DiffusionGemma
DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window. Temperature, min-p, seed, minimum output tokens, logit bias, bad words, and allowed token IDs are unavailable; omit these parameters to use native diffusion sampling.
- Reasoning
Added Sep 19, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.05
- Output
- $0.15
- Cache read
- $0.025
Specifications
- Context window
- 262.1K
- Max output
- 32.8K
- Parameters
- 26B / 4B
- Total / active
Benchmarks
No public benchmark scores for this model yet.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
| $0.05 | $0.15 | $0.025 | N/A | N/A | |
| $0.05 | $0.15 | $0.025 | N/A | N/A | |
| $0.0525 | $0.157 | $0.0263 | N/A | N/A |
Privacy:ZDR, prompts not retainedNo training on prompts