Gemma 4 26B A4B Uncensored
Gemma 4 26B A4B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Google’s Gemma 4 MoE model with 25.2B total / 3.8B active parameters, with hardware attestation evidence available for independent verification.
Input / output
$0.19 / $0.88
per 1M tokens
Context
64K
4K max output
Reasoning
None
answers directly
Cached input
—
no prompt caching
Modalities
Text
out: text
Pricing
USD per 1M tokensInput
$0.19
Output
$0.88
| Similar models | Input | Output |
|---|---|---|
| Gemma 4 26B A4B Uncensored | $0.19 | $0.88 |
| Venice Uncensored 1.2 | $0.20 | $0.90 |
| Qwen 3.6 35B A3B | $0.10 | $1.00 |
| Qwen 3.5 35B A3B | $0.15 | $1.00 |
| Qwen3 VL 30B A3B | $0.25 | $0.90 |
Specs
- Model ID
e2ee-gemma-4-26b-a4b-uncensored-p- Endpoint
POST /api/v1/chat/completions- Context window
- 64,000 tokens
- Max output
- 4,096 tokens
- Reasoning effort
- No separate reasoning phase
- Served precision
- FP8
- Added
- May 24, 2026
- Weights
- Open
Capabilities
Modalities
- Text
- Input and output
- Image
- Not supported
- Audio
- Not supported
- Video
- Not supported
Features
- Streaming (SSE)
- Supported
- Function calling
- Not supported
- Structured output (json_schema)
- Not supported
- Reasoning effort
- Not supported
- Prompt caching
- Not supported
- Web search
- venice_parameters
- X search
- Not supported
- Log probabilities
- Not supported
- Fine-tuning
- Not supported
- Image generation
- Not supported
POST
/api/v1/chat/completionsRecommendedE2EE requests encrypt the prompt on your device and send attestation headers; follow the TEE and E2EE guide. The samples show the plain request shape.
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "e2ee-gemma-4-26b-a4b-uncensored-p",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'Privacy
Tier 1
Anonymized
Included
Tier 2
Private
Included
Tier 3
TEE
Included
Tier 4 · this model
End-to-end encrypted
Your client encrypts the prompt, and only the verified enclave decrypts it.