AI model comparison
Gemma 4 31B vs Reka Flash 3
Side by side comparison of Gemma 4 31B and Reka Flash 3 on pricing, benchmark scores, context window, and more.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
- Input / 1M
- $0.20
- Output / 1M
- $0.40
- Context
- 262K
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling.
- Input / 1M
- $0.10
- Output / 1M
- $0.20
- Context
- 66K
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
Reka Flash 3
2x cheaper for a typical chat
Higher intelligence score
Reka Flash 3
6.4 vs 4.4 on Artificial Analysis
Larger context window
Gemma 4 31B
262K vs 66K tokens
Newer release
Gemma 4 31B
Released April 2, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Coding index
Agentic index
Pricing
Gemma 4 31B vs Reka Flash 3 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | ||
|---|---|---|
| Input tokensPer 1M tokens | $0.20 | $0.10 |
| Output tokensPer 1M tokens | $0.40 | $0.20 |
| Cached input (read)Per 1M tokens | Not available | 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 | 66K tokens |
| Max output | 16K tokens | 59K 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 | March 12, 2025 |
Features
Supported features
API features available for each model.
| Metric | ||
|---|---|---|
| Tool calling | Supported | Not supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Not supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Our take
Reka Flash 3 is 2x cheaper for a typical chat. Reka Flash 3 scores higher on the Artificial Analysis Intelligence Index (6.4 vs 4.4). Gemma 4 31B has the larger context window (262K vs 66K tokens). 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 Reka Flash 3 cheaper?
Reka Flash 3 is cheaper for a typical chat (2K input tokens and 500 output tokens). Reka Flash 3 costs $0.10 per 1M input tokens and $0.20 per 1M output tokens, while Gemma 4 31B costs $0.20 per 1M input tokens and $0.40 per 1M output tokens.
Which has a bigger context window, Gemma 4 31B or Reka Flash 3?
Gemma 4 31B supports up to 262K tokens of context, compared with 66K for Reka Flash 3.
Is Gemma 4 31B smarter than Reka Flash 3?
On the Artificial Analysis Intelligence Index, Gemma 4 31B scores 4.4 and Reka Flash 3 scores 6.4, putting Reka Flash 3 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Gemma 4 31B and Reka Flash 3 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Gemma 4 31B and Reka Flash 3 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Gemma 4 31B and Reka Flash 3 at the same time. Compare the answers side by side and keep the best one.