All ModelschatERNIE 5.5 Flash Preview

ERNIE 5.5 Flash Preview

by BaiduFast

Try on Kunya
B
chat

ERNIE 5.5 Flash Preview

Baidu ERNIE 5.5 Flash — 280B MoE foundation model with coding, agentic tool use, knowledge work, and deep research; 1M context

Model ID:ernie-5.5-flash-preview

API Documentation

Generate chat completions with this model.

POST/api/v1/chat/completions
GET /api/v1/models?type=chat
Request body
{
  "model": "ernie-5.5-flash-preview",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "thinking": true,
  "max_tokens": 4096
}
cURL example
curl -X POST https://kunya.ai/api/v1/chat/completions \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"ernie-5.5-flash-preview","messages":[{"role":"user","content":"Hello!"}],"stream":false,"thinking":true,"max_tokens":4096}'

Notes

  • •OpenAI-compatible endpoint — works with any Kunya API key.
  • •Set `"stream": true` for server-sent events.
  • •Supports tool calling via the `tools` parameter.
Full API referenceOpenAPI spec

Pricing

Input$0.364 per 1M tokens
Output$1.469 per 1M tokens
Context Window1024K

Capabilities

Streaming Yes
Vision No
Reasoning Yes
Tool Use Yes
ProviderBaidu
Try on Kunya

Similar Models

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 Documentation

LFM3 1.7B

LiquidAI

Compact 1.7B agent model with 256K context — tool calling, structured outputs, and built-in reasoning before answer text. Text-only; ideal for cheap subagents and high-volume classification.

API Documentation

DeepSeek V4 Flash

DeepSeek

Now served by V4.1 Flash 1017 — 1M context, thinking + non-thinking modes, tool calls

API Documentation

MiniMax M2.7 Highspeed

MiniMax

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

API Documentation