Model specifications
- Context
- 1,024,000 tokens
- Maximum output
- 131,072 tokens
- Architecture
- text->text
- Tokenizer
- Other
- Knowledge cutoff
- Not provided
- Moderated
- No
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $1.13 per 1M tokens
- Output
- $3.94 per 1M tokens
- Cache read
- $0.113 per 1M tokens
Model configuration
Reasoning
- Reasoning required
- No
- Default parameters
- max
- Capabilities
- max, high, low, none
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"baidu/ernie-light-dt-1.0-intl","messages":[{"role":"user","content":"Hello!"}]}'Input → Output
Yes · max · high · low · none
Supported API parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstructured_outputstemperaturetool_choicetoolstop_p1 Provider
Checked: November 11, 2026
Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
Baidu
Not provided- Context
- 1.0M
- Maximum output
- 131K
- Input
- $1.13
- Output
- $3.94
- Cache read
- $0.113
- Cache write
- Not provided