Continue with the AI Stupid Level Smart Router

One block in ~/.continue/config.yaml gives Continue’s chat, edit and apply roles a benchmark-routed model: your own provider keys, no token markup, and the model that answered in every response header.

Routing on benchmark results

A routing mode as the model name sends each request to the model placing highest on the relevant board — coding, reasoning or tool use — ranked on the average of its last five benchmark runs, never a single run. Statistically tied leaders are split by your tie-break preference, the cheaper measured cost per task by default. Drift-aware routing moves a model whose drift detector has fired for that skill behind every unflagged model.

Your own provider keys

You pay OpenAI, Anthropic, Google, DeepSeek, Moonshot AI (Kimi) or Z.ai (GLM) directly for tokens. Provider keys are encrypted at rest (AES-256-GCM) and never shown again.

No token markup

The router adds nothing to token prices. Free includes 1,000 routed requests a month, and only successful requests count.

The model that answered, every time

Every response carries X-AISM-Model and X-AISM-Reasoning: which model answered and why, including any fallback. If the chosen model fails before answering, the router tries your own fallback order, then up to 2 automatic fallbacks from different providers.

1. 01

   Create a router key

   Go to API keys, click Create key and copy it somewhere safe. The key starts with aism_ and is the one key for every tool you connect.

2. 02

   Add your provider keys

   Under Providers, add keys for OpenAI, Anthropic, Google, DeepSeek, Kimi or GLM. The more providers you add, the better the routing. You pay them directly for tokens; the router adds nothing to token prices, and provider keys are encrypted at rest (AES-256-GCM) and never shown again.

3. 03

   Add the model block to config.yaml

   Edit ~/.continue/config.yaml: provider: openai, apiBase set to the router and apiKey set to your aism_ key. The roles line gives the same entry to chat, edit and apply.

   ~/.continue/config.yamlYAML

   models:
     - name: ASL auto-coding
       provider: openai
       model: auto-coding
       apiBase: https://aistupidlevel.info/v1
       apiKey: aism_your_key_here
       roles: [chat, edit, apply]

4. 04

   Add more modes as more entries

   Each routing mode is one more entry with its own name and model: auto-tooling for agent work, auto-value-coding to spend less per coding run. Continue lists them by name, and the X-AISM-Model response header names the model that answered.

5. 05

   Optional: embeddings for RAG

   POST /v1/embeddings proxies to OpenAI’s embedding models, text-embedding-3-small (also auto-embedding) and text-embedding-3-large, which Continue uses for its RAG features. It requires an active OpenAI provider key, and each call counts as one request against your plan.

auto-coding

Coding. Best for code generation, debugging, refactoring.Top of the Coding board in the last 24 hours: DeepSeek V4.1 Flash, in a statistical tie for first place, of 22 ranked models.

auto-value-coding

Value. Most coding points per dollar (measured cost of a coding run), near-top models only.

auto-tooling

Tool use. Best at calling tools correctly — scored on our tool-calling suite.Top of the Tool use board in the last 24 hours: DeepSeek V4 Pro, in a statistical tie for first place, of 22 ranked models.

24-hour boards as of 26 Oct 2026, 10:51 UTC · places follow the leaderboard’s statistical ties · the full leaderboard

• Model dropdowns are filled from GET /v1/models, which needs a valid aism_ key.
• Embeddings for RAG go through POST /v1/embeddings, which requires an active OpenAI provider key; supported models are text-embedding-3-small (also auto-embedding) and text-embedding-3-large.
• Streaming is real: text arrives as the model writes it (X-AISM-Streaming-Mode: native).
• Text only: a request with images, audio or files gets a 400 unsupported_content.

401 invalid_api_key

Missing or invalid aism_ key. Check the key is correct and not revoked, and that the tool sends it as Authorization: Bearer aism_…. If a field insists on an sk- prefix, sk-aism_… is accepted: the prefix is stripped automatically. A key that had an expiry date and passed it gets 401 expired_api_key, and the message says when.

400 model_not_found

An unknown auto-* name is a 400 that lists the valid routing modes. For a real model id, check the spelling: direct pin routing infers the provider from the model name prefix, and GET /v1/models lists every id you can use.

No models in the dropdown

The tool fills its list from GET /v1/models, which requires a valid aism_ key. Check that the key and the base URL https://aistupidlevel.info/v1 are both in place.

400 provider_key_rejected or no_provider_keys

Your provider key is missing or was refused. Add or update it under Providers, re-check it on the provider’s dashboard, and make sure it has active credits and the right permissions.

Streaming

Set stream: true. Text arrives as the model writes it (X-AISM-Streaming-Mode: native); tool calls arrive in one chunk each once the model has finished them, then the finish reason, then usage if you set stream_options.include_usage. If the chosen model fails before sending anything, or its provider sends nothing for 120 seconds, the next fallback is tried.

400 unsupported_content

The router routes text only, on purpose: it picks a model from benchmark results for coding, reasoning and tool use, and none of those measure image, audio or file understanding. Send such requests to the provider directly.

429 allowance_exhausted

This month’s requests are used up and you have no prepaid credits. Credits top up the allowance; moving up a plan is the cheaper way to buy regular volume.