> ## Documentation Index
> Fetch the complete documentation index at: https://runinfra.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Model APIs quickstart
> Make a first hosted chat-completions call in three steps.
This quickstart calls the OpenAI-compatible `POST /v1/chat/completions` at `https://api.runinfra.ai/v1` with a workspace API key.
Using a coding agent? Your agent can set up RunInfra's open models for you. Copy the prompt from [Set up with your coding agent](/docs/tools-sdks/agent-setup).
Open the [Model Library](https://runinfra.ai/inference-api), pick a model that is not marked **Paused**, and select **Get API key**. If you already have a key you can copy, the page highlights that key's copy button instead of making another one.
```bash theme={"dark"}
export RUNINFRA_GATEWAY_KEY="rp_your_key_here"
```
```python Python theme={"dark"}
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.runinfra.ai/v1",
api_key=os.environ["RUNINFRA_GATEWAY_KEY"],
)
response = client.chat.completions.create(
model="nemotron-3-5-lightning-30b",
messages=[{"role": "user", "content": "Write a TypeScript retry helper."}],
max_tokens=16384,
)
print(response.choices[0].message.content)
```
```typescript TypeScript theme={"dark"}
import OpenAI from "openai";
// Server side only: never expose this key in browser code.
const client = new OpenAI({
baseURL: "https://api.runinfra.ai/v1",
apiKey: process.env.RUNINFRA_GATEWAY_KEY,
});
const response = await client.chat.completions.create({
model: "nemotron-3-5-lightning-30b",
messages: [{ role: "user", content: "Write a TypeScript retry helper." }],
max_tokens: 16384,
});
console.log(response.choices[0]?.message?.content);
```
```bash cURL theme={"dark"}
curl https://api.runinfra.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNINFRA_GATEWAY_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-5-lightning-30b",
"messages": [{"role": "user", "content": "Write a TypeScript retry helper."}],
"max_tokens": 16384
}'
```
A normal completion. Token counts and ids are illustrative; `reasoning` carries the model's thinking, and `content` carries the answer.
```json theme={"dark"}
{
"id": "chatcmpl-example",
"object": "chat.completion",
"model": "nemotron-3-5-lightning-30b",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"reasoning": "The user wants a retry helper. I should use exponential backoff...",
"content": "export async function retry(fn: () => Promise, attempts = 3) { ... }"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 14,
"completion_tokens": 892,
"total_tokens": 906
}
}
```
Check `finish_reason` before you use `content`. `stop` means the model finished on its own. `length` means it hit the output budget.
## List the live models
Run [`GET /v1/models`](/docs/api-reference/models) for the current list; a model that is temporarily paused is reported there and on its [Model Library](https://runinfra.ai/inference-api) page.
```bash theme={"dark"}
curl https://api.runinfra.ai/v1/models \
-H "Authorization: Bearer $RUNINFRA_GATEWAY_KEY"
```
## How usage is counted
The `usage` counts in the response are the billed counts; a local tokenizer can count differently. Cached input is part of `prompt_tokens`, shows in `usage.prompt_tokens_details.cached_tokens` on models with a cached-input price, and bills at that rate.
## Why max\_tokens is 16,384
These models reason before they answer, and reasoning tokens are billed output that count toward `max_tokens`.
You pay for what is generated, not for the ceiling, so a generous ceiling costs nothing extra and a small one can leave you without an answer.
## Next steps
Every field the gateway forwards, validates, or drops.
Read deltas and ask for the usage frame.
Discover the ids your key can call.
Paste one prompt. Your coding agent sets up RunInfra's open models for you.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.