BYOK (Bring Your Own Key)
BYOK lets your workspace call models with your own provider credentials instead of Tembo-managed credentials.- Add keys in Settings -> Models -> API Keys.
- You can connect OpenAI, Anthropic, Cursor, Amp, and AWS Bedrock credentials.
- Tembo still handles orchestration, task context, sandbox execution, and PR automation.
Bedrock BYOK support
Tembo supports BYOK with Amazon Bedrock. To enable it, add:- AWS Access Key ID
- AWS Secret Access Key
- AWS Region
Supported models
The table below reflects the models currently supported by Tembo.| Model | Model ID | Provider | BYOK Required |
|---|---|---|---|
| Opus 4.6 | claude-opus-4-6 | Anthropic | No |
| Sonnet 4.6 | claude-sonnet-4-6 | Anthropic | No |
| Opus 4.5 | claude-opus-4-5 | Anthropic | No |
| Haiku 4.5 | claude-4-5-haiku | Anthropic | No |
| GPT-5.4 | gpt-5.4 | OpenAI | Yes |
| GPT-5.4 Mini | gpt-5.4-mini | OpenAI | No |
| GPT-5.4 Nano | gpt-5.4-nano | OpenAI | No |
| GPT-5.3 Codex | gpt-5.3-codex | OpenAI | No |
| GPT-5.3 Codex Spark | gpt-5.3-codex-spark | OpenAI | Yes |
| GPT-5.2 Codex | gpt-5.2-codex | OpenAI | No |
| GPT-5.2 | gpt-5.2 | OpenAI | Yes |
| GPT-5.1 Codex Max | gpt-5.1-codex-max | OpenAI | Yes |
| GPT-5.1 Codex Mini | gpt-5.1-codex-mini | OpenAI | Yes |
| GPT-5.1 Codex | gpt-5.1-codex | OpenAI | Yes |
| GPT-5.1 | gpt-5.1 | OpenAI | Yes |
| GPT-5 Codex | gpt-5-codex | OpenAI | Yes |
| GPT-5 | gpt-5 | OpenAI | Yes |
| GPT-5 High | gpt-5-high | OpenAI | Yes |
| GPT-5 Medium | gpt-5-medium | OpenAI | Yes |
| GPT-5 Low | gpt-5-low | OpenAI | Yes |
| GPT-5 Minimal | gpt-5-minimal | OpenAI | Yes |
| GPT-oss 120B | gpt-oss-120b | OpenAI | No |
| GLM 5 | zai-glm-5 | Z.ai | No |
| GLM 4.7 | zai-glm-4.7 | Z.ai | No |
| Composer 1.5 | composer-1.5 | Cursor | Yes |
| Composer 2 | composer-2 | Cursor | Yes |
| Composer 2 Fast | composer-2-fast | Cursor | Yes |
| Gemini 3 Pro | gemini-3-pro | No | |
| Gemini 3.1 Pro | gemini-3.1-pro | No | |
| Gemini 3 Flash | gemini-3-flash | No | |
| Grok | grok | xAI | Yes |
| Kimi K2.5 | kimi-k2p5 | Fireworks | No |
| MiniMax M2.5 | minimax-m2p5 | MiniMax | No |
| Qwen 3 32B | qwen-3-32b | Qwen | No |
| Llama 3.3 70B | llama-3.3-70b | Meta | No |
Model availability can vary by agent and workspace configuration. If a model is disabled in your workspace, it will not appear in agent pickers until re-enabled.