token.app › Compare › Gemma 4 31B (free) vs Inkling Small
Gemma 4 31B (free) vs Inkling Small
Gemma 4 31B (free) is free to use, against $0.637 per million tokens. Inkling Small accepts the larger context window (524K).
Head to head
Blended price uses a 3:1 input:output mix
| Gemma 4 31B (free) | Inkling Small | |
|---|---|---|
| Provider | Thinkingmachines | |
| Input $/1M | Free | $0.450 |
| Output $/1M | Free | $1.20 |
| Blended $/1M | Free | $0.637 |
| Context window | 262K | 524K |
| Max output | 33K | 262K |
| Released | Apr 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
Choose Gemma 4 31B (free) if…
- Costs less per token — Free vs $0.637 blended
Choose Inkling Small if…
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 4 31B (free) or Inkling Small?
We do not hold independently-run benchmark scores covering both Gemma 4 31B (free) and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Gemma 4 31B (free) cheaper than Inkling Small?
Gemma 4 31B (free) is cheaper: Free versus $0.637 per million tokens blended at 3:1 input:output. Input alone: Free vs $0.450. Output alone: Free vs $1.20.
What context windows do Gemma 4 31B (free) and Inkling Small have?
Gemma 4 31B (free): 262,144 tokens. Inkling Small: 524,288 tokens.
Who makes Gemma 4 31B (free) and Inkling Small?
Gemma 4 31B (free) is made by Google. Inkling Small is made by Thinkingmachines.
Related comparisons
Gemma 4 31B (free) full details
Inkling Small full details
Gemma 4 31B (free) vs Ling 3.0 Tiny (free)
Gemma 4 31B (free) vs Muse Spark 1.2
Gemma 4 31B (free) vs Qwen3.8 Max
Gemma 4 31B (free) vs DeepSeek V4 Flash Latest
Gemma 4 31B (free) vs DeepSeek V4 Flash 0731
Gemma 4 31B (free) vs Qwen3.7 Flash