Gwarden AIДокументация API
Base URL: https://gwarden.su - 28 моделей через один API
Выбери свой инструмент
Получение ключа
Открой бота и нажми «Получить API» - ключ в формате GWAR-XXXX. При старте активируется free тариф на 7 дней (пополнение каждые 5ч).
CLI-агенты для кодинга
Работает со всеми крупными CLI-агентами. Установи под свою ОС, затем выбери инструмент. Все они говорят на OpenAI- или Anthropic-совместимом протоколе - направь их на https://gwarden.su.
# macOS brew install node # Linux (Debian / Ubuntu) sudo apt install -y nodejs npm # Windows (PowerShell, admin) winget install OpenJS.NodeJS.LTS # all OS: Claude Code + Codex + opencode npm install -g @anthropic-ai/claude-code @openai/codex opencode-ai # aider (Python) python -m pip install aider-install && aider-install
Замени GWAR-XXXX на свой ключ, а MODEL - на любую модель. Полный список: /v1/models и таблица на главной. Примеры: claude-fable-5-1, gpt-5.6-sol, grok-4.6, kimi-k3, glm-5.3. Tools / агентские циклы полностью поддерживаются.
Claude Code
Одна команда - работает сразу
# macOS / Linux export ANTHROPIC_BASE_URL="https://gwarden.su" export ANTHROPIC_AUTH_TOKEN="GWAR-XXXX" export ANTHROPIC_MODEL="MODEL" claude
# Windows PowerShell $env:ANTHROPIC_BASE_URL = "https://gwarden.su" $env:ANTHROPIC_AUTH_TOKEN = "GWAR-XXXX" $env:ANTHROPIC_MODEL = "MODEL" claude
Codex CLI (OpenAI)
~/.codex/config.toml (Windows: C:/Users/you/.codex/config.toml) model = "MODEL" model_provider = "gwarden" [model_providers.gwarden] name = "Gwarden AI" base_url = "https://gwarden.su/v1" env_key = "GWARDEN_API_KEY" wire_api = "responses"
export GWARDEN_API_KEY="GWAR-XXXX" # Windows: setx GWARDEN_API_KEY "GWAR-XXXX" codex
opencode
~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"gwarden": {
"npm": "@ai-sdk/openai-compatible",
"name": "Gwarden AI",
"options": { "baseURL": "https://gwarden.su/v1", "apiKey": "GWAR-XXXX" },
"models": { "MODEL": { "name": "Gwarden AI" } }
}
}
}opencode --model gwarden/MODEL
aider
# macOS / Linux export OPENAI_API_BASE="https://gwarden.su/v1" export OPENAI_API_KEY="GWAR-XXXX" aider --model openai/MODEL
# Windows PowerShell $env:OPENAI_API_BASE = "https://gwarden.su/v1" $env:OPENAI_API_KEY = "GWAR-XXXX" aider --model openai/MODEL
Chat Completions
curl https://gwarden.su/v1/chat/completions \
-H "Authorization: Bearer KEY" \
-H "Content-Type: application/json" \
-d '{"model": "MODEL",
"messages": [{"role": "user", "content": "Hello"}],
"stream": false}'Список моделей
curl https://gwarden.su/v1/models -H "Authorization: Bearer KEY"
Стриминг
Установи stream: true. В чанках отдельно приходят reasoning_content (мысли) и content (ответ).
Старые запросы с thinking: {{"type": "disabled"}} автоматически перезаписываются в {{"type": "enabled"}} + reasoning_effort: "low".
Claude Code / Anthropic-совместимость
Тот же API отдаётся в формате Anthropic Messages — Claude Code, Cursor и Cline работают из коробки. Укажи адрес и используй свой ключ.
curl https://gwarden.su/v1/messages \
-H "x-api-key: GWAR-XXXX" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "MODEL",
"max_tokens": 4096,
"messages": [{"role": "user", "content": "Hello"}]
}'Подписки
Каждые 5 часов баланс пополняется до лимита тарифа. Баланс в кредитах: Input 0.15 / Output 0.5 / Cache 0.03 за 1M. Пополнение: 1$ = 10.0$.
Chat Completions / models
| Model | Input / 1M | Output / 1M | Cache / 1M | Quality |
|---|---|---|---|---|
| claude-fable-5-1200k / 128k out | $3.50 | $13.00 | $4.00 | 65.7% |
| claude-opus-5200k / 64k out | $2.00 | $10.00 | $2.00 | 63.1% |
| claude-fable-5200k / 128k out | $3.50 | $13.00 | $4.00 | 62.1% |
| gpt-5.6-sol200k / 128k out | $3.50 | $18.00 | $0.35 | 60.9% |
| grok-4.6200k / 64k out | $1.70 | $5.00 | $0.40 | 60.9% |
| kimi-k31M / 64k out | $2.60 | $13.00 | $0.55 | 59.7% |
| glm-5.3200k / 128k out | $0.15 | $0.50 | $0.03 | 59.5% |
| gemini-3.8-flash200k / 64k out | $1.00 | $4.50 | $0.25 | 58.7% |
| qwen3.8-max200k / 64k out | $1.70 | $5.20 | $0.40 | 58.1% |
| qwen3.8-2.4t-a95b200k / 64k out | $0.80 | $1.70 | $0.15 | 57.7% |
| gpt-5.6-terra200k / 128k out | $1.70 | $10.00 | $0.18 | 56.5% |
| claude-sonnet-5200k / 64k out | $1.70 | $8.50 | $0.17 | 56.4% |
| Qwen3.8-Flash-Next200k / 64k out | $0.15 | $0.50 | $0.03 | 56.0% |
| gpt-5.5200k / 128k out | $4.50 | $27.00 | $0.45 | 55.8% |
| muse-spark-1.3-contributor1M / 64k out | $0.40 | $1.60 | $0.08 | 55.1% |
| mercury-2.5200k / 32k out | $0.15 | $0.50 | $0.03 | 55.0% |
| deepseek-v4-pro200k / 64k out | $0.80 | $2.20 | $0.20 | 54.5% |
| glm-5.2200k / 128k out | $1.20 | $3.90 | $0.25 | 53.5% |
| gpt-5.6-luna200k / 128k out | $0.18 | $1.05 | $0.01 | 52.1% |
| deepseek-v4-flash200k / 32k out | $0.30 | $0.90 | $0.08 | 52.0% |
| qwen3.8-27b200k / 32k out | $0.22 | $0.80 | $0.05 | 52.0% |
| gemini-3.1-pro200k / 64k out | $1.75 | $10.50 | $0.45 | 51.2% |
| gpt-oss-120b1M / 64k out | $0.45 | $1.80 | $0.09 | 50.6% |
| agnes-2.5-flash1M / 64k out | $0.35 | $1.40 | $0.07 | 49.8% |
| mimo-v2.5-pro200k / 64k out | $0.60 | $2.20 | $0.15 | 47.5% |
| minimax-m3200k / 64k out | $0.27 | $1.05 | $0.08 | 47.5% |
| deepseek-r1-0528-qwen3-8b1M / 32k out | $0.12 | $0.45 | $0.03 | 44.2% |
| claude-opus-4-8200k / 64k out | $2.00 | $10.00 | $2.00 | - |