Google · Open weights
Gemma 4 31B Cognitive Unshackled
ArliAI-hosted Gemma 4 31B finetune for open-ended reasoning, character chat, and multimodal creative work.
- Reasoning
- Tools
- Vision
- Input
- Text, Images
- Output
- Text
- Reasoning effort
- none · high
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.31
- Output
- $0.31
- Cache read
- $0.15
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- —
Side by side
Gemma 4 31B Cognitive Unshackled compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Gemma 4 31B Cognitive UnshackledGoogleThis model | Gemma 4 26B A4B Uncensored TEEGoogleRemove | |
|---|---|---|
| Provider | ||
| Discovery tier | Open weights | Open weights |
| Added | May 1, 2026 | May 23, 2026 |
| Limits | ||
| Context window | 262.14KBest | 65.54K |
| Max output | — | 65.54K |
| Pricing, USD per 1M tokens | ||
| Input | $0.31 | $0.15Best |
| Output | $0.31Best | $0.70 |
| Cache read | $0.15 | $0.05Best |
| Performance | ||
| Throughput | 16.4 tok/s | 55.3 tok/sBest |
| Time to first token | 12.4 s | 2.6 sBest |
| Request success (24h) | 66.6% | 99.8%Best |
| Capabilities | ||
| Reasoning | Yes | No |
| Tools | Yes | Yes |
| Vision | Yes | No |
| Structured output | No | Yes |
| Reasoning effort | none, high | — |
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
- 16.4 tok/s
- Faster than 11% of 52 models
- Time to first token
- 12.4 s
- Quicker than 7% of 52 models
- Request success (24h)
- 66.6%
- Failing
Hourly request success · last 72 hoursLowest hour 20.0%
- 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": "Gemma-4-31B-Cognitive-Unshackled", "reasoning_effort": "none", "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="Gemma-4-31B-Cognitive-Unshackled", messages=[{"role": "user", "content": "Explain this stack trace."}],)print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.