AI model comparison
Gemma 4 31B 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.
Gemma 4 31B
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
- Input / 1M
- $0.09
- Output / 1M
- $0.34
- 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
Tie
Same price for a typical chat
Higher intelligence score
Step 3.5 Flash
17 vs 14.7 on Artificial Analysis
Larger context window
Tie
262K vs 262K tokens
Newer release
Gemma 4 31B
Released April 2, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Gemma 4 31B14.7Coding index
Gemma 4 31B43.4Agentic index
Gemma 4 31B4.2Pricing
Gemma 4 31B vs Step 3.5 Flash API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Gemma 4 31B | |
|---|---|---|
| Input tokensPer 1M tokens | $0.09 | $0.10 |
| Output tokensPer 1M tokens | $0.34 | $0.30 |
| Cached input (read)Per 1M tokens | $0.05 | 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
Gemma 4 31B$0.35Coding task
30K in, 4K out
Gemma 4 31B$4.06$2.86 cachedLong document summary
150K in, 2K out
Gemma 4 31B$14.18$8.18 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Gemma 4 31B | |
|---|---|---|
| Context window | 262K tokens | 262K tokens |
| Max output | 16K tokens | 66K tokens |
| Input types | Image, Text, Video | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | April 2, 2026 | January 29, 2026 |
Features
Supported features
API features available for each model.
| Metric | Gemma 4 31B | |
|---|---|---|
| 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 |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Gemma 4 31BView full model details- Gemma 4 31B vs Gemini 2.5 Flash Lite
- Gemma 4 31B vs gpt-oss-120b
- Gemma 4 31B vs Gemini 3.1 Flash Lite
- Gemma 4 31B vs Gemini 2.5 Flash
- Gemma 4 31B vs Gemma 4 26B A4B
- Gemma 4 31B vs GPT-5 Nano
- Gemma 4 31B vs Ling 3.0 Flash
- Gemma 4 31B vs DeepSeek V3.1
- Gemma 4 31B vs Mercury 2.5
- Gemma 4 31B vs Qwen3.5-9B
- Gemma 4 31B vs Nemotron 3.5 Lightning
- Gemma 4 31B vs Granite 4.2 8B
- Gemma 4 31B vs GLM 4.7 Flash
- Gemma 4 31B vs DeepSeek V3.2 Exp
- Gemma 4 31B vs Nemotron 3 Super
- Gemma 4 31B vs DeepSeek V3.1 Terminus
- Gemma 4 31B vs Mercury 2
- Step 3.5 Flash vs Hy3
- Step 3.5 Flash vs DeepSeek V3.2
- Step 3.5 Flash vs Ling 3.0 Flash
- Step 3.5 Flash vs Step 3.7 Flash
- Step 3.5 Flash vs Qwen3.6 35B A3B
- Step 3.5 Flash vs Gemma 4 26B A4B
- Step 3.5 Flash vs DeepSeek V3.2 Exp
- Step 3.5 Flash vs Gemini 3.1 Flash Lite
- Step 3.5 Flash vs GLM 4.7 Flash
- Step 3.5 Flash vs GPT-5 Nano
Our take
Step 3.5 Flash scores higher on the Artificial Analysis Intelligence Index (17 vs 14.7). 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 Gemma 4 31B or Step 3.5 Flash cheaper?
Gemma 4 31B and Step 3.5 Flash cost the same for a typical chat (2K input tokens and 500 output tokens). Gemma 4 31B costs $0.09 per 1M input tokens and $0.34 per 1M output tokens, and Step 3.5 Flash costs $0.10 per 1M input tokens and $0.30 per 1M output tokens.
Which has a bigger context window, Gemma 4 31B or Step 3.5 Flash?
Gemma 4 31B supports up to 262K tokens of context, compared with 262K for Step 3.5 Flash.
Is Gemma 4 31B smarter than Step 3.5 Flash?
On the Artificial Analysis Intelligence Index, Gemma 4 31B scores 14.7 and Step 3.5 Flash scores 17, putting Step 3.5 Flash ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Gemma 4 31B and Step 3.5 Flash at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Gemma 4 31B and Step 3.5 Flash answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Gemma 4 31B and Step 3.5 Flash at the same time. Compare the answers side by side and keep the best one.