Codebase Inference API
The Inference API from Codebase — 1 operation(s) for inference.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/codebase-design:codebase-design-inference-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: Codebase Design Inference API
version: 1.0.0
contact:
email: admin@aipowergrid.io
description: 'Operations tagged Inference across 2 of this provider''s published API definitions: codebase-design-openapi.json, codebase-design-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: http://localhost:3001
description: Current
- url: https://dev.codebase.design
description: Development
- url: https://staging.codebase.design
description: Staging
- url: https://codebase.design
description: Production
security:
- ApiKeyAuth: []
- BearerAuth: []
tags:
- name: Inference
paths:
/api/v1/inference/chat:
post:
summary: LLM chat completion
description: Proxy a chat completion request to the configured LLM provider. Supports streaming (SSE) and non-streaming responses. Automatic fallback rechecks model access and balance; each attempt is billed at its served model. Streaming responses end with token usage and a codebase_billing receipt before [DONE].
tags:
- Inference
security:
- ApiKeyAuth: []
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- model
- messages
properties:
model:
type: string
description: Model ID from /api/v1/models
messages:
type: array
items:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- system
- user
- assistant
content:
type: string
stream:
type: boolean
default: false
temperature:
type: number
minimum: 0
maximum: 2
default: 0.7
max_tokens:
type: integer
default: 4096
responses:
'200':
description: Chat completion (JSON or SSE stream)
content:
application/json:
schema:
type: object
properties:
id:
type: string
object:
type: string
created:
type: integer
model:
type: string
description: Model that served the final response; may differ after automatic fallback.
choices:
type: array
items:
type: object
properties:
index:
type: integer
message:
type: object
properties:
role:
type: string
content:
type: string
finish_reason:
type: string
usage:
type: object
properties:
prompt_tokens:
type: integer
completion_tokens:
type: integer
total_tokens:
type: integer
prompt_tokens_details:
type: object
properties:
cached_tokens:
type: integer
cache_write_tokens:
type: integer
codebase_billing:
type: object
properties:
credits_charged:
type: integer
nullable: true
description: Acknowledged charge across attempts; null when settlement could not be confirmed.
usage_estimated:
type: boolean
description: True when any attempt was charged from its reservation because provider usage was unavailable. Token usage itself contains only reported counts.
'400':
$ref: '#/components/responses/BadRequest'
'401':
$ref: '#/components/responses/Unauthorized'
'402':
description: 'The account cannot pay for the call (`error: insufficient_credits`), or the
API key has used its spending limit (`code: key-budget-exhausted`). The call''s
actual cost is debited after it finishes and counts toward the key''s limit, so
a key can end past its limit by at most one call''s cost.
'
'500':
description: Internal server error
'503':
description: Credit service could not authorize an automatic fallback. No request is sent to that fallback model.
x-codeSamples:
- lang: TypeScript
label: TypeScript
source: "// Auth: X-API-Key header.\nconst apiKey = process.env.CODEBASE_API_KEY!;\n\nconst res = await fetch('https://codebase.design/api/v1/inference/chat', {\n method: 'POST',\n headers: {\n 'X-API-Key': apiKey,\n 'Content-Type': 'application/json',\n },\n body: JSON.stringify({\n \"model\": \"string\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"string\"\n }\n ],\n \"stream\": false,\n \"temperature\": 0.7,\n \"max_tokens\": 4096\n })\n});\n\nif (!res.ok) throw new Error(`${res.status} ${await res.text()}`);\nconst data = await res.json();\nconsole.log(data);"
- lang: Python
label: Python
source: "import os\nimport requests\n\napi_key = os.environ['CODEBASE_API_KEY']\n\nresponse = requests.post(\n 'https://codebase.design/api/v1/inference/chat',\n headers={\n 'X-API-Key': api_key,\n 'Content-Type': 'application/json',\n },\n json={\n \"model\": \"string\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"string\"\n }\n ],\n \"stream\": false,\n \"temperature\": 0.7,\n \"max_tokens\": 4096\n }\n)\nresponse.raise_for_status()\nprint(response.json())"
- lang: Rust
label: Rust
source: "// Cargo.toml:\n// reqwest = { version = \"0.12\", features = [\"json\"] }\n// serde_json = \"1\"\n// tokio = { version = \"1\", features = [\"full\"] }\n\nuse std::env;\n\n#[tokio::main]\nasync fn main() -> Result<(), Box<dyn std::error::Error>> {\n let api_key = env::var(\"CODEBASE_API_KEY\")?;\n let client = reqwest::Client::new();\n\n let res = client\n .post(\"https://codebase.design/api/v1/inference/chat\")\n .header(\"X-API-Key\", api_key)\n .header(\"Content-Type\", \"application/json\")\n .json(&serde_json::json!({\n \"model\": \"string\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"string\"\n }\n ],\n \"stream\": false,\n \"temperature\": 0.7,\n \"max_tokens\": 4096\n }))\n .send()\n .await?;\n\n let data: serde_json::Value = res.json().await?;\n println!(\"{:#?}\", data);\n Ok(())\n}"
operationId: postApiV1InferenceChat
x-operation-id-source: derived
servers:
- url: http://localhost:3001
description: Current
- url: http://localhost:3001
description: Local development
- url: https://dev.codebase.design
description: Development
- url: https://staging.codebase.design
description: Staging
- url: https://codebase.design
description: Production
components:
responses:
BadRequest:
description: Invalid request parameters
content:
application/json:
schema:
type: object
properties:
error:
type: string
Unauthorized:
description: Missing or invalid authentication
content:
application/json:
schema:
type: object
properties:
error:
type: string
securitySchemes:
ApiKeyAuth:
type: apiKey
in: header
name: X-API-Key
description: Revocable API key (cb_live_... or cb_test_...)
BearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: OAuth2 access token
x-refined-from:
- codebase-design-openapi.json
- codebase-design-openapi.yml