Gwarden AI
96 models
96 models for code, agents and any task - via one simple API.
Get your key in Telegram, start with a free 7-day trial.
Model lineup
Faster API Endpoints
Dedicated high-speed URLs with priority routing — no rate limits, no auth hiccups, no delays. Buy once, use forever.
Dedicated high-speed path with priority routing. No rate limits, no auth hiccups, no waiting on key rotation.
https://boost.gwarden.su/v1Maximum throughput with redundant failover. Built for agents that cannot afford delays.
https://dev.gwarden.su/v1Reserve gateway: swaps across every catalog model and works when the whole main service is down.
https://emergency.gwarden.su/v1Unlock the Gwarden AI model: friendly coding assistant, 1M context. One-time $2, yours forever.
"model": "gwarden-ai"Subscriptions
Every 5 hours your balance refills to the plan limit. Start - free 7 days. Per 1M tokens: Input 0.15, Output 0.5, Cache 0.03. Top-up: 1$ = 20.0$.
I can't pay for the subscription - what do I do?
Open the @xRocket payment guideLaunch in a minute
Get a key
Open the bot, subscribe to the channel, press «Get API».
Add config
Add baseURL and apiKey to your tool.
Done
Works with opencode, Claude Code and any OpenAI client.
Launch Claude Code in one command
export ANTHROPIC_BASE_URL="https://gwarden.su" export ANTHROPIC_AUTH_TOKEN="GWAR-XXXX" export ANTHROPIC_MODEL="glm-5.3[1m]" claude
Your key is in the cabinet. Codex, opencode and aider setups - in the documentation.
Or the raw API
# opencode - check the model
curl https://gwarden.su/v1/chat/completions \
-H "Authorization: Bearer GWAR-XXXX" \
-H "Content-Type: application/json" \
-d '{"model": "MODEL", "messages": [{"role": "user", "content": "Hello"}]}'