Alla modellerchatKunya Tab v1

Kunya Tab v1

av KunyaSnabb

Testa på Kunya
Kunya
chat

Kunya Tab v1

Fast Tab completion router — routes to the configured flash model with curation telemetry.

Modell-ID:kunya-tab-v1

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "kunya-tab-v1",
  "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":"kunya-tab-v1","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.

Priser

Indata$0.286 per 1M tokens
Utdata$0.858 per 1M tokens
Kontextfönster128K

Funktioner

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

Rankningar

Programming#5

Liknande modeller

DeepSeek V4 Flash

DeepSeek

1M context, thinking + non-thinking modes, tool calls

API-dokumentation

DeepSeek V4.1 Flash 1017

DeepSeek

Oct 17, 2026 V4.1 Flash snapshot (CED MoE) — native vision, coding & agentic workloads, 1M context, compressed KV cache

API-dokumentation

Dolphin Mistral 24B Venice

Venice

Venice uncensored Dolphin on Mistral 24B — low refusal creative chat (OpenRouter). No Kunya tool/web_search on this route — use Hermes or Grok for tools.

API-dokumentation

Llama 3.3 70B

Meta

Meta's powerful open source model

API-dokumentation