API & integrations

Create a key in your dashboard (Pro or Max plan) and plug the gremlin in anywhere.

Base URL

https://api.gremlingpt.com/v1

Model

gremlin-gpt

Formats

OpenAI · Anthropic

Context: 1M tokens on every plan. Long agent sessions are fine; set your client timeout to at least 300 seconds for very long answers.

Questions, payments, API keys — write to us, a human answers.

Telegram @GremlinGPTbot info@gremlingpt.com

1. Put your key in an environment variable

Every guide below reads it from GREMLIN_API_KEY, so the key never ends up in config files.

bash

export GREMLIN_API_KEY="sk-...your key..."

Instructions for agents in one plain-text page: https://gremlingpt.com/llms.txt

Agents & terminal

Claude Code

Claude Code speaks the Anthropic format, and so does the gremlin (/v1/messages). Set these variables in your shell (or ~/.zshrc) and run claude.

bash

export ANTHROPIC_BASE_URL="https://api.gremlingpt.com"
export ANTHROPIC_AUTH_TOKEN="$GREMLIN_API_KEY"
export ANTHROPIC_MODEL="gremlin-gpt"
export ANTHROPIC_DEFAULT_OPUS_MODEL="gremlin-gpt"
export ANTHROPIC_DEFAULT_SONNET_MODEL="gremlin-gpt"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="gremlin-gpt"
export CLAUDE_CODE_SUBAGENT_MODEL="gremlin-gpt"
export API_TIMEOUT_MS=600000
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
claude

Note: The gremlin's context is 1M tokens — five times Claude Code's usual 200K — so long sessions are fine. Your plan's usage windows still apply.

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Claude Code to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Claude Code" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Hermes Agent

Hermes has a built-in "Custom endpoint" provider. Put this in ~/.hermes/config.yaml, or set the same values through the menu.

1Run: hermes model
2Choose "Custom endpoint (self-hosted / VLLM / etc.)".
3Base URL: https://api.gremlingpt.com/v1
4Model: gremlin-gpt, API key: your key (or key_env: GREMLIN_API_KEY).

yaml

# ~/.hermes/config.yaml
model:
  provider: custom
  base_url: https://api.gremlingpt.com/v1
  default: gremlin-gpt
  key_env: GREMLIN_API_KEY
  context_length: 1000000

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Hermes Agent to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Hermes Agent" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

OpenCode

Add the provider to opencode.json in your project (or ~/.config/opencode/opencode.json), then pick GremlinGPT with /models.

json

{
  "$schema": "https://opencode.ai/config.json",
  "model": "gremlin/gremlin-gpt",
  "provider": {
    "gremlin": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "GremlinGPT",
      "options": { "baseURL": "https://api.gremlingpt.com/v1", "apiKey": "{env:GREMLIN_API_KEY}" },
      "models": { "gremlin-gpt": { "name": "GremlinGPT", "limit": { "context": 1000000, "output": 8192 } } }
    }
  }
}

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect OpenCode to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "OpenCode" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Codex CLI

Codex talks to custom providers through the Responses API, which the gremlin supports. Add this to ~/.codex/config.toml.

toml

# ~/.codex/config.toml
model = "gremlin-gpt"
model_provider = "gremlin"

[model_providers.gremlin]
name = "GremlinGPT"
base_url = "https://api.gremlingpt.com/v1"
env_key = "GREMLIN_API_KEY"
wire_api = "responses"
stream_idle_timeout_ms = 600000

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Codex CLI to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Codex CLI" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Aider

The openai/ prefix tells Aider to use an OpenAI-compatible server.

bash

export OPENAI_API_BASE="https://api.gremlingpt.com/v1"
export OPENAI_API_KEY="$GREMLIN_API_KEY"
aider --model openai/gremlin-gpt

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Aider to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Aider" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Editors

Cline · Roo Code · Kilo Code

The three extensions are set up the same way.

1Open the extension's settings → API Provider: "OpenAI Compatible".
2Base URL: https://api.gremlingpt.com/v1
3API Key: your key.
4Model ID: gremlin-gpt
5Model configuration → Context window: 1000000.

Continue

Add the model to ~/.continue/config.yaml (works in VS Code and JetBrains) and save the key as the GREMLIN_API_KEY secret.

yaml

# ~/.continue/config.yaml
name: GremlinGPT
version: 1.0.0
schema: v1
models:
  - name: GremlinGPT
    provider: openai
    model: gremlin-gpt
    apiBase: https://api.gremlingpt.com/v1
    apiKey: ${{ secrets.GREMLIN_API_KEY }}
    roles: [chat, edit, apply]
    defaultCompletionOptions:
      contextLength: 1000000

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Continue to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Continue" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Cursor

Cursor lets you swap the OpenAI base URL for your own.

1Cursor Settings → Models → API Keys.
2OpenAI API Key: your key.
3Turn on "Override OpenAI Base URL" and enter https://api.gremlingpt.com/v1
4Models → Add model: gremlin-gpt, then select it in the chat.

Note: Cursor's own built-in models keep working; the gremlin is used when you pick gremlin-gpt.

Chat apps

SillyTavern

Use the Chat Completion API with a custom OpenAI-compatible source.

1API Connections → API: Chat Completion.
2Chat Completion Source: Custom (OpenAI-compatible).
3Custom Endpoint (Base URL): https://api.gremlingpt.com/v1
4Custom API Key: your key; Model ID: gremlin-gpt → Connect.

Open WebUI

Add the gremlin as an OpenAI connection.

1Admin Panel → Settings → Connections → OpenAI API → +.
2URL: https://api.gremlingpt.com/v1
3Key: your key → Save.
4Pick gremlin-gpt in the model list of a new chat.

LibreChat · Chatbox · Jan

These apps all have an "OpenAI-compatible" / "Custom provider" option.

1Add a custom provider of type OpenAI-compatible.
2API host / Base URL: https://api.gremlingpt.com/v1
3API key: your key; model: gremlin-gpt.

Code & automation

curl

The API is OpenAI-compatible: anything that lets you set a custom OpenAI URL works with the gremlin.

bash

curl https://api.gremlingpt.com/v1/chat/completions \
  -H "Authorization: Bearer $GREMLIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gremlin-gpt","messages":[{"role":"user","content":"Hi"}],"stream":true}'

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect curl to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "curl" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Python

The official openai library, just with a different base_url.

python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.gremlingpt.com/v1", api_key=os.environ["GREMLIN_API_KEY"], timeout=600)
r = client.chat.completions.create(
    model="gremlin-gpt",
    messages=[{"role": "user", "content": "Hi"}],
)
print(r.choices[0].message.content)

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Python to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Python" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Node.js

The official openai package for Node.js, with a different baseURL.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.gremlingpt.com/v1", apiKey: process.env.GREMLIN_API_KEY, timeout: 600_000 });
const r = await client.chat.completions.create({
  model: "gremlin-gpt",
  messages: [{ role: "user", content: "Hi" }],
});
console.log(r.choices[0].message.content);

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Node.js to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Node.js" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

n8n

Use n8n's OpenAI nodes with your own base URL.

1Credentials → New → OpenAI.
2API Key: your key; Base URL: https://api.gremlingpt.com/v1 → Save.
3In an OpenAI / AI Agent node pick this credential and type the model: gremlin-gpt.

API & integrations

Create a key in your dashboard (Pro or Max plan) and plug the gremlin in anywhere.

Base URL

https://api.gremlingpt.com/v1

Model

gremlin-gpt

Formats

OpenAI · Anthropic

Context: 1M tokens on every plan. Long agent sessions are fine; set your client timeout to at least 300 seconds for very long answers.

Questions, payments, API keys — write to us, a human answers.

Telegram @GremlinGPTbot info@gremlingpt.com

1. Put your key in an environment variable

Every guide below reads it from GREMLIN_API_KEY, so the key never ends up in config files.

bash

export GREMLIN_API_KEY="sk-...your key..."

Instructions for agents in one plain-text page: https://gremlingpt.com/llms.txt

Agents & terminal

Claude Code

Claude Code speaks the Anthropic format, and so does the gremlin (/v1/messages). Set these variables in your shell (or ~/.zshrc) and run claude.

bash

export ANTHROPIC_BASE_URL="https://api.gremlingpt.com"
export ANTHROPIC_AUTH_TOKEN="$GREMLIN_API_KEY"
export ANTHROPIC_MODEL="gremlin-gpt"
export ANTHROPIC_DEFAULT_OPUS_MODEL="gremlin-gpt"
export ANTHROPIC_DEFAULT_SONNET_MODEL="gremlin-gpt"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="gremlin-gpt"
export CLAUDE_CODE_SUBAGENT_MODEL="gremlin-gpt"
export API_TIMEOUT_MS=600000
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
claude

Note: The gremlin's context is 1M tokens — five times Claude Code's usual 200K — so long sessions are fine. Your plan's usage windows still apply.

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Claude Code to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Claude Code" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Hermes Agent

Hermes has a built-in "Custom endpoint" provider. Put this in ~/.hermes/config.yaml, or set the same values through the menu.

1Run: hermes model
2Choose "Custom endpoint (self-hosted / VLLM / etc.)".
3Base URL: https://api.gremlingpt.com/v1
4Model: gremlin-gpt, API key: your key (or key_env: GREMLIN_API_KEY).

yaml

# ~/.hermes/config.yaml
model:
  provider: custom
  base_url: https://api.gremlingpt.com/v1
  default: gremlin-gpt
  key_env: GREMLIN_API_KEY
  context_length: 1000000

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Hermes Agent to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Hermes Agent" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

OpenCode

Add the provider to opencode.json in your project (or ~/.config/opencode/opencode.json), then pick GremlinGPT with /models.

json

{
  "$schema": "https://opencode.ai/config.json",
  "model": "gremlin/gremlin-gpt",
  "provider": {
    "gremlin": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "GremlinGPT",
      "options": { "baseURL": "https://api.gremlingpt.com/v1", "apiKey": "{env:GREMLIN_API_KEY}" },
      "models": { "gremlin-gpt": { "name": "GremlinGPT", "limit": { "context": 1000000, "output": 8192 } } }
    }
  }
}

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect OpenCode to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "OpenCode" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Codex CLI

Codex talks to custom providers through the Responses API, which the gremlin supports. Add this to ~/.codex/config.toml.

toml

# ~/.codex/config.toml
model = "gremlin-gpt"
model_provider = "gremlin"

[model_providers.gremlin]
name = "GremlinGPT"
base_url = "https://api.gremlingpt.com/v1"
env_key = "GREMLIN_API_KEY"
wire_api = "responses"
stream_idle_timeout_ms = 600000

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Codex CLI to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Codex CLI" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Aider

The openai/ prefix tells Aider to use an OpenAI-compatible server.

bash

export OPENAI_API_BASE="https://api.gremlingpt.com/v1"
export OPENAI_API_KEY="$GREMLIN_API_KEY"
aider --model openai/gremlin-gpt

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Aider to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Aider" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Editors

Cline · Roo Code · Kilo Code

The three extensions are set up the same way.

1Open the extension's settings → API Provider: "OpenAI Compatible".
2Base URL: https://api.gremlingpt.com/v1
3API Key: your key.
4Model ID: gremlin-gpt
5Model configuration → Context window: 1000000.

Continue

Add the model to ~/.continue/config.yaml (works in VS Code and JetBrains) and save the key as the GREMLIN_API_KEY secret.

yaml

# ~/.continue/config.yaml
name: GremlinGPT
version: 1.0.0
schema: v1
models:
  - name: GremlinGPT
    provider: openai
    model: gremlin-gpt
    apiBase: https://api.gremlingpt.com/v1
    apiKey: ${{ secrets.GREMLIN_API_KEY }}
    roles: [chat, edit, apply]
    defaultCompletionOptions:
      contextLength: 1000000

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Continue to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Continue" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Cursor

Cursor lets you swap the OpenAI base URL for your own.

1Cursor Settings → Models → API Keys.
2OpenAI API Key: your key.
3Turn on "Override OpenAI Base URL" and enter https://api.gremlingpt.com/v1
4Models → Add model: gremlin-gpt, then select it in the chat.

Note: Cursor's own built-in models keep working; the gremlin is used when you pick gremlin-gpt.

Chat apps

SillyTavern

Use the Chat Completion API with a custom OpenAI-compatible source.

1API Connections → API: Chat Completion.
2Chat Completion Source: Custom (OpenAI-compatible).
3Custom Endpoint (Base URL): https://api.gremlingpt.com/v1
4Custom API Key: your key; Model ID: gremlin-gpt → Connect.

Open WebUI

Add the gremlin as an OpenAI connection.

1Admin Panel → Settings → Connections → OpenAI API → +.
2URL: https://api.gremlingpt.com/v1
3Key: your key → Save.
4Pick gremlin-gpt in the model list of a new chat.

LibreChat · Chatbox · Jan

These apps all have an "OpenAI-compatible" / "Custom provider" option.

1Add a custom provider of type OpenAI-compatible.
2API host / Base URL: https://api.gremlingpt.com/v1
3API key: your key; model: gremlin-gpt.

Code & automation

curl

The API is OpenAI-compatible: anything that lets you set a custom OpenAI URL works with the gremlin.

bash

curl https://api.gremlingpt.com/v1/chat/completions \
  -H "Authorization: Bearer $GREMLIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gremlin-gpt","messages":[{"role":"user","content":"Hi"}],"stream":true}'

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect curl to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "curl" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Python

The official openai library, just with a different base_url.

python

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.gremlingpt.com/v1", api_key=os.environ["GREMLIN_API_KEY"], timeout=600)
r = client.chat.completions.create(
    model="gremlin-gpt",
    messages=[{"role": "user", "content": "Hi"}],
)
print(r.choices[0].message.content)

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Python to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Python" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

Node.js

The official openai package for Node.js, with a different baseURL.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.gremlingpt.com/v1", apiKey: process.env.GREMLIN_API_KEY, timeout: 600_000 });
const r = await client.chat.completions.create({
  model: "gremlin-gpt",
  messages: [{ role: "user", content: "Hi" }],
});
console.log(r.choices[0].message.content);

Let your agent set itself up

Paste this into the agent — it reads our instructions and configures itself:

prompt

Connect Node.js to GremlinGPT. Read https://gremlingpt.com/llms.txt and follow the "Node.js" section exactly. Take my API key from the GREMLIN_API_KEY environment variable — never print it, and never write it into a file inside a git repository. When done, send one test message and tell me whether it worked.

n8n

Use n8n's OpenAI nodes with your own base URL.

1Credentials → New → OpenAI.
2API Key: your key; Base URL: https://api.gremlingpt.com/v1 → Save.
3In an OpenAI / AI Agent node pick this credential and type the model: gremlin-gpt.