Models

Overview

The Models API exposes the models that the connected Allternit runtime can serve, along with routing policy aliases and a cross-provider pricing snapshot. Model listings are filtered by the virtual key’s allowlist, so callers only see models they are permitted to use.

Base URL

https://api.allternit.com/v1

For local development:

http://127.0.0.1:8013/v1

Endpoints

Method	Path	Description
`GET`	`/v1/models`	List available models and policy aliases
`GET`	`/v1/models/:id`	Retrieve a single model or policy alias
`GET`	`/v1/pricing`	List per-model pricing

List models

curl https://api.allternit.com/v1/models \
  -H "Authorization: Bearer $ALLTERNIT_API_KEY"

Example response

{
  "object": "list",
  "data": [
    {
      "id": "auto",
      "object": "model",
      "created": 0,
      "owned_by": "allternit"
    },
    {
      "id": "allternit-balanced",
      "object": "model",
      "created": 0,
      "owned_by": "allternit"
    },
    {
      "id": "provider/model-id",
      "object": "model",
      "created": 1704067200,
      "owned_by": "provider",
      "context_window": 128000,
      "max_output_tokens": 4096,
      "deprecated": false,
      "replacement": null
    }
  ]
}

Model object fields

Field	Type	Description
`id`	string	Model id or policy alias.
`object`	string	`model`.
`created`	integer	Release-date timestamp, or `0` for aliases.
`owned_by`	string	Provider id, or `allternit` for aliases.
`context_window`	integer	Maximum context tokens, when known.
`max_output_tokens`	integer	Maximum output tokens, when known.
`deprecated`	boolean	Whether the model is deprecated.
`replacement`	string	Recommended replacement id, if deprecated.

Policy aliases

Policy aliases are synthetic models that trigger the gateway’s benchmark-weighted router. The router picks a concrete provider/model pair and derives a cross-provider fallback chain.

Alias	Optimization target
`auto`	Same as `allternit-balanced`.
`allternit-balanced`	Balanced quality and cost across all benchmarks.
`allternit-code`	Coding and software-engineering tasks.
`allternit-reasoning`	Reasoning, math, and science tasks.
`allternit-knowledge`	Knowledge and recall tasks.
`allternit-instruct`	Instruction-following and chat quality.

Retrieve a model

curl https://api.allternit.com/v1/models/allternit-balanced \
  -H "Authorization: Bearer $ALLTERNIT_API_KEY"

{
  "id": "allternit-balanced",
  "object": "model",
  "created": 0,
  "owned_by": "allternit"
}

If the model does not exist or is not in the key’s allowlist, the gateway returns a 404 with code allternit.model_not_found.

Pricing

GET /v1/pricing returns the current per-model rates in dollars per 1 million tokens.

curl https://api.allternit.com/v1/pricing \
  -H "Authorization: Bearer $ALLTERNIT_API_KEY"

{
  "object": "list",
  "data": [
    {
      "id": "provider/model-id",
      "object": "model_pricing",
      "input": 2.50,
      "output": 10.00,
      "cache_read": 1.25,
      "cache_write": 0.00,
      "context_over_200k": null
    }
  ]
}

Pricing fields

Field	Type	Description
`id`	string	`provider/model` id.
`object`	string	`model_pricing`.
`input`	number	Input-token price per 1M tokens.
`output`	number	Output-token price per 1M tokens.
`cache_read`	number	Cache-read price per 1M tokens.
`cache_write`	number	Cache-write price per 1M tokens.
`context_over_200k`	object	Higher rates when input plus cache read exceeds 200k tokens.

Error codes

HTTP status	Code	Meaning
401	`allternit.authentication_failed`	Missing or invalid API key.
404	`allternit.model_not_found`	Model not found or not allowed.
429	`allternit.rate_limited`	Per-key rate limit exceeded.
429	`allternit.budget_exceeded`	Monthly key or tenant budget exhausted.
500	`allternit.internal_error`	Internal gateway error.

Chat Completions — use models and aliases in completions
Proxy — how the gateway routes model requests
Translate — wire-format translation details

Overview

LLM Gateway

Agents & Runtime

Work Queue & Deployments

Files, Webhooks & Sandbox

Tools & Connectors

Collaboration & Workflows

Infrastructure & Platform

Canvases

Onboarding

A Labs

Playground

Users & Profiles

Overview

Base URL

Endpoints

List models

Example response

Model object fields

Policy aliases

Retrieve a model

Pricing

Pricing fields

Error codes

​Overview

​Base URL

​Endpoints

​List models

​Example response

​Model object fields

​Policy aliases

​Retrieve a model

​Pricing

​Pricing fields

​Error codes

​Related pages

Overview

Base URL

Endpoints

List models

Example response

Model object fields

Policy aliases

Retrieve a model

Pricing

Pricing fields

Error codes

Related pages