Google · Open weights
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
- Input
- Text
- Output
- Text
- Reasoning effort
- none · xhigh
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.05
- Output
- $0.15
- Cache read
- $0.025
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 32.8K
- Average output (7 days)
- 266 tokens
- Longer than 28% of 473 models
Side by side
DiffusionGemma compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| DiffusionGemmaGoogleThis model | Gemma 4 31B Split-UntiedGoogleRemove | |
|---|---|---|
| Provider | ||
| Discovery tier | Open weights | Open weights |
| Added | Sep 19, 2026 | Sep 17, 2026 |
| Limits | ||
| Context window | 262.14K | 262.14K |
| Max output | 32.77K | 32.77K |
| Average output | 266 tokens | — |
| Pricing, USD per 1M tokens | ||
| Input | $0.05Best | $0.10 |
| Output | $0.15Best | $0.30 |
| Cache read | $0.025 | — |
| Performance | ||
| Request success (24h) | — | 99.7% |
| Benchmark indexes | ||
| Intelligence Index | 9.5 | — |
| Coding Index | 19.7 | — |
| Capabilities | ||
| Reasoning | Yes | No |
| Tools | No | Yes |
| Reasoning effort | none, xhigh | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- DiffusionGemma
- Gemma 4 31B Split-Untied
Intelligence Index
- DiffusionGemma9.5
- Gemma 4 31B Split-Untied—
DiffusionGemma: Better than 19% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- DiffusionGemma: 19.7
- Gemma 4 31B Split-Untied: —
Agentic work
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- DiffusionGemma: 321 Elo
- Gemma 4 31B Split-Untied: —
Document reasoning
AA-LCRv1.1
Reasoning across long documents
- DiffusionGemma: 19.7%
- Gemma 4 31B Split-Untied: —
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- DiffusionGemma: 10.8%
- Gemma 4 31B Split-Untied: —
GPQA Diamond
Graduate-level science questions
- DiffusionGemma: 66.9%
- Gemma 4 31B Split-Untied: —
IFBench
Following precise output instructions
- DiffusionGemma: 59.5%
- Gemma 4 31B Split-Untied: —
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- DiffusionGemma: 19.7%
- Gemma 4 31B Split-Untied: —
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 0.0%
- About $0.05 per 1M input tokens with caching
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/diffusiongemma",
"reasoning_effort": "none",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="google/diffusiongemma",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.
