mingyan

Claude Messages API

Claude Messages interface based on the Anthropic native request format

POST/gw_llm_power/v1/messages
baseUrlhttp://apillm.globalaiopc.com/gw_llm_power
Compatible with the Anthropic official documentation. You can integrate directly with the following reference:

Authentication

Get Key
Use the Authorization header for authentication.
cURL
Authorization: Bearer {{YOUR_API_KEY}}
Content-Type: application/json
Notes:
  • Authorization: API key in the format Bearer {{YOUR_API_KEY}}

Import to CC Switch

After clicking "Import to CC Switch", you can enter your API Key on the page and choose models from the four dropdowns. The default uses gpt-5.4-low first.

Supported Models

The following models are supported, organized by model family and version type:

Claude

Full VersionOfficial VersionAWS VersionAccount Pool / Proxy Version
claude-haiku-4-5claude-haiku-4-5-officialclaude-haiku-4-5-hcclaude-haiku-4-5-fd
claude-opus-4-5claude-opus-4-5-officialclaude-opus-4-5-hcclaude-opus-4-5-fd
claude-opus-4-6claude-opus-4-6-officialclaude-opus-4-6-hcclaude-opus-4-6-fd
claude-opus-4-7claude-opus-4-7-officialclaude-opus-4-7-hcclaude-opus-4-7-fd
claude-sonnet-4-5claude-sonnet-4-5-officialclaude-sonnet-4-5-hcclaude-sonnet-4-5-fd
claude-sonnet-4-6claude-sonnet-4-6-officialclaude-sonnet-4-6-hcclaude-sonnet-4-6-fd

GPT Models Compatible with Claude Messages API

Official VersionOfficial VersionPremium Account PoolMixed Account Pool / Proxy VersionLow-cost Version
gpt-5.4gpt-5.4-officialgpt-5.4-hcgpt-5.4-fdgpt-5.4-low
gpt-5.5gpt-5.5-officialgpt-5.5-hcgpt-5.5-fdgpt-5.5-low

Version Notes

Suffix / TypeDescription
no suffixOfficial version
-officialOfficial version
-hcAWS version or premium account pool version
-fdAccount pool / proxy version
-lowLow-cost version
Claude Messages API uses the Claude request schema and is not suitable for the official Gemini native format. For Gemini native requests, use the Gemini Native API. GPT models can be called through this format, but image recognition is currently not supported for them.

Multimodal Support

Image Analysis

Only the following models do not support image analysis:
  • gpt-5.4
  • gpt-5.4-official
  • gpt-5.4-fd
  • gpt-5.4-hc
  • gpt-5.4-low
  • gpt-5.5
  • gpt-5.5-official
  • gpt-5.5-fd
  • gpt-5.5-hc
  • gpt-5.5-low

Request Parameters

modelstringrequired
Model name to use, for example: claude-opus-4-7 or gpt-5.5
max_tokensintegerrequired
Maximum number of tokens allowed for this request
messagesarrayrequired
Message array in Claude Messages format
messages[].rolestringrequired
Message role, commonly user or assistant
messages[].contentstring/arrayrequired
Message content. Can be a string or a Claude native content block array
systemstring
Optional system prompt
streamboolean
Whether to enable streaming responses. When enabled, Claude-style streaming events are returned
temperaturenumber
Sampling temperature

Response

Returns a Claude Messages-style response.
idstring
Unique response identifier
typestring
Response type, usually message
rolestring
Returned message role, usually assistant
content[].typestring
Content block type, commonly text
content[].textstring
Generated text content
stop_reasonstring
Generation stop reason
usage.input_tokensinteger
Input token count
usage.output_tokensinteger
Output token count

Notes

  1. The Claude-format request path is POST /v1/messages
  2. For streaming responses, pass "stream": true in the request body
  3. Pass the API key using the Authorization header