Alla modellerchatHermes 4 70B

Hermes 4 70B

av Nous ResearchSnabb

Testa på Kunya
N
chat

Hermes 4 70B

Efficient uncensored reasoning model from Nous Research — hybrid think/respond mode, low refusal rates, strong at math, code, and structured output

Modell-ID:hermes-4-70b

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "hermes-4-70b",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false
}
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":"hermes-4-70b","messages":[{"role":"user","content":"Hello!"}],"stream":false}'

Anteckningar

  • •OpenAI-compatible endpoint — works with any Kunya API key.
  • •Set `"stream": true` for server-sent events.
Fullständig API-referensOpenAPI-spec

Priser

Indata$0.169 per 1M tokens
Utdata$0.52 per 1M tokens
Kontextfönster131K

Funktioner

Streaming Ja
Vision Nej
Resonemang Nej
Verktyg Nej
LeverantörNous Research
Testa på Kunya

Liknande modeller

GLM 4.5 Air

Z-AI

Lightweight GLM model

API-dokumentation

Nemotron 3 Nano

NVIDIA

Nvidia's compact free MoE model for fast chat and lightweight tasks

API-dokumentation

o4 mini

OpenAI

Fast, cost-efficient reasoning model

API-dokumentation

Grok 3 Mini

xAI

Smaller, faster Grok with reasoning

API-dokumentation