ERNIE 5.5 Flash Preview

NEW

Model ID

Put this value in the request body's `model` field — not the display name above.

Text generationReasoningToolsJSON1MClosed source

by baidu · Baidu ERNIE 5.5 Flash Preview: the newest ERNIE base model (preview), 280B total and 14B active parameters per token, built for coding, agents, knowledge work and deep research. 1M context and up to 1M output. Reasoning cannot be turned off (thinking tokens bill as output); tool calling and JSON output, text-only input. Billed at Baidu's official peak / off-peak prices: list price 8:00-22:00 Beijing time every day, half price 22:00-8:00.

Try it now

Quick start

EndpointPOST /v1/chat/completions
AuthenticationAuthorization: Bearer sk-gpushare-…Get API key
Call styleSynchronous: one request returns the result
Base URLhttps://qd.zsopc.com/v1
cURL
curl https://qd.zsopc.com/v1/chat/completions \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ernie-5.5-flash-preview",
    "messages": [
      {"role": "user", "content": "你可以帮我做什么"}
    ]
  }'

Pricing

Billed per token: input and output are priced separately and settled on the upstream's reported usage.

Rates
Input 0.12Credits/K·Output 0.48Credits/K
  • Input tokens that hit the prompt cache are billed at 12 Credits / 1M — cheaper than full-price input.
  • Failed requests (upstream 4xx / 5xx) are not billed.
  • All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.

Sign in and any personal discount on your account will show up here. Sign in

Capabilities & specs

Category
Text generation
Context window
1M tokens
Default max output
66k tokens
Endpoint family
Chat Completions
Protocols
OpenAI Chat
Released
2026-11-10
License
Closed source

Try it

Pick a key under "API access" and fire one real request to see the response — the estimated cost is shown before you send.

Common errors

404 model_not_found

You passed the display name instead of the model ID.✗ ERNIE 5.5 Flash Preview→✓ ernie-5.5-flash-preview

→ Copy the Model ID at the top of this page

402 quota_exceeded

Insufficient account balance. All your API keys share one balance.

→ Add funds in your account

401 / 403

The API key is invalid, or it has a model allowlist that doesn't include this ID.

→ Check the key's status and allowed models

400 invalid_request

A request body field is invalid, or this model doesn't support the protocol endpoint you called.

→ Check your request body against the sample code above

Try it

ERNIE 5.5 Flash Preview FAQ

How do I call ERNIE 5.5 Flash Preview?
Set the model field of the request body to ernie-5.5-flash-preview, send it to https://qd.zsopc.com/v1/chat/completions, and put your key (it starts with sk-gpushare-) in the Authorization: Bearer header. The official OpenAI, Anthropic and Google Gemini SDKs all work directly; just point base_url at this gateway.
How much does the ERNIE 5.5 Flash Preview API cost?
  • Input: 120 credits (≈ ¥2 / ≈ $0.297) per 1M tokens
  • Output: 480 credits (≈ ¥8 / ≈ $1.19) per 1M tokens
  • Cached input: 12 credits (≈ ¥0.2 / ≈ $0.03) per 1M tokens
  • Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.
How large is ERNIE 5.5 Flash Preview's context window?
1,048,576 tokens, with a default output limit of 65,536 tokens per request.
What can ERNIE 5.5 Flash Preview do?
Tool calling, Thinking mode, JSON mode. Compatible protocols: OpenAI Chat Completions.

Prices and details updated 2026-11-17. Input price is about $0.297 per 1M tokens. Markdown version of this page: /en/models/ernie-5.5-flash-preview.md

Related