# Call an open model

[Open models](https://www.rightnowai.co/docs/open-models) / [Call an open model](https://www.rightnowai.co/docs/open-models/quickstart)

Updated 2026-11-11

This quickstart makes a compatible chat-completions request from your server using the open-models API base and a workspace API key. An open-models workspace key (`rp_...`) works with this API.

Using a coding agent? Your agent can set up the open-models service for you. Copy the prompt from [Set up with your coding agent](https://www.rightnowai.co/docs/open-models/guides/coding-agents).

Replace `MODEL_ID` with an available id from [Open models](https://runinfra.ai/inference-api?utm_source=rightnowai.co&utm_medium=referral&utm_content=docs-open-models); read current capabilities, limits and prices from `GET /v1/models`.

**Open-model connection settings**

| Connection | Value |
| --- | --- |
| API base | `https://api.runinfra.ai/v1` |
| Authentication | `Authorization: Bearer` with an `rp_...` workspace key |
| Process variable | `RUNINFRA_GATEWAY_KEY` |
| Model | Replace `MODEL_ID` with an available ID from `/v1/models` |
| Billing | Your open-model account's existing funding rules |

Keep the connection values as written. Use the key for this API.

## Get a workspace API key

Open the [Model Library](https://runinfra.ai/inference-api?utm_source=rightnowai.co&utm_medium=referral&utm_content=docs-open-models), 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.

## Put the key in your environment

Keep the key in your server's secret store and inject it into the calling process as `RUNINFRA_GATEWAY_KEY`. The example reads that variable explicitly. Do not put the key in browser code or a prompt.

## List the live models

Run `GET /v1/models` for the current list; paused models are reported there and on their model pages. Choose an available ID with chat support. See [Models](https://www.rightnowai.co/docs/open-models/models) for the discovery fields.

## Make the call

Replace `MODEL_ID` below with that ID. This example sends one generation request and can spend open-model credit.

**Python**

```python
import json
import os
from urllib.request import Request, urlopen

base = "https://api.runinfra.ai/v1"
model_id = "MODEL_ID"
if model_id == "MODEL_ID":
    raise SystemExit("Replace MODEL_ID with an ID from /v1/models.")

headers = {
    "Authorization": "Bearer " + os.environ["RUNINFRA_GATEWAY_KEY"],
    "Content-Type": "application/json",
}

with urlopen(Request(base + "/models", headers=headers)) as response:
    models = json.load(response)
available = {row["id"]: row for row in models["data"]
             if row.get("availability") == "available"
             and "chat_completions" in row.get("supported_endpoints", [])}
if model_id not in available:
    raise SystemExit("Choose an available ID from the list.")

limit = available[model_id].get("max_output_tokens")
if type(limit) is not int or limit <= 0:
    raise SystemExit("The model list does not declare a usable output limit.")
output_budget = min(16_384, limit)

body = {
    "model": model_id,
    "messages": [{"role": "user", "content": "Say hello in one sentence."}],
    "max_tokens": output_budget,
}
request = Request(base + "/chat/completions", headers=headers,
                  data=json.dumps(body).encode("utf-8"), method="POST")
with urlopen(request) as response:
    request_id = response.headers.get("x-request-id")
    reply = json.load(response)
print(reply["choices"][0]["message"]["content"])
```

The example uses a generous output budget of 16,384 tokens where the selected model's published limit permits it; reasoning shares that budget. It takes the minimum of 16,384 and the live `max_output_tokens`. That sample budget is not a service maximum. If discovery omits the limit, the sample stops instead of guessing. The gateway may clamp further to the remaining context; see [Output limits](https://www.rightnowai.co/docs/open-models/chat-completions#output-limits).

## What comes back

In a normal completion, `reasoning` carries the model's thinking and `content` carries the answer. Token counts and ids in response examples are illustrative. Check `finish_reason` before using the answer: `stop` means the model finished on its own, and `length` means the output budget ended the reply.

Keep the request ID when reporting a problem. Use the [open-model errors](https://www.rightnowai.co/docs/open-models/errors) and [retry guides](https://www.rightnowai.co/docs/open-models/idempotent-retries) before adding automatic retries.

## 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.

For a model that reports reasoning support, 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.

A reasoning model can exhaust a 2,048-token budget before an answer; a 16,384-token budget leaves more room where the live model limit permits it. In measurements on 2026-08-14, a 2,048-token budget produced an empty or truncated answer. Under the current usage contract, a response with no answer settles at zero; older measurements that billed output are historical.

Read the live model's capabilities before requesting reasoning, tools, structured output or images.

## Next steps

[Source reference](https://runinfra.ai/docs/api-reference/model-apis-quickstart?utm_source=rightnowai.co&utm_medium=referral&utm_content=docs-open-models)

[Chat completions and Responses](https://www.rightnowai.co/docs/open-models/chat-completions), [Streaming](https://www.rightnowai.co/docs/open-models/streaming), [compatible clients](https://www.rightnowai.co/docs/sdks/open-models), or [use the RightNow model](https://www.rightnowai.co/docs/system-zero/quickstart).

## Next

[Models](https://www.rightnowai.co/docs/open-models/models)