Skip to main content
Modellix LLM is a model gateway at https://llm.modellix.ai. Use one Modellix API key to call OpenAI-compatible Chat Completions and Responses, or Anthropic-compatible Messages, with the same synchronous request model and optional streaming SSE. Some models accept image, audio, or video as input—see Multimodal Inputs.
This gateway returns text. Image, video, and speech generation use https://api.modellix.ai with async tasks—see REST API.

What You Get

Three protocols

Chat Completions, Responses, and Messages—each with its own URL and request body. Do not mix fields across protocols.

Drop-in clients

Point OpenAI or Anthropic SDKs, Codex, Claude Code, Cursor, and OpenCode at Modellix with a base URL override.

One API key

Authenticate with Bearer or x-api-key using a Modellix key from the console—not a vendor platform key.

provider/name models

Pass model IDs like openai/gpt-5.5, anthropic/claude-sonnet-5, or google/gemini-3.6-flash. See Modellix LLM for current IDs and prices.

Models & Pricing

Pass model as a provider/name ID (for example openai/gpt-5.6-sol). You can also use a Latest Model ID such as ~openai/gpt-latest to always call the current flagship in that series—Modellix updates the routing when newer versions ship. For the current Model ID list (including Latest Model IDs), Input Context tiers, discounts, and USD-per-1M-token rates, use the Modellix LLM page.

LLM Models and Pricing

Filter by provider and input modality, compare official list prices with Modellix rates, and estimate a call with the cost calculator. Billing uses token usage on successful responses.

Quick Start

1

Get an API Key

Create a key in the Modellix console and store it securely.
2

Pick a Protocol and Base URL

3

Send a Request

Use your SDK or a curl example from the API guide. Always set model to a provider/name ID.

Guides in This Section

Start with the API guide for protocols, auth, errors, and billing. Then open the client page that matches your stack.

API guide

Protocols, curl examples, session header, errors, rate limits, and billing.

OpenAI SDK

OPENAI_BASE_URL + Modellix key for Chat Completions and Responses.

Anthropic SDK

ANTHROPIC_BASE_URL without /v1 for Messages.

LangChain

ChatOpenAI with base_url pointed at the LLM gateway.

Vercel AI SDK

createOpenAICompatible with baseURL pointed at the LLM gateway.

Mastra

Custom OpenAI-compatible model.url pointed at the LLM gateway.

CrewAI

LLM with base_url and custom_openai pointed at the LLM gateway.

Agno

OpenAILike with base_url pointed at the LLM gateway.

OpenAI Agents SDK

Custom AsyncOpenAI client + Chat Completions for agents.

Microsoft Agent Framework

OpenAIChatCompletionClient with base_url pointed at the LLM gateway.

Claude Code

Environment variables or ~/.claude/settings.json.

CodeBuddy

Custom model Endpoint or models.json pointed at Chat Completions.

Codex

openai_base_url in ~/.codex/config.toml.

Claude Agent SDK

ANTHROPIC_BASE_URL without /v1 for the Agent SDK harness.

Cursor

OpenAI-compatible provider pointed at the LLM gateway.

DeepSeek Harness

Custom provider in the Web UI or settings.yaml pointed at the LLM gateway.

Hermes

Custom Endpoint in config.yaml pointed at the LLM gateway.

Junie

Custom LLM JSON profile pointed at Chat Completions.

Kilo Code

Custom OpenAI Compatible provider in kilo.jsonc pointed at the LLM gateway.

OpenClaw

Custom models.providers entry pointed at the LLM gateway.

OpenCode

Provider baseURL for OpenAI- or Anthropic-compatible mode.

Pi

Custom provider in models.json pointed at the LLM gateway.

Qwen Code

OPENAI_BASE_URL or modelProviders pointed at the LLM gateway.

WorkBuddy

Custom OpenAI-compatible model pointed at the LLM gateway.

Cline

OpenAI Compatible provider pointed at the LLM gateway.

CC Switch

Custom provider for Claude Code, Codex, and OpenAI Compatible apps.

API Reference

OpenAPI pages for the three endpoints live under API Reference → LLM:

Protocol Cheat Sheet

google/... (Gemini) models use Chat Completions or Responses, not Messages. For full field tables and error codes, see the LLM API guide.