DiffusionGemma
Description
DiffusionGemma is an experimental 26B (4B active) multimodal Mixture-of-Experts model that uses discrete diffusion for fast text generation, achieving an average generation speed of approximately 650 tokens per second.
At a Glance
Key pricing and model details available for this model.
Input price
$0.06
per 1M tokens
Output price
$0.18
per 1M tokens
Context window
262K
tokens
Hallucination rate
0%
Token Pricing
Token pricing normalized to per-million-token rates.
Input / 1M tokens
$0.06
Output / 1M tokens
$0.18
Cache Read / 1M tokens
$0.03
Token Pricing Details
Rates are shown per 1M tokens for easier comparison.
| Input / 1M tokens | $0.06 |
| Input unit | 1M tokens |
| Output / 1M tokens | $0.18 |
| Output unit | 1M tokens |
| Cache Read / 1M tokens | $0.03 |
| Cache Read unit | 1M tokens |
Feature Availability
Capabilities explicitly listed in the current payload.
LLM
Available
Vision
Available
Function calling
Available
Reasoning
Available
Service tiers
Not listed
Supported Parameters
Category Radar
Aggregated from the benchmark values present for reasoning, code, math, and accuracy.
Benchmark Breakdown
Detailed benchmark results drawn from the current payload.
GPQA
Graduate-level science questions designed to be difficult to shortcut.
66.9%
Reported score
HLE
A very hard expert-level exam across a wide range of subjects.
10.8%
Reported score
IFBench
Measures how precisely the model follows detailed instructions.
59.5%
Reported score
LCR
Tests long-context reasoning over large documents and conversations.
19.7%
Reported score
Code Samples
Quick start with the Routeway API
import OpenAI from 'openai';
const openai = new OpenAI({
baseURL: "https://api.routeway.ai/v1",
apiKey: "<YOUR_API_KEY>",
});
async function main() {
const completion = await openai.chat.completions.create({
model: "diffusiongemma",
messages: [
{
role: "user",
content: "Explain quantum computing in simple terms"
}
]
});
console.log(completion.choices[0].message);
}
main();