Modellix LLM Overview

Modellix LLM is a text 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.

LLM text runs on https://llm.modellix.ai. Image, video, and speech generation use the media API at 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. Availability follows the console.

Models & Pricing

Pass model as a provider/name ID (for example openai/gpt-5.6-sol). Prices below are USD per 1M tokens. In each cell, the strikethrough amount is the official vendor list price; the following amount is what Modellix charges. Supported LLMs:

Model ID	Discount
`openai/gpt-5.6-sol`	20% OFF
`openai/gpt-5.6-terra`	20% OFF
`openai/gpt-5.6-luna`	20% OFF
`openai/gpt-5.5`	20% OFF
`anthropic/claude-opus-5`	3% OFF
`anthropic/claude-sonnet-5`	3% OFF
`anthropic/claude-haiku-4.5`	3% OFF
`google/gemini-3.6-flash`	15% OFF
`google/gemini-3.5-flash`	15% OFF
`google/gemini-3.1-pro`	15% OFF
`xai/grok-4.5`	—
`xai/grok-4.3`	15% OFF
`moonshot/kimi-k2.7`	5% OFF
`moonshot/kimi-k3`	—
`qwen/qwen3.7-plus`	10% OFF
`qwen/qwen3.7-max`	10% OFF
`qwen/qwen3.8-max`	—
`deepseek/deepseek-v4-flash`	25% OFF
`deepseek/deepseek-v4-pro`	25% OFF
`zai/glm-5.2`	25% OFF

OpenAI

GPT 5.6 Sol

Model ID: openai/gpt-5.6-sol
Discount: 20% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
≤ 272K	~~5.00~~ 4.00	~~30.00~~ 24.00	~~0.50~~ 0.40	~~6.25~~ 5.00
＞ 272K	~~10.00~~ 8.00	~~45.00~~ 36.00	~~1.00~~ 0.80	~~12.50~~ 10.00

GPT 5.6 Terra

Model ID: openai/gpt-5.6-terra
Discount: 20% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
≤ 272K	~~2.00~~ 1.60	~~12.00~~ 9.60	~~0.20~~ 0.16	~~2.50~~ 2.00
＞ 272K	~~4.00~~ 3.20	~~18.00~~ 14.40	~~0.40~~ 0.32	~~5.00~~ 4.00

GPT 5.6 Luna

Model ID: openai/gpt-5.6-luna
Discount: 20% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
≤ 272K	~~0.20~~ 0.16	~~1.20~~ 0.96	~~0.02~~ 0.016	~~0.25~~ 0.20
＞ 272K	~~0.40~~ 0.32	~~1.80~~ 1.44	~~0.04~~ 0.032	~~0.50~~ 0.40

GPT 5.5

Model ID: openai/gpt-5.5
Discount: 20% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
≤ 272K	~~5.00~~ 4.00	~~30.00~~ 24.00	~~0.50~~ 0.40	—
＞ 272K	~~10.00~~ 8.00	~~45.00~~ 36.00	~~4.00~~ 3.20	—

Anthropic

Claude Opus 5

Model ID: anthropic/claude-opus-5
Discount: 3% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~5.00~~ 4.85	~~25.00~~ 24.25	~~0.50~~ 0.485	~~6.25~~ 6.0625

Claude Sonnet 5

Model ID: anthropic/claude-sonnet-5
Discount: 3% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~2.00~~ 1.94	~~10.00~~ 9.70	~~0.20~~ 0.194	~~2.50~~ 2.425

Claude Haiku 4.5

Model ID: anthropic/claude-haiku-4.5
Discount: 3% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~1.00~~ 0.97	~~5.00~~ 4.85	~~0.10~~ 0.097	~~1.25~~ 1.2125

Google

Gemini 3.6 Flash

Model ID: google/gemini-3.6-flash
Discount: 15% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~1.50~~ 1.275	~~7.50~~ 6.375	~~0.15~~ 0.1275	—

Gemini 3.5 Flash

Model ID: google/gemini-3.5-flash
Discount: 15% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~1.50~~ 1.275	~~9.00~~ 7.65	~~0.15~~ 0.1275	—

Gemini 3.1 Pro

Model ID: google/gemini-3.1-pro
Discount: 15% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
≤ 200K	~~2.00~~ 1.70	~~12.00~~ 10.20	~~0.20~~ 0.17	—
＞ 200K	~~4.00~~ 3.40	~~18.00~~ 15.30	~~0.40~~ 0.34	—

xAI

Grok 4.5

Model ID: xai/grok-4.5

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
≤ 200K	2.00	6.00	0.30	—
＞ 200K	4.00	12.00	0.60	—

Grok 4.3

Model ID: xai/grok-4.3
Discount: 15% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
≤ 200K	~~1.25~~ 1.0625	~~2.50~~ 2.125	~~0.20~~ 0.17	—
＞ 200K	~~2.50~~ 2.125	~~5.00~~ 4.25	~~0.40~~ 0.34	—

Moonshot

Kimi K2.7

Model ID: moonshot/kimi-k2.7
Discount: 5% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~0.95~~ 0.9025	~~4.00~~ 3.80	~~0.19~~ 0.1805	—

Kimi K3

Model ID: moonshot/kimi-k3

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	3.00	15.00	0.30	—

Qwen

Qwen 3.7 Plus

Model ID: qwen/qwen3.7-plus
Discount: 10% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~0.32~~ 0.288	~~1.28~~ 1.152	~~0.064~~ 0.0576	~~0.40~~ 0.36

Qwen 3.7 Max

Model ID: qwen/qwen3.7-max
Discount: 10% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~1.475~~ 1.3275	~~4.425~~ 3.9825	~~0.295~~ 0.2655	~~1.844~~ 1.6596

Qwen 3.8 Max

Model ID: qwen/qwen3.8-max

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	2.00	6.00	0.25	2.50

DeepSeek

DeepSeek V4 Flash

Model ID: deepseek/deepseek-v4-flash
Discount: 25% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~0.14~~ 0.105	~~0.28~~ 0.21	~~0.0028~~ 0.0021	—

DeepSeek V4 Pro

Model ID: deepseek/deepseek-v4-pro
Discount: 25% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~0.435~~ 0.3262	~~0.87~~ 0.6525	~~0.0036~~ 0.0027	—

ZAI

GLM 5.2

Model ID: zai/glm-5.2
Discount: 25% OFF

Input Context (tokens)	Input ($)	Output ($)	Cached Read ($)	Cached Write ($)
—	~~1.00~~ 0.75	~~4.40~~ 3.30	~~0.26~~ 0.195	—

Availability and prices can change. Confirm the live catalog and rates in the Modellix console. Billing uses token usage on successful responses.

Quick Start

Get an API Key

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

Pick a Protocol and Base URL

Client type	Base URL	Protocol
OpenAI SDK, OpenAI Agents SDK, Microsoft Agent Framework, LangChain, Vercel AI SDK, Mastra, CrewAI, Agno, Codex, Cursor, OpenCode, OpenClaw, Hermes, Junie, Pi, CodeBuddy, WorkBuddy, Qwen Code, Kilo Code, Cline, CC Switch (Codex / OpenAI apps)	`https://llm.modellix.ai/v1`	Chat Completions (or Responses)
Anthropic SDK, Claude Code, Claude Agent SDK, CC Switch (Claude)	`https://llm.modellix.ai` (no `/v1`)	Messages

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.

Codex

openai_base_url in ~/.codex/config.toml.

Claude Code

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

Claude Agent SDK

ANTHROPIC_BASE_URL without /v1 for the Agent SDK harness.

Cursor

OpenAI-compatible provider pointed at the LLM gateway.

OpenCode

Provider baseURL for OpenAI- or Anthropic-compatible mode.

OpenClaw

Custom models.providers entry 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.

Pi

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

CodeBuddy

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

WorkBuddy

Custom OpenAI-compatible model pointed at the LLM gateway.

Qwen Code

OPENAI_BASE_URL or modelProviders pointed at the LLM gateway.

Kilo Code

Custom OpenAI Compatible provider in kilo.jsonc 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:

Endpoint	Docs
`POST /v1/chat/completions`	Chat Completions
`POST /v1/responses`	Responses
`POST /v1/messages`	Messages

Protocol Cheat Sheet

	Chat Completions	Responses	Messages
Path	`/v1/chat/completions`	`/v1/responses`	`/v1/messages`
Main input	`messages`	`input`	`messages` + optional `system`
Length field	`max_tokens` / `max_completion_tokens`	`max_output_tokens`	`max_tokens` (required)
Best for	Most OpenAI-compatible tools	OpenAI Responses clients	Anthropic-native tools

For full field tables and error codes, see the LLM API guide.

​What You Get

Three protocols

Drop-in clients

One API key

provider/name models

​Models & Pricing

​OpenAI

​GPT 5.6 Sol

​GPT 5.6 Terra

​GPT 5.6 Luna

​GPT 5.5

​Anthropic

​Claude Opus 5

​Claude Sonnet 5

​Claude Haiku 4.5

​Google

​Gemini 3.6 Flash

​Gemini 3.5 Flash

​Gemini 3.1 Pro

​xAI

​Grok 4.5

​Grok 4.3

​Moonshot

​Kimi K2.7

​Kimi K3

​Qwen

​Qwen 3.7 Plus

​Qwen 3.7 Max

​Qwen 3.8 Max

​DeepSeek

​DeepSeek V4 Flash

​DeepSeek V4 Pro

​ZAI

​GLM 5.2

​Quick Start

​Guides in This Section

API guide

OpenAI SDK

Anthropic SDK

LangChain

Vercel AI SDK

Mastra

CrewAI

Agno

OpenAI Agents SDK

Microsoft Agent Framework

Codex

Claude Code

Claude Agent SDK

Cursor

OpenCode

OpenClaw

Hermes

Junie

Pi

CodeBuddy

WorkBuddy

Qwen Code

Kilo Code

Cline

CC Switch

​API Reference

​Protocol Cheat Sheet

What You Get

Models & Pricing

OpenAI

GPT 5.6 Sol

GPT 5.6 Terra

GPT 5.6 Luna

GPT 5.5

Anthropic

Claude Opus 5

Claude Sonnet 5

Claude Haiku 4.5

Google

Gemini 3.6 Flash

Gemini 3.5 Flash

Gemini 3.1 Pro

xAI

Grok 4.5

Grok 4.3

Moonshot

Kimi K2.7

Kimi K3

Qwen

Qwen 3.7 Plus

Qwen 3.7 Max

Qwen 3.8 Max

DeepSeek

DeepSeek V4 Flash

DeepSeek V4 Pro

ZAI

GLM 5.2

Quick Start

Guides in This Section

API Reference

Protocol Cheat Sheet