DeepInfra

1 graded endpoint serving gemma-4-31b · back to the matrix

Findings affecting DeepInfra

• red harness Images in tool results: rejected, 500'd, or silently blinded on 7 of 11 providers
  The model reads images returned by tools — the reference provider delivers them, perception-judged, and three OpenAI-compat providers prove the standard shape works. Seven providers fail on schema choice, not model...
• red harness DeepInfra validates tool_choice but does not enforce it
  Invalid values are rejected with 400/422 — every surface signal says the capability exists — but a valid constraint has zero effect on decoding: "required" returns prose with zero calls, and forcing a tool by name yields...
• yellow harness Tool results replayed out of order are mis-paired on most providers
  The chat dialect's contract is that a tool message is matched to its call by tool_call_id, in any order. After two parallel calls, replaying the results reversed swaps the data between them on these providers — the...