Creates a model response for the given chat conversation.
Documentation Index
Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
Use this file to discover all available pages before exploring further.
Authentication via Bearer token. Create an API Key in the Anyfast console and pass it as Bearer YOUR_API_KEY in the Authorization header.
Model ID
deepseek-v4-pro "deepseek-v4-pro"
A list of messages comprising the conversation so far.
1[{ "role": "user", "content": "Hello!" }]Enable or disable thinking mode.
The maximum number of tokens to generate.
x >= 1Set to {"type": "json_object"} to enable JSON mode.
Sequences where the model will stop generating further tokens. Up to 16 strings.
If true, stream partial message deltas using SSE.
Options for streaming. Only valid when stream is true.
Sampling temperature. Higher values make output more random.
0 <= x <= 21
Nucleus sampling threshold.
0 <= x <= 1A list of tools the model may call. Currently only functions are supported.
Controls which tool is called. none, auto, required, or a specific function.
none, auto, required Deprecated by DeepSeek. Passed through but has no effect.
-2 <= x <= 2Deprecated by DeepSeek. Passed through but has no effect.
-2 <= x <= 2Custom user ID for content safety and KVCache isolation.
512^[a-zA-Z0-9\-_]+$