Continue
Last updated
Continue (the open-source VS Code / JetBrains extension and CLI) configures models declaratively in config.yaml. Point one or more model blocks at Tempr Gateway's apiBase and you can list Claude, GPT, Gemini, and anything else on your allowlist side by side — one key, every provider, no separate config block per vendor's own API.
-
Create a virtual key
In the Portal, create a Gateway virtual key. Keys are prefixed
tvk_and shown once at creation. -
Add a provider key
Gateway is BYOK: add a key for at least one provider from the supported list.
-
Edit config.yaml
Open Continue's
config.yaml(Continue extension → gear icon → Open config, or~/.continue/config.yaml) and add a model block:
models:
- name: Tempr Gateway
provider: openai
model: anthropic/claude-sonnet-4-5
apiBase: https://api.temprhq.io/v1
apiKey: tvk_...
roles:
- chat
- edit
- apply
Model ids
Use the fully-qualified provider/model form (e.g. anthropic/claude-sonnet-4-5, openai/gpt-5) — the same ids GET /v1/models returns. Add one model block per model you want selectable.
Embeddings for codebase context
Continue indexes your codebase with an embedding model, for its codebase context. Give that role to a model on Tempr too, and the index is built with your own provider key through the same virtual key:
models:
- name: Tempr Embeddings
provider: openai
model: openai/text-embedding-3-small
apiBase: https://api.temprhq.io/v1
apiKey: tvk_...
roles:
- embed
Any embedding model Tempr serves works, such as google/gemini-embedding-001, mistral/codestral-embed or cohere/embed-v4.0, as long as it's on your virtual key's allowlist. Switching embedding models means Continue re-indexes.
What's next
- Authentication & virtual keys — scoping keys with model allowlists, budgets, and rate limits.
- Embeddings — the providers and models the
embedrole can use. - Models, limits & logs — request logs and analytics for everything you send through the gateway.