Alla modellerchatStep 5 Preview

Step 5 Preview

av StepFunPremium

Testa på Kunya
S
chat

Step 5 Preview

StepFun flagship agentic MoE (27B active) — sparse experts, image & video input, tool use, 1M context

Modell-ID:step-5-preview

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "step-5-preview",
  "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":"step-5-preview","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$1.3 per 1M tokens
Utdata$3.51 per 1M tokens
Kontextfönster1049K

Funktioner

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

Liknande modeller

Muse Wonder

Meta

Meta frontier reasoning model for long-horizon agentic work — plans, delegates to sub-agents, parallel tool use, and error recovery across text, image, video, audio, and PDF input with 1M context. Strong on multi-file engineering, extended sessions, and browser or desktop automation workflows.

API-dokumentation

Muse Spark 1.3

Meta

Meta multimodal reasoning model for long-running agentic, multi-agent, and coding workflows — text, image, video, PDF, and audio input with 1M context, tool calling, structured output, and configurable reasoning. Available globally on OpenRouter (unlike Muse Spark 1.1). Audio understanding is still limited upstream.

API-dokumentation

GPT-6 Astra

OpenAI

OpenAI flagship for complex reasoning, coding, computer use, and agentic work

API-dokumentation

Grok 4.3

xAI

Fast, intelligent Grok — 1M context, 3 reasoning levels, top agentic tool calling

API-dokumentation