Alla modellerchatMercury 2.5 Preview

Mercury 2.5 Preview

av InceptionSnabb

Testa på Kunya
I
chat

Mercury 2.5 Preview

Fastest reasoning diffusion LLM — parallel token generation (~140 tps), tunable reasoning, tool calling, and JSON schema output. Built for search agents, voice pipelines, and coding subagents.

Modell-ID:mercury-2.5-preview

API-dokumentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "mercury-2.5-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":"mercury-2.5-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 tool calling via the `tools` parameter.
Fullständig API-referensOpenAPI-spec

Priser

Indata$0.052 per 1M tokens
Utdata$0.195 per 1M tokens
Kontextfönster260K

Funktioner

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

Liknande modeller

Nemotron 3.5 Lightning

NVIDIA

30B MoE (3B active) — high-throughput agentic workloads, tool calling, 1M context. Free on OpenRouter (rate-limited). Newer/fast tier vs Nemotron 3 Nano.

API-dokumentation

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

API-dokumentation

DeepSeek V4 Flash

DeepSeek

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

API-dokumentation

MiniMax M2.7 Highspeed

MiniMax

M2.7 at ~100 tps — same performance, faster and more agile

API-dokumentation