Wszystkie modelechatGemini 3.8 Flash

Gemini 3.8 Flash

od GoogleSzybki

Wypróbuj na 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)

ID modelu:gemini-3.8-flash

Dokumentacja API

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Treść żądania
{
  "model": "gemini-3.8-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true,
  "max_tokens": 4096
}
Przykład cURL
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}'

Uwagi

  • •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.
Pełna dokumentacja APISpecyfikacja OpenAPI

Ceny

Wejście$0.975 za 1M tokenów
Wyjście$4.875 za 1M tokenów
Okno kontekstu1049K

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

Comparisons

Full benchmark report →

Możliwości

Streaming Tak
Wizja Tak
Rozumowanie Tak
Narzędzia Tak
DostawcaGoogle
Wypróbuj na Kunya

Rankingi

Overall#1
Technology#1

Podobne modele

Gemini 3.7 Flash

Google

Newest Flash workhorse — best-in-class coding, agents, and multimodal at half the original 3.6 Flash cost (intro pricing through Dec 2026)

Dokumentacja API

Gemini 3.5 Flash-Lite

Google

Fastest 3.5-class model — high-throughput chat, tools, and vision at lower cost than full Flash

Dokumentacja API

Qwen 3.8 Flash

Qwen

Next-gen multimodal reasoning MoE — coding, agentic workflows, visual and long-video analysis, document and codebase understanding, 1M context

Dokumentacja API

GLM 5.3 Flash

Z-AI

Native multimodal flash model — efficient coding and long-horizon agent tasks with 1M context, image & video input, tool calling

Dokumentacja API