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

# Cursor IDE

> Add ByteSpike as an OpenAI-compatible provider in Cursor — works with the editor's chat, agent, and tab-complete features.

Cursor uses OpenAI-shape clients under the hood for its model
providers. Adding ByteSpike means you get every model in the catalog
(Claude, GPT-5, Gemini, DeepSeek, etc.) inside the editor's chat
panel and the inline edit / agent features.

## Prerequisites

* A ByteSpike account + a key. Choose the group based on which
  models you want inside Cursor — `claude-default` for Claude, or
  `default` to route everything. See
  [Models](/models).
* Cursor `0.42+` (older versions don't have the custom provider UI).

## Configure

1. Open **Cursor → Settings → Models** (`Cmd/Ctrl + ,`)
2. Scroll to **OpenAI API Key** section
3. Click **Override OpenAI Base URL** and paste:
   ```
   https://llm.bytespike.ai/v1
   ```
4. Set **OpenAI API Key** to your ByteSpike key (`sk-byts-...`)
5. Click **Verify** — Cursor pings `/v1/chat/completions` to confirm

That's the whole config. Cursor's chat panel + agent + inline edit
all start routing through ByteSpike from the next request.

## Enable specific models

Cursor lets you toggle which model ids show up in the picker:

1. Same **Models** settings page
2. Scroll to **Models** list
3. Click **Add model** for each ByteSpike id you want exposed:
   * `claude-opus-4-8`
   * `claude-sonnet-4-6`
   * `claude-haiku-4-5`
   * `gpt-5-5`
   * `gpt-5-4`
   * `gemini-3-5-flash`
   * `deepseek-v4-pro`
   * …add any other id from [Models](/models)

The dropdown for each Cursor surface (chat, edit, agent) gets the
new id. Pick per task.

<Warning>
  Cursor's built-in `gpt-4`, `claude-3.5-sonnet`, etc. picker entries
  will still hit OpenAI / Anthropic directly **unless** you've toggled
  off "Use my own API key". With ByteSpike configured + that toggle on,
  every model — built-in or custom — goes through ByteSpike.
</Warning>

## Cursor Agent + ByteSpike

Cursor's **Agent** feature runs as multi-turn tool-use loops. The
ByteSpike gateway preserves tool definitions across protocols, so
Agent works the same against translated routes (Claude via OpenAI
shape, Gemini via OpenAI shape) as it does against native paths.

If you see "tool calls returning malformed json", that's typically
the model's native tool format mapping to OpenAI's strict
schema. Switch the Agent's model to a native OpenAI id (`gpt-5-5`,
`gpt-5-4`) — those have the cleanest schema fidelity.

## Streaming, image inputs, vision

All three work via ByteSpike — the gateway forwards streaming events
1:1 and proxies image inputs (data URLs or http URLs) without
re-encoding. Cursor's vision features against `claude-sonnet-4-6` or
`gemini-3-5-flash` work identically to going direct.

## Tab-complete

Cursor's tab-complete is a separate, lighter request shape that
typically uses a smaller / faster model. Pin a low-latency model
(`claude-haiku-4-5`, `gpt-5-4-mini`, `gemini-3-flash-lite`) for that
slot — the chat panel can stay on a bigger model.

## Troubleshooting

| Symptom                                 | Cause                                               | Fix                                                                          |
| --------------------------------------- | --------------------------------------------------- | ---------------------------------------------------------------------------- |
| Verify returns 401                      | Wrong key                                           | Copy a fresh value from console                                              |
| Verify returns 402                      | Key has \$0 budget                                  | Top up                                                                       |
| Models dropdown empty                   | Cursor version doesn't have custom-provider support | Upgrade Cursor to 0.42+                                                      |
| Inline edit returns "model unavailable" | Cursor uses a built-in model name not in your group | Add a working ByteSpike id to the Models list and select it explicitly       |
| Slow first token                        | Cold start on cross-protocol translation routes     | Warm with a small request first, or pin to a native id for hot-path features |

## Other editor integrations

The same `https://llm.bytespike.ai/v1` + `sk-byts-...` recipe works
for any OpenAI-compatible editor:

| Editor / IDE           | Config path                                                                        |
| ---------------------- | ---------------------------------------------------------------------------------- |
| Continue.dev (VS Code) | `~/.continue/config.json` → `"apiBase": "https://llm.bytespike.ai/v1"`             |
| Cline (VS Code)        | Settings → API Provider → OpenAI Compatible → Base URL                             |
| Aider (CLI)            | `aider --openai-api-base https://llm.bytespike.ai/v1 --openai-api-key sk-byts-...` |
| Zed                    | Settings → AI → custom OpenAI endpoint                                             |
| JetBrains AI Assistant | Settings → Tools → AI Assistant → custom endpoint                                  |

Whatever the editor, the gist is the same: an OpenAI-compatible
`base_url` + your ByteSpike key.

## Next

<CardGroup cols={2}>
  <Card title="Claude Code CLI" icon="terminal" href="/claude-code-cli">
    The terminal-side alternative.
  </Card>

  <Card title="Codex CLI" icon="terminal" href="/codex-cli">
    OpenAI's CLI — works with the same key.
  </Card>

  <Card title="/chat/completions reference" icon="code" href="/api-reference/text/openai-chat-completions">
    The protocol Cursor speaks.
  </Card>

  <Card title="Models" icon="boxes-stacked" href="/models">
    Catalog Cursor can pick from.
  </Card>
</CardGroup>