Alla modellerchatGemini 3.8 Flash

Gemini 3.8 Flash

av GoogleSnabb

Testa på Kunya
chat

Gemini 3.8 Flash

Most intelligent Flash model — long-horizon software engineering, autonomous agents, and enterprise workflows at Flash speed (intro pricing through Dec 2026)

Modell-ID:gemini-3.8-flash

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "gemini-3.8-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true,
  "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-3.8-flash","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true,"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$0.975 per 1M tokens
Utdata$4.875 per 1M tokens
Kontextfönster1049K

Kunya benchmark

Updated 2026-10-06 · #9 performance · #2 value

Performance
95.7
Value (KVI)
130.0
Literary writing
82.8
Hard tier
77.1
SWE Verified
80.0%
Cost
$0.58/1k tasks
Full benchmark report →

Funktioner

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

Rankningar

Overall#1
Technology#1

Liknande modeller

Gemini 3 Flash

Google

Frontier intelligence with superior search and grounding

API-dokumentation

Gemini 3.5 Flash

Google

Frontier intelligence optimized for agentic workflows, coding, and video at higher speed

API-dokumentation

GPT-6 Luna

OpenAI

Fast, cost-efficient GPT-6 model for chat, classification, high-volume agents, and subagent loops

API-dokumentation

Kunya V1 Fast

Kunya

Admin-only fast stack — Gemini 3.8 Flash execution + GLM 5.3 Flash budget tiers. Maximum speed/cost ratio.

API-dokumentation