DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window.
Context
262K
262,144 tokens
Max output
33K
32,768 tokens
Input
$0.05
per 1M tokens
Output
$0.15
per 1M tokens
Providers
2
2 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by NanoGPT
| Token type | Standard |
|---|---|
| Input | $0.05 |
| Output | $0.15 |
| Cache read | $0.03 |
Lowest input price across providers: Free.
Capabilities
ReasoningYes
Effort: none, xhigh
Tool callNo
Structured outputNo
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsYes
ModeratedUnknown
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 2
2 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 NanoGPT | google/diffusiongemma | 262K | 262K | 33K | $0.05 | $0.15 | — | $0.03 | — | — | — | Yes | No | No | Yes | Jul 15, 2026 |
 Nvidia | google/diffusiongemma-26b-a4b-it | 250K | — | 33K | Free | Free | — | — | — | — | — | Yes | Yes | Unknown | Yes | Jul 15, 2026 |