# Cerebras - gemma-4-31b grade card

OpenAI chat/completions · serves `gemma-4-31b` as gemma-4-31b · probed live 2026-08-29

HTML version: [https://inferencecanary.com/cerebras/gemma-4-31b](https://inferencecanary.com/cerebras/gemma-4-31b) · matrix: [https://inferencecanary.com/index.md](https://inferencecanary.com/index.md)

## Grades


| Axis | Grade | Basis |
|---|---|---|
| Inference | B | A − 1 high − 0 medium severity, per the published ladder |
| Billing | OK | Reported usage consistent with bytes on the wire. |
| Caching | Yes (3/3 hits) | Reused already-seen context on 3/3 cold→warm trials. Speed numbers: [https://inferencecanary.com/speed.md](https://inferencecanary.com/speed.md) |


## Flags

- **[high · inference] Images in tool results: rejected or silently blinded on several providers** - The model reads images returned by tools - the reference provider delivers them, perception-judged, and several OpenAI-compat providers prove the standard shape works. The failing providers fail on schema choice, not model limits: several reject the request (400/422), and AWS Bedrock (Responses) is the worst class - it returns 200 and the model never sees the image, answering confidently about content it never saw. Google's own shim rejects a capability Google's native protocol serves. SambaNova and Novita, which rejected these requests through July, deliver tool-result images since 2026-08-25. (details: [/tool-result-images.md](https://inferencecanary.com/tool-result-images.md))