Unverified50% confidenceFactExact time
OpenCode (issue #54801, reproduced on v2.0.27) cannot parse effort variants for M3.1 Flash; the workaround is to declare five variants in opencode.json and set reasoning_effort for each separately (without none).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/19/2026
First Seen
Valid until: 11/2/2026
Sources
Related Entities
Related Claims
UnverifiedOpenCode announced the addition of the V4 Flash multimodal model to its plans, and it is now available70% similarUnverifiedFor the same MiniMax M3.1 Flash model, the effort field is named reasoning_effort, output_config.effort, and reasoning.effort under the OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses protocols respectively; all three accept the five values low/medium/high/xhigh/max, and all default to max.69% similarUnverifiedWorkBody, CodeBody, and OpenCode have all been fully integrated with the new DeepSeek V4.1 Flash model.69% similarUnverifiedOpenCode is a coding agent tool that can integrate Gemini 2.0 Flash by adding the Google provider and registering the model ID gemini-2.0-flash.67% similarUnverifiedMost client SDKs or in-house message serializers keep only the OpenAI-standard content and tool_calls fields and discard the non-standard extension field reasoning_content, which is the structural reason the 400 error keeps recurring in projects such as opencode, LangChain and claude-code-router.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067195API
curl https://kongchang.com/api/v1/knowledge/claims/1067195MCP
get_claim(id=1067195)