Gemini native

generateContent and streamGenerateContent in the native Gemini format.

Generates content in the native Gemini format. Works with the official Gemini SDK (google-genai).

Method and path

POST/v1beta/models/{model}:generateContent

POST/v1beta/models/{model}:streamGenerateContent

Gemini SDKs take the base URL https://api.relayvia.dev. Put the model name in the path and send the key as x-goog-api-key: sk-... or Authorization: Bearer sk-....

Common parameters

Parameter	Type	Required	Description
model	string	Yes	Official model name, in the path.
alt	string	No	`sse` on streamGenerateContent for Server-Sent Events; without it the stream is a JSON array.
contents	array	Yes	The conversation: user and model turns made of parts.
systemInstruction	object	No	System instruction.
generationConfig	object	No	Generation settings, including `maxOutputTokens` (it decides the reservation) and `candidateCount`.
tools	array	No	Only `functionDeclarations`.
toolConfig	object	No	Function calling mode.

Requests are forwarded in the original format, so the original API's parameters work unless the next section says otherwise. This table lists the common ones; see the official reference for the rest.

Differences from the original API

Only generateContent and streamGenerateContent are served; other actions such as countTokens and embedContent return 404.
Cached content (cachedContent) and files stored at Google (file_data.file_uri pointing to files/..., generativelanguage.googleapis.com or gs://) return 400 unsupported_parameter. Remote files other than images are refused too; send the data inline with inline_data.
Tools only accept functionDeclarations. Google Search, code execution and other built-in tools return 400 unsupported_parameter.
candidateCount must be a positive integer, otherwise 400 invalid_request. The reservation and the charge cover every candidate.
modelVersion in the response is the model name you sent.
A non-streaming request with no response within 95 seconds returns 500 upstream_timeout; use streaming for long outputs. Or send the header X-Robi-Keepalive: 1: if there is no response within 30 seconds you get a 200 right away and a space every 15 seconds until the JSON arrives, and a later failure arrives as an error object in the body.

Request examples

cURL

curl https://api.relayvia.dev/v1beta/models/gemini-3.6-flash:generateContent \
  -H "x-goog-api-key: sk-..." \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"role":"user","parts":[{"text":"Hello!"}]}]}'

Python

from google import genai

client = genai.Client(api_key="sk-...", http_options={"base_url": "https://api.relayvia.dev"})
resp = client.models.generate_content(model="gemini-3.6-flash", contents="Hello!")
print(resp.text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "sk-...", httpOptions: { baseUrl: "https://api.relayvia.dev" } });
const resp = await ai.models.generateContent({ model: "gemini-3.6-flash", contents: "Hello!" });
console.log(resp.text);

Response and streaming examples

Response

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Hello! How can I help?"
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 9,
    "candidatesTokenCount": 8,
    "totalTokenCount": 17
  },
  "modelVersion": "gemini-3.6-flash"
}

Streaming

data: {"candidates":[{"content":{"role":"model","parts":[{"text":"Hello!"}]}}],"modelVersion":"gemini-3.6-flash"}

data: {"candidates":[{"content":{"role":"model","parts":[{"text":" How can I help?"}]},"finishReason":"STOP"}],"usageMetadata":{"promptTokenCount":9,"candidatesTokenCount":8,"totalTokenCount":17},"modelVersion":"gemini-3.6-flash"}

Errors this endpoint returns

HTTP	code	When
400	invalid_request	A parameter is invalid. If the model rejected it, the message is this sentence, or `Invalid value for parameter <param>.` with `param` set.
400	unsupported_parameter	The request uses something Relayvia does not offer: stored server-side state, a hosted tool or a remote file. `param` names it.
400	invalid_media	The model reports that an input image or file format is not supported.
400	media_unreachable	The model could not read the media URL you sent.
400	content_policy	The input did not pass the model's safety review. If the model does not say whether the input or the output was refused, the message is `Content did not pass safety review.`
400	content_policy_output	The model generated a result, but the result did not pass safety review. Your input was not the problem.
401	invalid_api_key	The API key does not exist, is disabled or has expired.
402	insufficient_quota	Not enough credits: the account's credits, the key's limit, the team member's limit or an account spend limit cannot cover the request, or the account is frozen.
403	forbidden	The key may not use this model, the source IP is not on the allowlist, or the account is disabled.
404	model_not_found	The model is not listed.
413	request_too_large	The request body is over 20 MB, or the model reports that the input exceeds its context or size limit (then with this sentence).
429	rate_limited	Too many requests: per IP, per key, per account, or too many requests in progress at once.
500	model_price_error	The model has no price yet, so it cannot be called.
500	upstream_error	Relayvia tried other model services and every attempt failed.
503	no_available_channel	No model service is available for this model right now.
503	service_busy	Every model service for this model reported being busy.
500	upstream_timeout	Every attempt timed out.

Every code, its fixed message and what to do are on the error codes page.