Docs
TryLLM speaks the OpenAI API. Anything that can talk to OpenAI can talk to TryLLM — change two settings and you're done.
Get your API keyBase URL and authorization
Base URL
https://trychat.net/api/public/llm/v1Header
Authorization: Bearer sk-llm_…Keys start with sk-llm_. Create and revoke them in your dashboard — a key is shown in full only once.
curl
chat/completions
curl https://trychat.net/api/public/llm/v1/chat/completions \
-H "Authorization: Bearer sk-llm_your_key" \
-H "Content-Type: application/json" \
-d '{
"model": "tryllm-chat",
"messages": [{ "role": "user", "content": "Explain recursion in one line." }]
}'OpenAI SDK
Python
from openai import OpenAI
client = OpenAI(
api_key="sk-llm_your_key",
base_url="https://trychat.net/api/public/llm/v1",
)
response = client.chat.completions.create(
model="tryllm-chat",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)JavaScript / TypeScript
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "sk-llm_your_key",
baseURL: "https://trychat.net/api/public/llm/v1",
});
const response = await client.chat.completions.create({
model: "tryllm-chat",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Streaming
Set stream: true and read server-sent chunks, exactly as with OpenAI.
Streaming
const stream = await client.chat.completions.create({
model: "tryllm-chat",
messages: [{ role: "user", content: "Write a haiku about yellow." }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}Models
Fetch the live list any time from GET https://trychat.net/api/public/llm/v1/models.
Errors
Error shape and codes
{
"error": {
"message": "Invalid API key.",
"type": "invalid_request_error",
"code": "invalid_api_key"
}
}
401 invalid_api_key The key is wrong, revoked or missing.
402 insufficient_credit Allowance used up and no credit left.
404 model_not_found That model id does not exist.
429 rate_limit_exceeded Too many requests — slow down or upgrade.
500 server_error Something failed on our side. Retry.Recommended apps
Cursor
- 1Settings → Models → OpenAI API Key.
- 2Turn on "Override OpenAI Base URL" and paste https://trychat.net/api/public/llm/v1.
- 3Paste your sk-llm_ key, add the model id tryllm-chat, then verify.
VS Code (Continue or Cline)
- 1Open the extension settings and add a new model provider of type OpenAI.
- 2Set apiBase to https://trychat.net/api/public/llm/v1 and apiKey to your sk-llm_ key.
- 3Set the model to tryllm-chat (or tryllm-reasoner) and save.
Zed
- 1Open Settings → Assistant → OpenAI compatible provider.
- 2Set the API URL to https://trychat.net/api/public/llm/v1 and paste your key.
- 3Pick tryllm-chat in the assistant model picker.
Open WebUI
- 1Admin Panel → Settings → Connections → OpenAI API.
- 2Set the API base URL to https://trychat.net/api/public/llm/v1 and the key to sk-llm_...
- 3Save, then choose a TryLLM model in a new chat.
Any OpenAI-compatible client
- 1Point the base URL at https://trychat.net/api/public/llm/v1.
- 2Send your key as the Authorization: Bearer header.
- 3Use one of the model ids listed above — everything else is standard OpenAI.
