Gemini 3.6 Flash

GoogleTextReasoningToolsVision

Gemini 3.6 Flash: the same family as 3.5 at half the upstream price - coding, agents and multimodal work.

Our price
$0.64 / $3.19
input / output per 1M
Official
$0.75 / $3.75
15% vs official

First request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.altrouter.ai/v1",
    api_key="ar-...",
)

resp = client.chat.completions.create(
    model="gemini-3.6-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
API

OpenAI-compatible chat completions endpoint, with SSE streaming.

POST/v1/chat/completions
Body parameters
modelstringrequired"gemini-3.6-flash"
The model id.
messagesarrayrequired
The conversation: [{ role, content }].
streambooleandefault false
Stream the response over SSE.
temperaturenumber0–2default 1
Sampling randomness: lower is more deterministic, higher more creative.
top_pnumber0–1default 1
Nucleus sampling - the probability mass to sample from.
max_tokensnumber1–32000
Maximum tokens to generate.
reasoning_effortenumlow · medium · highdefault medium
Thinking budget for reasoning models.
seednumber0–2147483647
Seed for reproducibility.
frequency_penaltynumber-2–2
Penalizes tokens by their existing frequency.
presence_penaltynumber-2–2
Penalizes tokens that have already appeared.
web_searchbooleandefault false
Server-side web search - answers with live data.

Structured fields (tools, response_format, stop and more) are in the full parameter reference.

Response
idstring
Completion id.
choicesarray
Completions. Each: index, message { role, content, reasoning_content, tool_calls }, finish_reason.
usageobject
Tokens: prompt_tokens, completion_tokens, total_tokens.
Example
cURLPythonJSON
curl https://api.altrouter.ai/v1/chat/completions \
  -H "Authorization: Bearer ar-..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-3.6-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "reasoning_effort": "medium"
}'
Errors
400Invalid request.
401Missing or invalid API key.
402Insufficient credits, or the key’s spending cap is exhausted.
404Model not found.
429Rate limit exceeded.

More from Google