token.app › Compare › Gemma 2 27B vs Inkling
Gemma 2 27B vs Inkling
Inkling leads on 2 of 2 shared benchmarks. Gemma 2 27B is 2.7× cheaper per token on a blended 3:1 basis. Inkling accepts the larger context window (524K).
Head to head
Blended price uses a 3:1 input:output mix
| Gemma 2 27B | Inkling | |
|---|---|---|
| Provider | Thinkingmachines | |
| Input $/1M | $0.650 | $1.00 |
| Output $/1M | $0.650 | $4.05 |
| Blended $/1M | $0.650 | $1.76 |
| Context window | 8K | 524K |
| Max output | 2K | 472K |
| Released | Jul 2024 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 36.5% | 88.3% |
| OTIS Mock AIME | 1.4% | 88.9% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Gemma 2 27B if…
- Costs less per token — $0.650 vs $1.76 blended
Choose Inkling if…
- Higher GPQA Diamond (88.3% vs 36.5%)
- Higher OTIS Mock AIME (88.9% vs 1.4%)
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 2 27B or Inkling?
Across the 2 benchmarks both models have independently-run scores for, Gemma 2 27B leads on 0 and Inkling leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Gemma 2 27B cheaper than Inkling?
Gemma 2 27B is cheaper: $0.650 versus $1.76 per million tokens blended at 3:1 input:output. Input alone: $0.650 vs $1.00. Output alone: $0.650 vs $4.05.
What context windows do Gemma 2 27B and Inkling have?
Gemma 2 27B: 8,192 tokens. Inkling: 524,288 tokens.
Who makes Gemma 2 27B and Inkling?
Gemma 2 27B is made by Google. Inkling is made by Thinkingmachines.