DiffusionGemma 26B A4B ITOpen weights
Google · released 2026-06-09
No price from the maker itself is on record for DiffusionGemma 26B A4B IT. The lowest of 2 providers is NanoGPT: $0.05 per 1M input tokens and $0.15 per 1M output tokens (as of 2026-11-12). Context window: 250K tokens, up to 32.8K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestgoogle/ | $0.05 | $0.15 | $0.025 | Lowest | Official docs |
 Nvidiagoogle/ | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window.
Description from models.dev.
Specs
- Type
- Text
- Context
- 250K
- Max output
- 32.8K
- Input
- Text, Image, Video
- Output
- Text
- Reasoning
- Yes
- Tool calling
- No
- Structured output
- No
- Knowledge cutoff
- 2025-01
- Open weights
- Yes
- Released
- 2026-06-09
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.