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

# Create an LLM config

> Creates a named LLM config that you own, optionally storing the referenced API-key secret and marking it as your default.



## OpenAPI

````yaml /api-reference/openapi.json post /api/llm-configs
openapi: 3.1.0
info:
  title: Nasiko API
  description: >-
    HTTP API for the Nasiko OpenRuntime: agents, coding harnesses, TokenOps,
    routing, MCP, and secrets. Spec is generated from annotated routes; some
    surfaces are documented on the hand-written pages alongside this file.
  license:
    name: ''
  version: 0.1.0
servers:
  - url: https://free.app.nasiko.com
    description: Nasiko Cloud Free
  - url: https://{workspace}.app.nasiko.com
    description: Nasiko Cloud paid workspace
    variables:
      workspace:
        default: your-workspace
        description: >-
          Your workspace's subdomain, as shown in the connect command on the
          dashboard's Nasiko CLI page
security:
  - bearer_auth: []
tags:
  - name: secrets
    description: Encrypted per-user agent secrets
  - name: catalog
    description: >-
      Agent catalog: registration, discovery, versions, per-agent secrets, and
      source import
  - name: agents
    description: >-
      Agent lifecycle: deployments, LLM routing config, update/rollback,
      upload-and-deploy
  - name: orchestrator
    description: >-
      A2A dispatch: routing-engine/ReAct orchestrator and direct agent chat,
      plus routing stats
  - name: users
    description: >-
      User management: CRUD, roles, credentials, accessible agents
      (superuser-only)
  - name: usage
    description: Per-user token usage and cost reporting
  - name: observability
    description: Sessions, traces, spans, agent logs, and FinOps reporting
  - name: llm-router
    description: LLM routing presets, provider/model catalog, and tier→model registry
  - name: context-selection
    description: >-
      Per-user chat-history selection preferences: strategy, PACMS budget tier,
      the on/off switch, a dry-run preview, and settings-change history
  - name: coding-agents
    description: >-
      The progress local clients report while they bring in the caller's coding
      agents
  - name: settings
    description: >-
      Workspace-wide settings, including the Optimization tiers a user's PACMS
      budget level resolves against
  - name: mcp
    description: >-
      MCP gateway: agent-facing JSON-RPC tool calls, connector
      registration/upload/sharing, credentials & OAuth, and per-agent tool
      permissions
paths:
  /api/llm-configs:
    post:
      tags:
        - llm-router
      summary: Create an LLM config
      description: >-
        Creates a named LLM config that you own, optionally storing the
        referenced API-key secret and marking it as your default.
      operationId: create
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateLlmConfigRequest'
        required: true
      responses:
        '201':
          description: >-
            `data` is the created config object (id, name, provider, model,
            fallback_models, temperature, max_tokens, api_key_secret_name,
            pinned, pinned_model, tier1_model, tier2_model, tier3_model,
            embedding_provider, embedding_model, embedding_api_key_secret_name,
            embedding_model_override, is_default, created_at, updated_at)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/McpEnvelope'
        '400':
          description: >-
            Validation failed (name/provider/model/pinned_model/secret, or
            embedding_provider/embedding_model not set together)
        '401':
          description: Missing or invalid session
        '409':
          description: A config with this name already exists
components:
  schemas:
    CreateLlmConfigRequest:
      type: object
      required:
        - name
        - provider
      properties:
        api_key_secret_name:
          type:
            - string
            - 'null'
          description: >-
            Name of your secret that holds the provider API key. Omit it to use
            the server's provider key.
        confirm_embedding_change:
          type: boolean
          description: >-
            Accepted for client uniformity and ignored: a create has no previous
            embedding

            model, so there is never anything to confirm.
        embedding_api_key_secret_name:
          type:
            - string
            - 'null'
        embedding_model:
          type:
            - string
            - 'null'
        embedding_model_override:
          type: boolean
          description: >-
            When true, this config's `embedding_model` outranks the model an
            agent names on

            its own `POST /v1/embeddings` request.
        embedding_provider:
          type:
            - string
            - 'null'
          description: >-
            Embedding destination — independent of the chat provider/model
            above. Set the

            provider and model together or not at all; the secret name is
            optional and means

            "use the platform key for this provider" when absent.
        embedding_secret_value:
          type:
            - string
            - 'null'
          description: >-
            Plaintext key to store under `embedding_api_key_secret_name` when no
            such secret

            exists yet — the embedding-side twin of `secret_value`.
        fallback_models:
          type: array
          items:
            type: string
        is_default:
          type: boolean
          description: Mark this as the caller's default (clears any prior default).
        max_tokens:
          type:
            - integer
            - 'null'
          format: int64
        model:
          type:
            - string
            - 'null'
        name:
          type: string
        pinned:
          type: boolean
        pinned_model:
          type:
            - string
            - 'null'
        provider:
          type: string
        secret_value:
          type:
            - string
            - 'null'
          description: >-
            Plaintext key to store under `api_key_secret_name` when no such
            secret exists yet.

            Required when the named secret is absent; ignored (as an upsert)
            when it already exists.
        temperature:
          type:
            - number
            - 'null'
          format: double
        tier1_model:
          type:
            - string
            - 'null'
          description: >-
            Per-config tier-to-model override. When set, the LLM router uses it
            instead of the model registry for this config's provider.
        tier2_model:
          type:
            - string
            - 'null'
        tier3_model:
          type:
            - string
            - 'null'
    McpEnvelope:
      type: object
      description: >-
        Standard MCP response envelope: `{"data": …, "status_code": N,
        "message": "…"}`. `data` is a free-form object; each route's response
        description says what it contains.
      required:
        - data
        - status_code
        - message
      properties:
        data:
          type:
            - object
            - 'null'
        message:
          type: string
        status_code:
          type: integer
          format: int32
          example: 200
          minimum: 0
  securitySchemes:
    bearer_auth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: >-
        Session JWT. After `nasiko auth login`, print it with `jq -r
        '.clusters[.active].token' ~/.nasiko/config.json`. API keys aren't
        supported.

````

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