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

# Modellix LLM Overview

> Get started with the Modellix LLM gateway—OpenAI-compatible Chat Completions and Responses, Anthropic-compatible Messages, and guides for SDKs and coding tools.

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.

<Note>
  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](/ways-to-use/api).
</Note>

## What you get

<Columns cols={2}>
  <Card title="Three protocols" icon="layers">
    Chat Completions, Responses, and Messages—each with its own URL and request
    body. Do not mix fields across protocols.
  </Card>

  <Card title="Drop-in clients" icon="plug">
    Point OpenAI or Anthropic SDKs, Codex, Claude Code, Cursor, and OpenCode at
    Modellix with a base URL override.
  </Card>

  <Card title="One API key" icon="key">
    Authenticate with Bearer or `x-api-key` using a Modellix key from the
    [console](https://modellix.ai/console/api-key)—not a vendor platform key.
  </Card>

  <Card title="provider/name models" icon="boxes">
    Pass model IDs like `openai/gpt-5.5`, `anthropic/claude-sonnet-5`, or
    `google/gemini-3.6-flash`. Availability follows the console.
  </Card>
</Columns>

<h2 id="models-and-pricing">
  Models & Pricing
</h2>

Pass `model` as a `provider/name` ID (for example `openai/gpt-5.6-sol`). Prices below are **USD per 1M tokens**. Official is the vendor list price; Modellix is what you are charged.

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`               | 15% OFF  |
| `xai/grok-4.3`               | 15% OFF  |

### OpenAI

#### GPT 5.6 Sol

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

Input Context ≤ 272K

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$5.00 | \$30.00 | \$0.50      | \$6.25       |
| Modellix | \$4.00 | \$24.00 | \$0.40      | \$5.00       |

Input Context ＞ 272K

|          | Input   | Output  | Cached Read | Cached Write |
| -------- | ------- | ------- | ----------- | ------------ |
| Official | \$10.00 | \$45.00 | \$1.00      | \$12.50      |
| Modellix | \$8.00  | \$36.00 | \$0.80      | \$10.00      |

#### GPT 5.6 Terra

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

Input Context ≤ 272K

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$2.00 | \$12.00 | \$0.20      | \$2.50       |
| Modellix | \$1.60 | \$9.60  | \$0.16      | \$2.00       |

Input Context ＞ 272K

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$4.00 | \$18.00 | \$0.40      | \$5.00       |
| Modellix | \$3.20 | \$14.40 | \$0.32      | \$4.00       |

#### GPT 5.6 Luna

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

Input Context ≤ 272K

|          | Input  | Output | Cached Read | Cached Write |
| -------- | ------ | ------ | ----------- | ------------ |
| Official | \$0.20 | \$1.20 | \$0.02      | \$0.25       |
| Modellix | \$0.16 | \$0.96 | \$0.016     | \$0.20       |

Input Context ＞ 272K

|          | Input  | Output | Cached Read | Cached Write |
| -------- | ------ | ------ | ----------- | ------------ |
| Official | \$0.40 | \$1.80 | \$0.04      | \$0.50       |
| Modellix | \$0.32 | \$1.44 | \$0.032     | \$0.40       |

#### GPT 5.5

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

Input Context ≤ 272K

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$5.00 | \$30.00 | \$0.50      | —            |
| Modellix | \$4.00 | \$24.00 | \$0.40      | —            |

Input Context ＞ 272K

|          | Input   | Output  | Cached Read | Cached Write |
| -------- | ------- | ------- | ----------- | ------------ |
| Official | \$10.00 | \$45.00 | \$4.00      | —            |
| Modellix | \$8.00  | \$36.00 | \$3.20      | —            |

### Anthropic

#### Claude Opus 5

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

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$5.00 | \$25.00 | \$0.50      | \$6.25       |
| Modellix | \$4.85 | \$24.25 | \$0.485     | \$6.0625     |

#### Claude Sonnet 5

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

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$2.00 | \$10.00 | \$0.20      | \$2.50       |
| Modellix | \$1.94 | \$9.70  | \$0.194     | \$2.425      |

#### Claude Haiku 4.5

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

|          | Input  | Output | Cached Read | Cached Write |
| -------- | ------ | ------ | ----------- | ------------ |
| Official | \$1.00 | \$5.00 | \$0.10      | \$1.25       |
| Modellix | \$0.97 | \$4.85 | \$0.097     | \$1.2125     |

### Google

#### Gemini 3.6 Flash

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

|          | Input   | Output  | Cached Read | Cached Write |
| -------- | ------- | ------- | ----------- | ------------ |
| Official | \$1.50  | \$7.50  | \$0.15      | —            |
| Modellix | \$1.275 | \$6.375 | \$0.1275    | —            |

#### Gemini 3.5 Flash

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

|          | Input   | Output | Cached Read | Cached Write |
| -------- | ------- | ------ | ----------- | ------------ |
| Official | \$1.50  | \$9.00 | \$0.15      | —            |
| Modellix | \$1.275 | \$7.65 | \$0.1275    | —            |

#### Gemini 3.1 Pro

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

Input Context ≤ 200K

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$2.00 | \$12.00 | \$0.20      | —            |
| Modellix | \$1.70 | \$10.20 | \$0.17      | —            |

Input Context ＞ 200K

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$4.00 | \$18.00 | \$0.40      | —            |
| Modellix | \$3.40 | \$15.30 | \$0.34      | —            |

### xAI

#### Grok 4.5

* Model ID: `xai/grok-4.5`
* Discount: 15% OFF

Input Context ≤ 200K

|          | Input  | Output | Cached Read | Cached Write |
| -------- | ------ | ------ | ----------- | ------------ |
| Official | \$2.00 | \$6.00 | \$0.30      | —            |
| Modellix | \$1.70 | \$5.10 | \$0.255     | —            |

Input Context ＞ 200K

|          | Input  | Output  | Cached Read | Cached Write |
| -------- | ------ | ------- | ----------- | ------------ |
| Official | \$4.00 | \$12.00 | \$0.60      | —            |
| Modellix | \$3.40 | \$10.20 | \$0.51      | —            |

#### Grok 4.3

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

Input Context ≤ 200K

|          | Input    | Output  | Cached Read | Cached Write |
| -------- | -------- | ------- | ----------- | ------------ |
| Official | \$1.25   | \$2.50  | \$0.20      | —            |
| Modellix | \$1.0625 | \$2.125 | \$0.17      | —            |

Input Context ＞ 200K

|          | Input   | Output | Cached Read | Cached Write |
| -------- | ------- | ------ | ----------- | ------------ |
| Official | \$2.50  | \$5.00 | \$0.40      | —            |
| Modellix | \$2.125 | \$4.25 | \$0.34      | —            |

<Note>
  Availability and prices can change. Confirm the live catalog and rates in the
  [Modellix console](https://modellix.ai/console). Billing uses token `usage` on
  successful responses.
</Note>

## Quick start

<Steps>
  <Step title="Get an API key">
    Create a key in the [Modellix console](https://modellix.ai/console/api-key)
    and store it securely.
  </Step>

  <Step title="Pick a protocol and base URL">
    | Client type                                       | Base URL                             | Protocol                        |
    | ------------------------------------------------- | ------------------------------------ | ------------------------------- |
    | OpenAI SDK, Codex, Cursor, OpenCode (OpenAI mode) | `https://llm.modellix.ai/v1`         | Chat Completions (or Responses) |
    | Anthropic SDK, Claude Code                        | `https://llm.modellix.ai` (no `/v1`) | Messages                        |
  </Step>

  <Step title="Send a request">
    Use your SDK or a curl example from the [API guide](/llm/api). Always set
    `model` to a `provider/name` ID.
  </Step>
</Steps>

## Guides in this section

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

<Columns cols={2}>
  <Card title="API guide" icon="book-open" href="/llm/api">
    Protocols, curl examples, session header, errors, rate limits, and billing.
  </Card>

  <Card title="OpenAI SDK" icon="code" href="/llm/openai-sdk">
    `OPENAI_BASE_URL` + Modellix key for Chat Completions and Responses.
  </Card>

  <Card title="Anthropic SDK" icon="code" href="/llm/anthropic-sdk">
    `ANTHROPIC_BASE_URL` without `/v1` for Messages.
  </Card>

  <Card title="Codex" icon="terminal" href="/llm/codex">
    `openai_base_url` in `~/.codex/config.toml`.
  </Card>

  <Card title="Claude Code" icon="terminal" href="/llm/claude-code">
    Environment variables or `~/.claude/settings.json`.
  </Card>

  <Card title="Cursor" icon="sparkles" href="/llm/cursor">
    OpenAI-compatible provider pointed at the LLM gateway.
  </Card>

  <Card title="OpenCode" icon="terminal" href="/llm/opencode">
    Provider `baseURL` for OpenAI- or Anthropic-compatible mode.
  </Card>
</Columns>

## API reference

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

| Endpoint                    | Docs                                      |
| --------------------------- | ----------------------------------------- |
| `POST /v1/chat/completions` | [Chat Completions](/llm/chat-completions) |
| `POST /v1/responses`        | [Responses](/llm/responses)               |
| `POST /v1/messages`         | [Messages](/llm/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](/llm/api).