Use Inference APIs with Continue (VS Code / JetBrains)

Add Inference APIs models to Continue with provider: openai and an apiBase. Works for chat, edit and autocomplete roles.

Settings

Setting	Value
Base URL	`https://api.inferenceapis.com/v1` (also `/openai/v1`)
API key	From API Keys; send as `Authorization: Bearer …`
Chat model ids	`openai/gpt-oss-120b`, `deepseek-ai/DeepSeek-V4-Flash`, `zai-org/GLM-5.3-Flash`, `meta-llama/Llama-3.3-70B-Instruct-Turbo` — all models
Audio model ids	`openai/whisper-large-v3` (transcription), `hexgrad/Kokoro-82M` (speech)

Configuration

config.yaml

name: Inference APIs
version: 0.0.1
models:
  - name: GPT-OSS 120B
    provider: openai
    model: openai/gpt-oss-120b
    apiBase: https://api.inferenceapis.com/v1
    apiKey: ${{ secrets.INFERENCE_API_KEY }}
    roles: [chat, edit]
    defaultCompletionOptions:
      maxTokens: 1200
  - name: DeepSeek V4 Flash
    provider: openai
    model: deepseek-ai/DeepSeek-V4-Flash
    apiBase: https://api.inferenceapis.com/v1
    apiKey: ${{ secrets.INFERENCE_API_KEY }}
    roles: [chat, edit, apply]

Verify

Open the Continue sidebar, pick "GPT-OSS 120B", send "ping".

Gotchas

Autocomplete works best with a fast small model; DeepSeek V4 Flash is the cheapest option here.

If something fails

401 — key missing or wrong · 402 insufficient_balance — add credits on Billing · 404 model_not_found — check the id against the model list (aliases such as gpt-oss-120b work too) · 503 model_unavailable — the model is being enabled. Full details in the API docs.