task
30K in, 4K out
Long document summary
150K in, 2K out
Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | ||
|---|---|---|
| Context window | 262K tokens | 262K tokens |
| Max output | 128K tokens | 66K tokens |
| Input types | Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Low, None | Not available |
| Default reasoning effort | High | Not available |
| Release date | July 6, 2026 | January 29, 2026 |
Features
Supported features
API features available for each model.
| Metric | ||
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Not supported |
| JSON mode | Supported | Not supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Not supported |
| Deterministic seed | Supported | Not supported |
| Verbosity control | Not supported | Not supported |
Our take
Hy3 is 1.1x cheaper for a typical chat. Hy3 scores higher on the Artificial Analysis Intelligence Index (25.3 vs 17). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Hy3 or Step 3.5 Flash cheaper?
Hy3 is cheaper for a typical chat (2K input tokens and 500 output tokens). Hy3 costs $0.08 per 1M input tokens and $0.33 per 1M output tokens, while Step 3.5 Flash costs $0.10 per 1M input tokens and $0.30 per 1M output tokens.
Which has a bigger context window, Hy3 or Step 3.5 Flash?
Hy3 supports up to 262K tokens of context, compared with 262K for Step 3.5 Flash.
Is Hy3 smarter than Step 3.5 Flash?
On the Artificial Analysis Intelligence Index, Hy3 scores 25.3 and Step 3.5 Flash scores 17, putting Hy3 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Hy3 and Step 3.5 Flash at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Hy3 and Step 3.5 Flash answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Hy3 and Step 3.5 Flash at the same time. Compare the answers side by side and keep the best one.