Alla modellerchatGemini 3.1 Flash-Lite

Gemini 3.1 Flash-Lite

av GoogleSnabb

Testa på Kunya
chat

Gemini 3.1 Flash-Lite

Cheapest frontier-class model — half the cost of Gemini 3 Flash with strong tool calling

Modell-ID:gemini-3.1-flash-lite

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "gemini-3.1-flash-lite",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "max_tokens": 4096
}
cURL-exempel
curl -X POST https://kunya.ai/api/v1/chat/completions \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"gemini-3.1-flash-lite","messages":[{"role":"user","content":"Hello!"}],"stream":false,"max_tokens":4096}'

Anteckningar

  • •OpenAI-compatible endpoint — works with any Kunya API key.
  • •Set `"stream": true` for server-sent events.
  • •Supports vision: pass image URLs in message content as `{ "type": "image_url", "image_url": { "url": "..." } }`.
  • •Supports tool calling via the `tools` parameter.

Priser

Indata$0.325 per 1M tokens
Utdata$1.95 per 1M tokens
Kontextfönster1049K

Funktioner

Streaming Ja
Vision Ja
Resonemang Nej
Verktyg Ja
LeverantörGoogle
Testa på Kunya

Liknande modeller

Gemini 2.5 Flash-Lite

Google

Fastest flash model for cost-efficiency

API-dokumentation

Gemini 3.8 Live

Google

Default Live API model for low-latency voice agents — fluid dialogue without reasoning delays

API-dokumentation

GPT-5 mini

OpenAI

A faster, cost-efficient version of GPT-5

API-dokumentation

Seed 2.0 Lite

ByteDance

Versatile multimodal model with low latency for agent and vision tasks

API-dokumentation