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

# Trae

> ByteDance's AI-native IDE integration with GravitexAI — drive 100+ models through dual OpenAI + Anthropic protocols via custom models

## 1. Introduction

**Trae** is ByteDance's **AI-native IDE** released in January 2025 — a productivity tool aimed at professional developers ("Vibe Coding"): describe what you want in natural language, AI handles code completion, bug fixes, project scaffolding, and one-click preview. Trae ships as both a **China edition** (`trae.cn`) and an **International edition** (`trae.ai`), with a spin-off **SOLO** lineup (SOLO Desktop / SOLO App / SOLO Web) where AI fully drives the task lifecycle.

Plug Trae into GravitexAI via its "Custom Model" mechanism and you get:

<CardGroup cols={2}>
  <Card title="🔌 Dual-protocol coverage" icon="plug">
    Configure OpenAI and Anthropic protocols simultaneously — one key drives both
  </Card>

  <Card title="🤖 100+ frontier models" icon="layer-group">
    GPT, Claude, Gemini, DeepSeek, Doubao, Qwen, Kimi, MiniMax in one place
  </Card>

  <Card title="🛡️ Automatic failover" icon="shield">
    Distributed infrastructure routes around outages with backup models
  </Card>

  <Card title="💼 Enterprise-grade" icon="building">
    Transparent token-level billing, org-level data policies, team/enterprise ready
  </Card>
</CardGroup>

<Info>
  **Product info**

  * 🔗 China edition: `www.trae.cn`
  * 🔗 International edition: `www.trae.ai`
  * 👥 Developer: ByteDance
  * 📅 First released: January 2025
  * 🧩 Modes: Builder (agent) / Chat (sidebar) / Inline Chat
  * 🌐 Compatible protocols: OpenAI, Anthropic, and other custom providers
</Info>

## 2. Core Features

### Three interaction modes

* **Builder**: agent mode — AI reads/writes multiple files, runs commands, and builds the project autonomously
* **Chat**: side-bar conversation, similar to Cursor Chat / Cline — best for Q\&A and snippet generation
* **Inline Chat**: invoke directly inside the editor with `Cmd/Ctrl + I` — fastest path for inline completion and refactors

### MCP & tooling ecosystem

* Built-in **MCP (Model Context Protocol)** support for connecting external tools and APIs
* **Remote-SSH** support — remote development feels identical to local
* `.rules` project-level rule files to constrain AI behavior style

### Custom models (the focus of this guide)

Trae International ships with presets for **Anthropic, OpenAI, Gemini, xAI, OpenRouter, Ollama, DeepSeek, Volcengine, Aliyun, Tencent Cloud, SiliconFlow, PPIO, Novita, BytePlus**, and each preset allows you to fill in a **custom model ID + API key + custom request URL** — exactly the hook we use to wire in GravitexAI.

<Tip>
  **Why route through GravitexAI**: Trae's built-in models are limited by region and version, and there's no unified billing across providers. Wire in GravitexAI and **one key covers both OpenAI and Anthropic protocols** — switching between GPT/Gemini and Claude no longer requires touching the settings panel; just pick from the top model dropdown.
</Tip>

## 3. Prerequisites

* **Trae** installed (`trae.cn` or `trae.ai`)
* An **API key** from the [GravitexAI Console](https://maas.gravitex.ai/#/keys) (format: `sk-xxxxxxxxxx`)

<Tip>
  **Base URL**: Trae's custom-model field requires the **full endpoint path**, not just the domain.

  * OpenAI protocol: `https://api.gravitex.ai/v1/chat/completions`
  * Anthropic protocol: `https://api.gravitex.ai/v1/messages`
</Tip>

## 4. Quick Start

### Step 1: Install Trae

<Tabs>
  <Tab title="China edition (recommended for mainland China)">
    Visit `www.trae.cn` to download. Supports macOS and Windows. The China edition bundles Doubao, DeepSeek, and other domestic models; login is via mobile number.
  </Tab>

  <Tab title="International edition">
    Visit `www.trae.ai` to download. Supports macOS, Windows, Linux. Comes pre-configured with GPT / Claude / Gemini presets.
  </Tab>
</Tabs>

### Step 2: Get a GravitexAI API key

1. Open the [GravitexAI Console](https://maas.gravitex.ai/#/keys)
2. Click "Create token", name it, and save
3. Copy the `sk-…` key

### Step 3: Open Trae's "Custom Model" entry

* **In IDE mode**: click ⚙️ (top-right) → **Models** in the left nav → "Add model" / "Custom model"
* **In SOLO mode**: click ⚙️ on the chat panel → **Models** → Add

### Step 4: Add an OpenAI-protocol provider (GPT / Gemini / DeepSeek / Doubao etc.)

| Field                  | Value                                                      | Notes                                                               |
| ---------------------- | ---------------------------------------------------------- | ------------------------------------------------------------------- |
| **Provider**           | `OpenAI`                                                   | Pick the OpenAI preset                                              |
| **Model**              | `Custom model`                                             | Choose "Custom model" at the bottom of the dropdown                 |
| **Model ID**           | e.g. `gpt-5.5`, `gemini-3.5-flash`, `deepseek-v3-2-251201` | Use the [canonical model ID](https://maas.gravitex.ai/#/api-models) |
| **API key**            | `sk-…`                                                     | Paste the GravitexAI token from Step 2                              |
| **Custom request URL** | `https://api.gravitex.ai/v1/chat/completions`              | **Must include `/v1/chat/completions`**                             |

<Warning>
  **The base URL must include the full path**: starting from v3.3.51, Trae's custom-model baseURL field requires the **complete endpoint path**. Submitting just `https://api.gravitex.ai` or `https://api.gravitex.ai/v1` will fail.
</Warning>

### Step 5: Add an Anthropic-protocol provider (Claude family)

To use Claude Opus 4.7 / Sonnet 4.6 / Haiku 4.5, add a second provider entry:

| Field                  | Value                                           | Notes                                                                         |
| ---------------------- | ----------------------------------------------- | ----------------------------------------------------------------------------- |
| **Provider**           | `Anthropic`                                     | Pick the Anthropic preset                                                     |
| **Model**              | `Claude-Sonnet-4.6` (or another Claude variant) | Use the official preset, or "Custom model"                                    |
| **API key**            | `sk-…`                                          | Paste the same GravitexAI token — keys are shared across both protocols       |
| **Custom request URL** | `https://api.gravitex.ai/v1/messages`           | **Must include `/v1/messages`** — note this is **not** `/v1/chat/completions` |

<Info>
  **Why two protocols**: OpenAI talks `/v1/chat/completions`, Anthropic talks `/v1/messages`. GravitexAI hosts both, so a single key can drive both provider entries in Trae without interference.
</Info>

### Step 6: Switch and ship

Back in the editor, click the model dropdown at the top. Both providers and their models appear together. Pick one and start chatting or jump into Builder mode.

## 5. Recommended Model Pairings

<CardGroup cols={2}>
  <Card title="Daily coding (best value)" icon="code">
    **Claude Sonnet 4.6** (Anthropic) + **GPT-5.5** (OpenAI)

    Sonnet 4.6 is highly capable at code with great value; GPT-5.5 replies faster in Chat mode
  </Card>

  <Card title="Complex architecture (flagship)" icon="crown">
    **Claude Opus 4.7** (Anthropic)

    Best for complex refactors, cross-file analysis, architecture decisions; pair with Builder mode
  </Card>

  <Card title="Deep reasoning" icon="brain">
    **Claude Sonnet 4.6 Thinking** / **GPT-5.5 Thinking**

    Forces chain-of-thought reasoning — ideal for algorithm problems, logic, security audits
  </Card>

  <Card title="Cost-effective domestic" icon="yuan-sign">
    **DeepSeek V3.2** / **Doubao Seed 2.0 Pro** / **Qwen3 Coder Plus**

    All ride the OpenAI protocol; cheaper per token with strong Chinese output
  </Card>
</CardGroup>

<Card title="Full model catalog and coding picks" icon="star" href="/en/api-reference/models">
  GravitexAI exposes 100+ frontier models through a unified API. The model catalog is updated with the latest performance and pricing comparisons.
</Card>

## 6. Tips

<Steps>
  <Step title="Keep both provider entries">
    Add **both** OpenAI and Anthropic entries so you can switch between GPT/Gemini ↔ Claude without re-editing the baseURL.
  </Step>

  <Step title="Can't find your model in the dropdown?">
    Trae's built-in model list lags behind GravitexAI's catalog. **Pick "Custom model" and type the model ID manually** — that's the most reliable path. Refer to the [GravitexAI catalog](https://maas.gravitex.ai/#/api-models) for canonical IDs.
  </Step>

  <Step title="Use Claude for Builder mode">
    Builder's agent loop relies heavily on multi-turn tool calls. Claude (especially Sonnet 4.6 / Opus 4.7) is markedly more stable at instruction-following and tool use than other model families.
  </Step>

  <Step title="Pin Thinking variants for complex work">
    Append `-thinking` to the model ID (e.g. `claude-sonnet-4-6-thinking`) to force chain-of-thought reasoning. Makes Builder-mode architecture decisions and security audits much more reliable.
  </Step>

  <Step title="Split keys by purpose">
    Create separate GravitexAI tokens for dev/prod or per-team in the console for cleaner quota management and reconciliation.
  </Step>
</Steps>

## 7. FAQ

<AccordionGroup>
  <Accordion title="Any difference between Trae China and International editions when wiring up GravitexAI?">
    **No** — both editions support custom models and allow you to add OpenAI and Anthropic provider entries side by side. The difference is mainly in the pre-bundled model presets (China edition leans on Doubao/DeepSeek; International leans on GPT/Claude/Gemini).

    Recommendation: prefer `trae.cn` if you're on a mainland-China network, otherwise `trae.ai` for global teams or international model presets.
  </Accordion>

  <Accordion title="Why does the baseURL have to include /v1/chat/completions?">
    Starting from **v3.3.51**, Trae changed how it resolves the custom-model baseURL — it now uses the value verbatim instead of auto-appending `/chat/completions`.

    Correct values:

    * OpenAI: `https://api.gravitex.ai/v1/chat/completions`
    * Anthropic: `https://api.gravitex.ai/v1/messages`

    Incorrect (will 404 or mis-route):

    * ❌ `https://api.gravitex.ai`
    * ❌ `https://api.gravitex.ai/v1`
  </Accordion>

  <Accordion title="Can I use 'Custom model' under the Anthropic provider for any Claude ID?">
    Yes. The Anthropic provider entry also exposes a "Custom model" option — drop in IDs like `claude-opus-4-7` / `claude-sonnet-4-6-thinking` / `claude-haiku-4-5-20251001`. GravitexAI's `/v1/messages` endpoint accepts all official model IDs.
  </Accordion>

  <Accordion title="Why don't I see GPT-5.5 / Claude 4.7 in Trae's dropdown?">
    Trae's built-in presets lag the actual provider catalog. **Just pick "Custom model" and type the ID** — anything GravitexAI supports works in Trae without waiting for the client to update.
  </Accordion>

  <Accordion title="Builder mode keeps stalling / tool calls fail. What now?">
    1. **Default to Claude Sonnet 4.6 or Opus 4.7** — both lead in tool-use stability
    2. **Avoid non-reasoning small models** like DeepSeek-Chat / Qwen base for Builder; switch to `-thinking` variants
    3. **Watch context length** — when a single file is huge or you're touching many files, move to Opus 4.7 (1M context)
    4. **Check GravitexAI status** — transient upstream issues affect all clients; the console shows live channel health
  </Accordion>

  <Accordion title="How does Trae handle privacy / data upload?">
    Trae is a ByteDance product and uploads telemetry / conversation data per its official privacy policy. If client telemetry is a concern:

    * Whitelist outbound traffic at your network egress
    * Mask sensitive snippets before invoking Builder mode
    * Consider [Claude Code](/en/integrations/claude-code) / [Codex](/en/integrations/codex) as open-source / auditable alternatives
  </Accordion>

  <Accordion title="Trae vs Cursor / Claude Code / Codex — how to choose?">
    | Tool            | Type           | Agent mode    | GravitexAI difficulty         | Best for                                                     |
    | --------------- | -------------- | ------------- | ----------------------------- | ------------------------------------------------------------ |
    | **Trae**        | Standalone IDE | ✅ Builder     | Medium (two protocol entries) | Cursor-like experience with stronger China / Chinese support |
    | **Cursor**      | Standalone IDE | ❌ (Chat only) | Easy (OpenAI only)            | Strong autocomplete & diff preview                           |
    | **Claude Code** | CLI            | ✅             | Easy                          | Terminal workflow, CI / remote dev                           |
    | **Codex**       | CLI            | ✅             | Easy                          | Official OpenAI terminal agent, full GPT family              |
    | **Open Code**   | CLI            | ✅             | Easy                          | Open-source CLI agent, multi-provider                        |

    Detailed guides: [Codex](/en/integrations/codex) · [Claude Code](/en/integrations/claude-code) · [Open Code](/en/integrations/open-code) · [Gemini CLI](/en/integrations/gemini-cli)
  </Accordion>

  <Accordion title="Requests return 401 / 403 — how to troubleshoot?">
    1. Confirm the API key starts with `sk-` and has no stray whitespace
    2. Confirm the baseURL is spelled correctly (`/v1/chat/completions` vs `/v1/messages`)
    3. Open the [GravitexAI Console](https://maas.gravitex.ai/#/keys) to verify the token is active and the account has balance
    4. Insufficient balance also surfaces as 401 — double-check
  </Accordion>
</AccordionGroup>

## 8. Related Resources

<CardGroup cols={2}>
  <Card title="Model catalog" icon="star" href="/en/api-reference/models">
    100+ models with performance / pricing comparisons and coding picks
  </Card>

  <Card title="GravitexAI Console" icon="gear" href="https://maas.gravitex.ai">
    Manage tokens, usage, and projects
  </Card>

  <Card title="Codex integration" icon="terminal" href="/en/integrations/codex">
    OpenAI's official terminal agent, full GPT family
  </Card>

  <Card title="Claude Code integration" icon="code" href="/en/integrations/claude-code">
    Anthropic's official CLI agent, full Claude family
  </Card>
</CardGroup>

<Info>
  **Need more help?** Reach our BD team at [bd@gravitex.ai](mailto:bd@gravitex.ai) or call +86 136 0305 5233.
</Info>