Native Gemini Format

In addition to the OpenAI and Anthropic formats, AccelsRouter accepts Google Gemini's native API shape under /v1beta, so code written for the Gemini SDK works with a one-line base-URL change.

Authenticate with your sk- key — pass it as the x-goog-api-key header (the Gemini convention) or as Authorization: Bearer sk-....

List models

GET https://router.accels.tech/v1beta/models

Returns the available models in Gemini's models list shape.

Generate content

POST https://router.accels.tech/v1beta/models/{model}:generateContent

Body is application/json:

Field	Type	Required	Notes
contents	array	✓	The conversation turns / content parts
generationConfig	object	✓	Generation settings (e.g. temperature, maxOutputTokens)

Example

curl "https://router.accels.tech/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "x-goog-api-key: $ACCELSROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{ "parts": [{ "text": "Explain how a router works in one sentence." }] }],
    "generationConfig": { "temperature": 0.7 }
  }'

from google import genai
from google.genai import types

client = genai.Client(
    api_key="sk-...",
    http_options=types.HttpOptions(base_url="https://router.accels.tech"),
)
resp = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Explain how a router works in one sentence.",
)
print(resp.text)

Notes

• {model} is the exact model id from the model marketplace.
• Prefer the OpenAI format (Chat Completions) unless you specifically need Gemini-native features; it reaches the same models with broader SDK support.