PixMind Docs
Agent Integrations

Agent Integrations

Connect PixMind GPT-5.6 models to OpenCode, Cursor, Trae, Cherry Studio, Cline, and other agent clients.

PixMind exposes an OpenAI Chat Completions-compatible API for language models. Supported agents, IDEs, and desktop clients share one API key, Base URL, and set of model IDs.

Before you start

  1. Create an API key in the API Platform key dashboard.
  2. Use https://aihub-admin.aimix.pro/api-platform/v1 as the shared Base URL.
  3. Start with gpt-5.6-terra, then switch models after the connection works.

Store the API key only in a secure credential store, system keychain, or environment variable. Never commit it to Git.

Supported clients

ClientProtocolCurrent supportGuide
OpenCodeOpenAI Chat CompletionsDirectConfigure
CursorOpenAI Chat CompletionsDirectConfigure
TraeOpenAI Chat CompletionsDirectConfigure
Cherry StudioOpenAI Chat CompletionsDirectConfigure
Cline / Roo CodeOpenAI CompatibleDirectConfigure
Codex CLIOpenAI ResponsesGateway requiredRead limitation
Claude CodeAnthropic MessagesDirectConfigure

Choose a model

Anthropic

Model IDPositioningRecommended for
claude-fable-5Flagship agentComplex agents, deep reasoning, long workflows
claude-opus-5Advanced reasoningArchitecture, complex planning, difficult debugging
claude-sonnet-5Balanced codingDaily coding, tool calls, code review
claude-opus-4-8Complex engineeringLarge codebases and cross-file refactors
claude-opus-4-8-ccCoding agentTerminal tools and development automation

OpenAI

Model IDPositioningRecommended for
gpt-5.6-solFlagship reasoningLarge codebases, architecture, complex debugging
gpt-5.6-terraBalanced defaultDaily development, tool calls, mixed agent workloads
gpt-5.6-lunaFast and lightQuick answers, small edits, and batch tasks

Google

Model IDPositioningRecommended for
gemini-3.1-pro-previewMultimodal reasoningComplex image and video understanding
gemini-3.5-flashBalanced multimodalVisual Q&A, video understanding, tool calls
gemini-3.6-flashEfficient multimodalFrequent multimodal and batch workloads
gemini-3.7-flashVision and videoFast content understanding
gemini-3.5-flash-liteLight multimodalClassification, extraction, batch summaries

Protocol support

PixMind exposes two client protocols:

  • OpenAI-compatible clients use POST /api-platform/v1/chat/completions.
  • Claude Code uses POST /api-platform/anthropic/v1/messages, with /v1/messages/count_tokens and /v1/models under the same prefix.
  • Codex CLI custom providers use OpenAI Responses and still require a Responses-compatible endpoint.

Common troubleshooting

  • 401 Unauthorized: verify the client sends Authorization: Bearer <API_KEY> or x-api-key.
  • 404 Not Found: the Base URL must end in /api-platform/v1; the client appends /chat/completions.
  • Model not found: use an exact model ID such as gpt-5.6-terra, not a display name.
  • Streaming errors: verify a non-streaming request first, then enable OpenAI-compatible streaming.

On this page