Model Registry
Platform models and bring-your-own-key (BYOK) custom model configuration.
The Model Registry manages the LLM models available in your organization. Pipelines ships a set of platform models (served through our OpenRouter integration — no keys to manage), and lets your org add custom models with its own credentials.
Open Models in the left sidebar to see every model available to your org.
Platform models
| Display name | Model ID |
|---|---|
| GPT 5.4 | openai/gpt-5.4 |
| GPT 5.2 | openai/gpt-5.2 |
| GPT 5 Mini | openai/gpt-5-mini |
| Claude Opus 4.6 | anthropic/claude-opus-4.6 |
| Claude Sonnet 4.6 | anthropic/claude-sonnet-4.6 |
| Gemini 3.1 Pro | google/gemini-3.1-pro-preview |
| Gemini 3 Flash | google/gemini-3-flash-preview |
| Grok 4 | x-ai/grok-4 |
| Grok 4.1 Fast | x-ai/grok-4.1-fast |
The default model is Gemini 3.1 Pro. The catalog is updated as providers release new models.
Custom models (BYOK)
Custom models call a provider directly with your own credentials.
Supported providers
| Provider | What you enter |
|---|---|
| Fireworks | API key + provider model ID (e.g. accounts/acme/models/llama-ft-v2) |
| Together AI | API key + provider model ID (e.g. meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo) |
| Bedrock | AWS region + either an IAM key pair (Access Key ID + Secret Access Key) or a Bedrock API key; provider model ID (e.g. anthropic.claude-3-5-sonnet-20240620-v1:0) |
| HuggingFace | API token + Inference Endpoint URL + provider model ID |
| OpenAI-compatible | Base URL (required) + optional API key + provider model ID. Use this for any OpenAI-style endpoint — self-hosted vLLM, Ollama, or a hosted OpenAI/Anthropic-compatible gateway. |
Adding a custom model
The Add Custom Model dialog collects:
- Provider — the form adapts to the provider you pick.
- Credentials — the fields required by the selected provider (see above).
- Provider Model ID — the ID the upstream provider expects.
- Display Name — the Model Slug is auto-derived from this and is what workflow configurations reference.
- Max Tokens and the capability switches (see below), matching what the underlying model supports.
- Input / Output cost per token (optional) — used for cost tracking. If left blank, Test Connection may suggest values based on known pricing.
Test Connection makes a small live call with the entered credentials; saving is gated on it succeeding. If another model already uses the same credentials, the dialog offers Reuse saved credentials.
Custom model capabilities
Capability switches drive what the model is offered for in the Pipeline Builder and how Pipelines forwards requests. Set them based on what the upstream provider documents — incorrect flags can cause runtime errors or silently ignored parameters.
| Capability | Meaning |
|---|---|
| JSON mode | Provider natively supports structured JSON responses. |
| Vision | Model can process image inputs. |
| Tool use | Model supports function / tool calling. |
| Extended reasoning | Model exposes a thinking / reasoning step. When enabled, also pick the reasoning parameter shape — effort (provider accepts reasoning.effort) or otherwise reasoning.max_tokens. Use effort only if the provider documents an effort-style control. |
Credential security
API credentials are encrypted at rest, never returned in API responses (the UI only sees a masked preview), and are never written to logs.
Model selection in pipelines
In the Pipeline Builder, the model dropdown groups models under Platform and Custom. Each model's capability flags gate features:
- Tool-calling controls are disabled unless the selected model has Tool use on.
- Extended reasoning controls only appear for reasoning-capable models.
Managing custom models
Open a model from the registry for its detail page:
- Edit — update display name, provider model ID, credentials, endpoint URL, max tokens, capabilities, reasoning parameter, and cost overrides. Unlike the Add dialog, Save is not gated on Test Connection — run it yourself after changing credentials or the provider model ID. Leaving the credential field blank during a test reuses the stored credential.
- Delete — deactivates the model. If active workflows still reference it, you'll be warned with a count; those workflows fail to generate LLM responses until repointed.