Handle according to the following process:
- Identify the user's scenario (model invocation, integration solution, troubleshooting).
- Use WebFetch or an equivalent HTTP reading tool to retrieve the minimum required reference files from the mapping table below.
- Treat pricing, model availability, and service status as dynamic data; obtain the latest information before answering.
- Return copy-paste-ready commands or code snippets whenever possible.
- If the local reference files do not cover the required content, provide the closest verified guidance, clearly state the gap, and point to the official live documentation.
LLM (Large Language Model) Quick Reference
| Key | Value |
|---|---|
| API Base URL | https://api.jiekou.ai/openai |
| Authentication method | Authorization: Bearer <API_KEY> |
| Get API Key | https://jiekou.ai/settings/key-management |
| Model list | https://jiekou.ai |
| Pricing | https://jiekou.ai/pricing |
| Console | https://jiekou.ai/console |
Image, Video, Audio API Quick Reference
API AI aggregates mainstream multimodal APIs in the industry, covering three major directions: image generation, video generation, and speech synthesis.
| Key | Value |
|---|---|
| Authentication method | Authorization: Bearer <API_KEY>(same as LLM) |
| Get API Key | https://jiekou.ai/settings/key-management |
| API documentation (MCP) | https://jiekou.mintlify.app/mcp |
| Video unified interface documentation | https://jiekou.ai/docs/models/reference-unified-video-generation |
| Pricing | https://jiekou.ai/pricing |
Documentation Mapping Table
| Question | Read this file | Live documentation |
|---|---|---|
| Quick start | quick-start.md | - |
| LLM API usage | llm-guide.md | API reference |
| Image / Video / Audio API | quick-start.md §3 | MCP tools · Video unified interface |
| Tool integration | integrations.md | - |
| FAQ | faq.md | - |
Reference File Selection Rules
- For initial configuration and minimal examples, use
quick-start.md(see the mapping table above). - For chat completions, tool calling, vision, JSON mode, and batch tasks, use
llm-guide.md(see the mapping table above). - For multimodal APIs such as image generation, video generation, and speech synthesis, use
quick-start.md §3, and point to the MCP tool documentation for complete parameter descriptions. - For integration questions, uniformly use
integrations.md(see the mapping table above) as the entry point, then select sub-documents from it. - When debugging, prioritize using
faq.md(see the mapping table above). - If the original files cannot be retrieved from GitHub, fall back to the local
references/*.mdfiles in this skill directory. - If the answer involves quotas, pricing, or the number of models, first verify through live documentation/API, and note the verification date in the response.
Dynamic Data Policy
- Treat model catalog size, pricing, rate limiting, latency, and regional availability as dynamic data.
- In the final response, mark the verification time of dynamic data in the
Verified on: YYYY-MM-DDformat. - If real-time verification is not possible, clearly state that the data may be outdated and attach the official source link.
Dynamic Data (always obtain the latest values)
Get the latest model list
curl https://api.jiekou.ai/openai/v1/models \
-H "Authorization: Bearer $接口AI_API_KEY"
Current pricing
Visit https://jiekou.ai/pricing to view the latest pricing.