> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tembo.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Supported models, providers, and BYOK options.

Tembo supports multiple model providers across coding agents. You can access the full managed model catalog during your free trial and on paid plans. You can also connect your own model access with BYOK (Bring Your Own Key) or a ChatGPT, Claude, or SuperGrok subscription.

## 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, xAI, Cursor, OpenRouter, and Neon AI Gateway credentials during your free trial and on paid plans.
* AWS Bedrock and GCP Vertex AI credentials are available during your free trial and on paid plans.
* Tembo still handles orchestration, session context, sandbox execution, and PR automation.

BYOK inference costs \$0 through Tembo. Sessions still use billable cloud VM compute, which draws from your workspace's [usage allowance](https://docs.tembo.io/resources/pricing.md).

### Switch a model between BYOK and Tembo Managed Inference

Workspace admins can change the inference provider for individual models from **Settings -> Models**.

In **Available Models**, use the model's **Inference** dropdown to choose **BYOK** or **Tembo Managed Inference**, when those options are available for that model and workspace.

![Available Models table with the Inference dropdown open for switching between BYOK and Tembo Managed Inference](https://mintcdn.com/test-8862363a/_KF7n4fDwDrxMgZe/images/models/model-provider-toggle.png?fit=max\&auto=format\&n=_KF7n4fDwDrxMgZe\&q=85\&s=00d7d91409141b913e502dbe8ae78bca)

### Neon AI Gateway BYOK support

You can use your existing [Neon AI Gateway](https://neon.com/docs/ai-gateway/overview) credential for model access while your coding agents run in Tembo's cloud.

To connect it, add your Neon AI Gateway credential in **Settings -> Models -> API Keys**. Then choose a supported model for your coding agent.

### Bedrock BYOK support

Tembo supports BYOK with Amazon Bedrock.

To enable it, add:

* **AWS Access Key ID**
* **AWS Secret Access Key**
* **AWS Region**

in **Settings -> Models -> API Keys -> AWS Bedrock**.

![AWS Bedrock BYOK API key fields in Tembo Settings](https://mintcdn.com/test-8862363a/_KF7n4fDwDrxMgZe/images/models/aws-bedrock-byok.png?fit=max\&auto=format\&n=_KF7n4fDwDrxMgZe\&q=85\&s=ece3a4bd442cc4ca0b9661fefcfb30d2)

### GCP Vertex AI BYOK support

Tembo supports BYOK with GCP Vertex AI.

To enable it, add:

* **Service account JSON**
* **Project ID**
* **Location**

in **Settings -> Models -> API Keys -> GCP Vertex AI**.

## Connecting multiple accounts

> [!WARNING]
>
> You can connect multiple accounts to your Tembo user account, but every connected account must be yours and yours alone. Tembo does not condone account sharing. Sharing subscriptions or credentials with other users is not allowed and clearly violates vendors' terms of service.

## Connect a ChatGPT subscription

You can connect a ChatGPT subscription during your free trial or on a paid plan to use supported OpenAI models with Codex, OpenCode, Pi, or fx. You need a ChatGPT Plus, Pro, Business, Edu, or Enterprise plan.

1. Open **Settings > Connected accounts**.
2. Under **LLM subscriptions**, click **Connect Codex**.
3. Copy the authorization code, then click **Open authorization page**.
4. Enter the code in ChatGPT and approve the connection. Keep the Tembo dialog open while authorization completes.
5. Return to Tembo and confirm that **ChatGPT Codex** shows **Connected**.

> [!NOTE]
>
> If prompted, enable device code authorization in [ChatGPT Settings > Security](https://chatgpt.com/settings/security), then try connecting again.

![Connected accounts settings showing a connected ChatGPT Codex subscription under LLM subscriptions](https://mintcdn.com/test-8862363a/KRTyBK_8Is_6dkL_/images/models/chatgpt-codex-connected.png?fit=max\&auto=format\&n=KRTyBK_8Is_6dkL_\&q=85\&s=8d99e70506875ecb27318008b13626cd)

### Connect a workspace ChatGPT subscription

Org admins can connect a single ChatGPT Codex subscription for the whole workspace, instead of (or in addition to) each member connecting their own.

1. Open **Settings > Models**.
2. Under **Subscriptions**, click **Connect Codex**.
3. Copy the authorization code, then click **Open authorization page**.
4. Enter the code in ChatGPT and approve the connection. Keep the Tembo dialog open while authorization completes.

A workspace subscription is the default for supported OpenAI models for all workspace users. If a member has their own personal Codex subscription connected, Tembo prefers that member's personal subscription over the workspace one.

## Reset Codex usage

If your connected ChatGPT subscription has an available usage reset, open the **Connected** dropdown next to ChatGPT Codex in **Settings > Connected accounts** (or **Settings > Models** for a workspace subscription) and select **Use reset**. In the confirmation dialog, click **Use one reset** to reset eligible Codex usage limits. This uses one of the subscription's available resets and cannot be undone. For a workspace subscription, only org admins can redeem a reset, and it affects the shared workspace account.

## Connect a Claude subscription

You can connect a Claude subscription during your free trial or on a paid plan to use supported Anthropic models with Claude Code. You need a Claude subscription that includes Claude Code access. This connection is personal: it applies to your sessions, not other workspace members' sessions.

1. Open **Settings > Connected accounts**.
2. Under **LLM subscriptions**, click **Connect Claude**.
3. Click **Open Anthropic**, sign in to your Claude account, and approve access. Keep the Tembo dialog open.
4. On Anthropic's confirmation page, click **Copy code**.
5. Return to Tembo, paste the authentication code, and click **Connect**.
6. Confirm that **Claude subscription** shows **Connected**, then start a session with Claude Code and a supported Anthropic model.

### Check usage or disconnect

Once connected, the usage panel shows your remaining subscription limits and reset times when Anthropic reports them. Use the refresh button to update the panel. Usage includes activity across your Claude account, not just Tembo sessions.

To disconnect, open the **Connected** menu and select **Disconnect**. If Tembo shows **Reconnect Claude**, repeat the connection steps above.

Subscription-backed inference costs \$0 through Tembo. Your sessions still use billable cloud VM compute, which draws from your workspace's [usage allowance](https://docs.tembo.io/resources/pricing.md).

## Connect a SuperGrok subscription

You can connect a SuperGrok subscription during your free trial or on a paid plan to use Grok models with OpenCode or Pi.

1. Open **Settings > Connected accounts**.
2. Under **LLM subscriptions**, click **Connect SuperGrok**.
3. Open the xAI authorization page and enter the code shown in the dialog.
4. Approve the connection in the xAI authorization page. Keep the Tembo dialog open while authorization completes.
5. Return to Tembo and confirm that **SuperGrok** shows **Connected**.

## Supported models

The table below reflects the models currently supported by Tembo.

Neon AI Gateway is a [BYOK option](#neon-ai-gateway-byok-support), not a separate model. Model availability through the gateway depends on your Neon access and workspace configuration.

| Model | Model ID | Provider | BYOK Required |
| - | - | - | - |
| Opus 5.5 | `claude-opus-5-5` | Anthropic | No |
| Opus 5 | `claude-opus-5` | Anthropic | No |
| Fable 5.2 | `claude-fable-5-2` | Anthropic | No |
| Fable 5.1 | `claude-fable-5-1` | Anthropic | No |
| Fable 5 | `claude-fable-5` | Anthropic | No |
| Sonnet 5.5 | `claude-sonnet-5-5` | Anthropic | No |
| Haiku 5.5 | `claude-haiku-5-5` | Anthropic | No |
| Opus 4.8 | `claude-opus-4-8` | Anthropic | No |
| Opus 4.7 | `claude-opus-4-7` | Anthropic | No |
| Opus 4.6 | `claude-opus-4-6` | Anthropic | No |
| Opus 4.5 | `claude-opus-4-5` | Anthropic | No |
| Haiku 4.5 | `claude-4-5-haiku` | Anthropic | No |
| GPT-6.2 Astra | `gpt-6.2-astra` | OpenAI | Yes |
| GPT-6.2 Sol | `gpt-6.2-sol` | OpenAI | Yes |
| GPT-6.1 Sol | `gpt-6.1-sol` | OpenAI | Yes |
| GPT-6.1 Terra | `gpt-6.1-terra` | OpenAI | Yes |
| GPT-6 Astra | `gpt-6-astra` | OpenAI | Yes |
| GPT-6 Sol | `gpt-6-sol` | OpenAI | Yes |
| GPT-6 Luna | `gpt-6-luna` | OpenAI | Yes |
| GPT-5.6 Sol | `gpt-5.6-sol` | OpenAI | Yes |
| GPT-5.6 Terra | `gpt-5.6-terra` | OpenAI | Yes |
| GPT-5.6 Luna | `gpt-5.6-luna` | OpenAI | Yes |
| GPT-5.5 Pro | `gpt-5.5-pro` | OpenAI | Yes |
| GPT-5.5 | `gpt-5.5` | OpenAI | Yes |
| 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 |
| GLM 5.3 | `glm-5p3` | Z.ai | No |
| GLM 5.3 Flash | `glm-5p3-flash` | 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 |
| Composer 2.5 | `composer-2.5` | Cursor | Yes |
| Gemini 3.1 Pro | `gemini-3.1-pro` | Google | No |
| Gemini 3.5 Flash | `gemini-3.5-flash` | Google | No |
| Grok 4.7 | `grok-4.7` | xAI | Yes |
| Kimi K3 | `kimi-k3` | Fireworks | No |
| MiniMax M2.7 | `minimax-m2p7` | MiniMax | No |
| MiniMax M3 | `minimax-m3` | MiniMax | No |
| DeepSeek V4 Pro | `deepseek-v4-pro` | DeepSeek | No |
| DeepSeek V4.1 Flash | `deepseek-v4p1-flash` | DeepSeek | No |

> [!NOTE]
>
> 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.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.