AI model comparison
Hy3 vs Mistral Small 4
Side by side comparison of Hy3 and Mistral Small 4 on pricing, benchmark scores, context window, and more.
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
- $0.13
- Output / 1M
- $0.53
- Context
- 262K
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.
- Input / 1M
- $0.15
- Output / 1M
- $0.60
- Context
- 262K
Comparing image generators? Compare image models
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
Not available
Not enough benchmark data
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
Mistral Small 44.3Coding index
Mistral Small 426.6Agentic index
Mistral Small 40.8Pricing
Hy3 vs Mistral Small 4 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mistral Small 4 | |
|---|---|---|
| Input tokensPer 1M tokens | $0.13 | $0.15 |
| Output tokensPer 1M tokens | $0.53 | $0.60 |
| Cached input (read)Per 1M tokens | $0.03 | $0.02 |
| 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
Mistral Small 4$0.60Coding task
30K in, 4K out
Mistral Small 4$6.90$2.85 cachedLong document summary
150K in, 2K out
Mistral Small 4$23.70$3.45 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mistral Small 4 | |
|---|---|---|
| Context window | 262K tokens | 262K tokens |
| Max output | 128K tokens | 210K tokens |
| Input types | Text | Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Low, None | High, None |
| Default reasoning effort | High | High |
| Release date | July 6, 2026 | March 16, 2026 |
Features
Supported features
API features available for each model.
| Metric | Mistral Small 4 | |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
- Hy3 vs DeepSeek V4.1 Flash 1017
- Hy3 vs GLM 5.3 Flash
- Hy3 vs DeepSeek V4.1 Flash
- Hy3 vs GPT-6 Luna
- Hy3 vs Hy4 preview
- Hy3 vs MiniMax M3.1 Flash
- Hy3 vs MiMo-V2.6-Flash
- Hy3 vs Claude Haiku 5.5
- Hy3 vs Muse Spark 1.3 Contributor
- Hy3 vs Qwen3.8 Flash
- Hy3 vs GPT-6 Luna Pro
- Hy3 vs Gemma 4 31B
- Hy3 vs Step 3.7 Flash
- Hy3 vs gpt-oss-120b
- Hy3 vs Gemini 2.5 Flash Lite
- Hy3 vs DeepSeek V3.2
- Hy3 vs Nemotron 3.5 Super VL
- Hy3 vs GPT-4o-mini
- Hy3 vs Qwen3.6 35B A3B
Mistral Small 4View full model details- Mistral Small 4 vs Nemotron 3.5 Super VL
- Mistral Small 4 vs Muse Glimmer 30B
- Mistral Small 4 vs Command A+
- Mistral Small 4 vs Nemotron 3.5 Lightning
- Mistral Small 4 vs DeepSeek V4.1 Flash 1017
- Mistral Small 4 vs DeepSeek V4.1 Flash
- Mistral Small 4 vs Qwen3.8 Flash
- Mistral Small 4 vs GPT-6 Luna Pro
- Mistral Small 4 vs gpt-oss-120b
Our take
Hy3 is 1.1x cheaper for a typical chat. 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 Mistral Small 4 cheaper?
Hy3 is cheaper for a typical chat (2K input tokens and 500 output tokens). Hy3 costs $0.13 per 1M input tokens and $0.53 per 1M output tokens, while Mistral Small 4 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens.
Which has a bigger context window, Hy3 or Mistral Small 4?
Hy3 supports up to 262K tokens of context, compared with 262K for Mistral Small 4.
Can I use Hy3 and Mistral Small 4 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Hy3 and Mistral Small 4 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Hy3 and Mistral Small 4 at the same time. Compare the answers side by side and keep the best one.