Skip to main content
Tembo supports multiple coding agents to solve your software engineering tasks.

​
Supported LLMs

Use these model IDs with your agent key (agent:model or agent:model:reasoningLevel for GPT-5 variants). Choose a model from a provider your agent supports and make sure any required API keys are configured. Anthropic (no API key required)
  • claude-4-5-sonnet (default for Claude Code/OpenCode/Cursor)
  • claude-opus-4-5
  • claude-4.1-opus
  • claude-4-5-haiku
  • claude-4-sonnet
  • claude-3-5-sonnet
  • claude-3-5-haiku
OpenAI (API key required)
  • gpt-5, gpt-5-minimal, gpt-5-low, gpt-5-medium, gpt-5-high
  • gpt-5.1, gpt-5.2
  • gpt-5-codex, gpt-5-codex-high
  • gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.1-codex-high
  • gpt-5.2-codex
  • zai-glm-4.7 (OpenAI-compatible)
Google (no API key required)
  • gemini-2.5-pro
  • gemini-3-pro
  • gemini-3-flash
Moonshot via Bedrock (no API key required)
  • bedrock-kimi-k2-thinking
Cursor (Cursor API key required)
  • composer-1
XAI (XAI API key required)
  • grok
For GPT-5 and GPT-5.2 families you can append a reasoning effort (:minimal, :low, :medium, :high) when the agent supports it.

​
Available Coding Agents

Coding AgentModel ProvidersDefault Model
Claude CodeAnthropicclaude-4-5-sonnet
CodexOpenAIgpt-5.2
OpencodeAnthropic/OpenAIclaude-4-5-sonnet
AmpAnthropic (auto-selected)claude-opus-4-5
CursorAnthropic/OpenAI/Google/Cursor/XAIclaude-4-5-sonnet

​
Claude Code (Default)

Powered by Anthropic’s Claude models. Best balance of quality, reliability, and cost. Models: claude-4-5-sonnet (default), claude-opus-4-5, claude-4.1-opus, claude-4-5-haiku, claude-4-sonnet

​
Codex

Powered by OpenAI’s Responses API (GPT-5 family) with configurable reasoning effort. Models: gpt-5.2 (default), gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini Add :minimal, :low, :medium, or :high to gpt-5.2 to control reasoning effort.

​
Opencode

Alternative agent supporting multiple model providers. Models: claude-4-5-sonnet (default), claude-opus-4-5, claude-4.1-opus, claude-4-5-haiku, claude-4-sonnet, gpt-5.2, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini Also supports OpenAI models.

​
Amp

Powered by Claude models. Manages model selection automatically, defaults to claude-opus-4-5.

​
Cursor

Supports Claude, GPT, Gemini, Composer, and Grok through the Cursor CLI. Models: claude-4-5-sonnet (default), claude-opus-4-5, claude-4.1-opus, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-high, gpt-5.2, gemini-3-pro, gemini-3-flash, composer-1, grok Also supports Gemini 3 Flash.

​
Selecting an Agent

Use the format agentType:model[:reasoningLevel]: 
claudeCode:claude-4-5-sonnet
codex:gpt-5.2:high
cursor:grok
Default: claudeCode:claude-4-5-sonnet

​
Choosing the Right Model

Use CaseRecommended Models
Most tasksclaude-4-5-sonnet, gpt-5.2
Quick fixesclaude-4-5-haiku, gpt-5.1-codex-mini
Complex refactoringclaude-opus-4-5, gpt-5.1-codex-max

​
Rule Files

All agents use rule files (AGENTS.md, tembo.md, .cursorrules, etc.) to understand your coding standards. See Rule Files for details.

​
Configuration

Set your coding agent via:
  • Dashboard Settings — Default for all tasks
  • API — Specify per-task with agent key
  • Integration Settings — Per-integration preferences

​
Troubleshooting

Task taking too long? Break into smaller tasks, or use a faster model (Sonnet/Haiku instead of Opus). Unexpected output? Check your rule files, add more context to task descriptions, or use the Feedback Loop via PR comments. Model unavailable? Verify the model ID or omit it to use the default. Contact support@tembo.io if issues persist.