> For the complete documentation index, see [llms.txt](https://anyint.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://anyint.gitbook.io/docs/api-reference/agent-coding-tool-integrations.md). # Agent Coding Tool Integrations Use AnyInt with agent coding tools that support OpenAI-compatible, Anthropic-compatible, or custom model providers. ### Before You Start Create an AnyInt API key, then set it as an environment variable: ```bash export ANYINT_API_KEY="your-anyint-api-key" ``` Use the Models API to find model IDs available to your account: ```bash curl https://gateway.api.anyint.ai/openai/v1/models \ -H "Authorization: Bearer $ANYINT_API_KEY" ``` The OpenAI-compatible and Anthropic-compatible model list endpoints both work: ```bash curl https://gateway.api.anyint.ai/openai/v1/models \ -H "Authorization: Bearer $ANYINT_API_KEY" curl https://gateway.api.anyint.ai/anthropic/v1/models \ -H "x-api-key: $ANYINT_API_KEY" \ -H "anthropic-version: 2023-06-01" ``` Do not use `https://gateway.api.anyint.ai/v1/models`; it returns `404`. Common endpoints: | Compatibility | Base URL | Auth | | -------------------- | --------------------------------------------- | -------------------------------------------------------------- | | OpenAI-compatible | `https://gateway.api.anyint.ai/openai/v1` | `Authorization: Bearer $ANYINT_API_KEY` | | Anthropic-compatible | `https://gateway.api.anyint.ai/anthropic/v1` | `x-api-key: $ANYINT_API_KEY` + `anthropic-version: 2023-06-01` | | Gemini-compatible | `https://gateway.api.anyint.ai/gemini/v1beta` | `Authorization: Bearer $ANYINT_API_KEY` | Use the OpenAI-compatible endpoint unless the tool specifically expects Anthropic Messages API behavior. ### Tool Setup Summary | Tool | Recommended AnyInt Base URL | Setup | | ------------------- | -------------------------------------------- | ------------------------------------------------------------------------------------- | | Claude Code | `https://gateway.api.anyint.ai/anthropic` | Set `ANTHROPIC_BASE_URL`, `ANTHROPIC_AUTH_TOKEN`, and model environment variables. | | Codex CLI | `https://gateway.api.anyint.ai/openai/v1` | Add a custom Responses provider in `~/.codex/config.toml`; see Codex CLI notes below. | | GitHub Copilot | Extension-dependent | Use only if your Copilot extension supports custom OpenAI or Anthropic endpoints. | | GitHub Copilot CLI | `https://gateway.api.anyint.ai/anthropic/v1` | Use only if your Copilot CLI build supports BYOK provider environment variables. | | Kilo Code | `https://gateway.api.anyint.ai/openai/v1` | Add AnyInt as a custom OpenAI-compatible provider. | | WorkBuddy/CodeBuddy | `https://gateway.api.anyint.ai/openai/v1` | Add entries to `.codebuddy/models.json`. | | OpenCode | `https://gateway.api.anyint.ai/openai/v1` | Add a custom provider in `opencode.json`. | | Oh My Pi | `https://gateway.api.anyint.ai/openai/v1` | Add AnyInt provider to `~/.omp/agent/models.yml`. | | OpenClaw | `https://gateway.api.anyint.ai/openai/v1` | Use onboarding or custom provider settings if available. | | AstrBot | `https://gateway.api.anyint.ai/openai/v1` | Add the provider in the Web UI. | | Deep Code | `https://gateway.api.anyint.ai/openai/v1` | Configure `~/.deepcode/settings.json`. | | Hermes | `https://gateway.api.anyint.ai/openai/v1` | Choose a custom OpenAI-compatible provider during setup. | | nanobot | `https://gateway.api.anyint.ai/openai/v1` | Edit `~/.nanobot/config.json`. | | Crush | `https://gateway.api.anyint.ai/openai/v1` | Add provider in `~/.config/crush/crush.json`. | | Pi | `https://gateway.api.anyint.ai/openai/v1` | Add provider in `~/.pi/agent/models.json`. | | Reasonix | Tool-dependent | Requires custom provider or base URL support. | | Langcli | Tool-dependent | Requires custom provider or base URL support. | ### Claude Code ```bash export ANTHROPIC_BASE_URL="https://gateway.api.anyint.ai/anthropic" export ANTHROPIC_AUTH_TOKEN="$ANYINT_API_KEY" export ANTHROPIC_MODEL="" export ANTHROPIC_DEFAULT_OPUS_MODEL="" export ANTHROPIC_DEFAULT_SONNET_MODEL="" export ANTHROPIC_DEFAULT_HAIKU_MODEL="" export CLAUDE_CODE_SUBAGENT_MODEL="" claude ``` Use Anthropic-compatible model IDs returned by the Models API or shown in your AnyInt dashboard. ### Codex CLI Codex CLI uses `~/.codex/config.toml`. Current Codex CLI releases expect a Responses API provider; OpenAI Chat Completions provider wiring is no longer supported by Codex CLI. ```toml [profiles.anyint] model_provider = "anyint" model = "" [model_providers.anyint] name = "AnyInt" base_url = "https://gateway.api.anyint.ai/openai/v1" env_key = "ANYINT_API_KEY" wire_api = "responses" ``` Then run: ```bash export ANYINT_API_KEY="your-anyint-api-key" codex exec --profile anyint "Reply exactly OK." ``` Verification note: AnyInt's non-streaming `POST /openai/v1/responses` returned a valid `200` response in local testing. Codex CLI `0.128.0` itself did not complete the smoke test because its Responses stream closed before a `response.completed` event. Treat Codex CLI as not verified until streaming Responses compatibility is confirmed for your AnyInt account and Codex version. ### GitHub Copilot CLI ```bash export COPILOT_PROVIDER_TYPE="anthropic" export COPILOT_PROVIDER_BASE_URL="https://gateway.api.anyint.ai/anthropic/v1" export COPILOT_PROVIDER_API_KEY="$ANYINT_API_KEY" export COPILOT_MODEL="" copilot ``` If the model is not in Copilot CLI's built-in catalog, also set token limits if needed: ```bash export COPILOT_PROVIDER_MAX_PROMPT_TOKENS=200000 export COPILOT_PROVIDER_MAX_OUTPUT_TOKENS=8192 ``` Verification note: GitHub Copilot CLI `0.0.422` did not expose these BYOK provider variables in `copilot help environment`, and a local smoke test with these variables did not route successfully to AnyInt. Use this only with a Copilot CLI build that explicitly documents custom provider support. ### OpenCode Create or edit `opencode.json`: ```json { "$schema": "https://opencode.ai/config.json", "provider": { "anyint": { "npm": "@ai-sdk/openai-compatible", "name": "AnyInt", "options": { "baseURL": "https://gateway.api.anyint.ai/openai/v1", "apiKey": "{env:ANYINT_API_KEY}" }, "models": { "": { "name": "AnyInt model", "limit": { "context": 200000, "output": 8192 } } } } }, "model": "anyint/" } ``` Then run `opencode` and use `/models` to switch models. The `limit.output` value is important for Anthropic-family models because OpenCode may otherwise request more output tokens than the upstream model allows. ### Local Verification Results Tested on 2026-05-07 with the provided AnyInt API key. The key is intentionally not included in this document. | Check | Result | Notes | | ---------------------------------------------------------- | ------------ | ---------------------------------------------------------------------------- | | `GET /openai/v1/models` | Pass | Returned AnyInt model list. | | `GET /anthropic/v1/models` | Pass | Returned AnyInt model list. | | `GET /v1/models` | Fail | Returned `404`; doc updated to avoid this path. | | `POST /openai/v1/chat/completions` with `claude-3-5-haiku` | Pass | Returned `OK.`. | | `POST /anthropic/v1/messages` with `claude-3-5-haiku` | Pass | Returned `OK.`. | | Claude Code `2.1.112` | Pass | `ANTHROPIC_BASE_URL`, `ANTHROPIC_AUTH_TOKEN`, and `claude-3-5-haiku` worked. | | OpenCode `1.14.39` | Pass | Custom `anyint` provider worked after adding `limit.output = 8192`. | | Codex CLI `0.128.0` | Partial | Raw Responses API worked; Codex CLI streaming did not complete. | | GitHub Copilot CLI `0.0.422` | Not verified | Installed CLI did not document or accept the BYOK provider flow. | The other tools in this document are UI-only, extension-dependent, or not installed locally during this verification pass, so their existing setup guidance is kept as-is. ### WorkBuddy / CodeBuddy Create either user-level or project-level config: ``` ~/.codebuddy/models.json /.codebuddy/models.json ``` Example: ```json { "models": [ { "id": "", "name": "AnyInt Model", "vendor": "AnyInt", "url": "https://gateway.api.anyint.ai/openai/v1/chat/completions", "apiKey": "${ANYINT_API_KEY}", "maxInputTokens": 200000, "maxOutputTokens": 8192, "supportsToolCall": true, "supportsImages": false } ], "availableModels": [""] } ``` Restart WorkBuddy/CodeBuddy after editing the file. ### Kilo Code, Crush, Pi, Oh My Pi, Deep Code, nanobot For tools that support custom OpenAI-compatible providers, use this mapping: ``` Provider name: AnyInt API type: OpenAI-compatible Base URL: https://gateway.api.anyint.ai/openai/v1 API key: $ANYINT_API_KEY Model: Chat endpoint: /chat/completions ``` If the tool asks for the full completion URL, use: ``` https://gateway.api.anyint.ai/openai/v1/chat/completions ``` ### AstrBot, OpenClaw, Hermes In the provider setup UI or onboarding wizard, choose a custom OpenAI-compatible provider when available: ``` Provider: AnyInt Base URL: https://gateway.api.anyint.ai/openai/v1 API key: your AnyInt API key Model: ``` Then set the configured model as the default chat or coding model. ### GitHub Copilot, Reasonix, Langcli These tools may not expose a stable generic provider configuration in every release. Use AnyInt directly only if the tool supports one of: | Required Support | AnyInt Value | | ------------------------------------ | --------------------------------------------------------------------------- | | Custom OpenAI-compatible base URL | `https://gateway.api.anyint.ai/openai/v1` | | Custom Anthropic-compatible base URL | `https://gateway.api.anyint.ai/anthropic/v1` | | Custom API key | `$ANYINT_API_KEY` | | Custom model ID | Any model returned by `GET /openai/v1/models` or `GET /anthropic/v1/models` | If a tool only supports a fixed built-in provider list, AnyInt integration requires a plugin, extension, or upstream provider entry.