Google · Open weights
Gemma 4 26B A4B Uncensored TEE
Gemma 4 26B A4B Uncensored Heretic is an MoE model tuned to reduce refusal behavior while preserving coding, reasoning, and function-calling strengths. Running inside a TEE (Trusted Execution Environment), with provider attestation support. Image input is unavailable on this deployment.
- Tools
- Structured output
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.15
- Output
- $0.70
- Cache read
- $0.05
Reference prices as published by the model provider. API example
Specifications
- Context window
- 65.5K
- Max output
- 65.5K
Side by side
Gemma 4 26B A4B Uncensored TEE compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Gemma 4 26B A4B Uncensored TEEGoogleThis model | Gemma 4 26B A4B Chimera X HereticGoogleRemove | |
|---|---|---|
| Provider | ||
| Discovery tier | Open weights | Open weights |
| Added | May 23, 2026 | Oct 8, 2026 |
| Limits | ||
| Context window | 65.54K | 262.14KBest |
| Max output | 65.54KBest | 32.77K |
| Pricing, USD per 1M tokens | ||
| Input | $0.15 | $0.12Best |
| Output | $0.70 | $0.38Best |
| Cache read | $0.05Best | $0.06 |
| Performance | ||
| Throughput | 55.3 tok/sBest | 52.9 tok/s |
| Time to first token | 2.6 s | 2.5 sBest |
| Request success (24h) | 99.8%Best | 99.2% |
| Capabilities | ||
| Reasoning | No | Yes |
| Tools | Yes | Yes |
| Vision | No | Yes |
| Structured output | Yes | No |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
There are no public benchmark results for these models yet.
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.
- Throughput
- 55.3 tok/s
- Faster than 38% of 52 models
- Time to first token
- 2.6 s
- Quicker than 67% of 52 models
- Prompt cache hits
- 29.7%
- About $0.12 per 1M input tokens with caching
- Request success (24h)
- 99.8%
- Reliable
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.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Ophiris’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.ophiris.xyz/api/v1/chat/completions \ -H "Authorization: Bearer $OPHIRIS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "TEE/gemma-4-26b-a4b-uncensored", "messages": [{ "role": "user", "content": "Explain this stack trace." }] }'import osfrom openai import OpenAI client = OpenAI(base_url="https://www.ophiris.xyz/api/v1", api_key=os.environ["OPHIRIS_API_KEY"])reply = client.chat.completions.create( model="TEE/gemma-4-26b-a4b-uncensored", messages=[{"role": "user", "content": "Explain this stack trace."}],)print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.