Skip to main content
POST
/
chat
/
completions
curl --request POST \
  --url https://api.siliconflow.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "Pro/zai-org/GLM-4.7",
    "messages": [
      {"role": "system", "content": "你是一个有用的助手"},
      {"role": "user", "content": "你好，请介绍一下你自己"}
    ]
  }'
{
  "id": "019bdaa55225ef854b320e9b838f77ce",
  "object": "chat.completion",
  "created": 1768899826,
  "model": "Pro/zai-org/GLM-4.7",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！...",
        "reasoning_content": "..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 1540,
    "total_tokens": 1555,
    "completion_tokens_details": {
      "reasoning_tokens": 1190
    },
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "prompt_cache_hit_tokens": 0,
    "prompt_cache_miss_tokens": 15
  },
  "system_fingerprint": ""
}

Documentation Index

Fetch the complete documentation index at: https://docs.siliconflow.cn/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Use the following format for authentication: Bearer

Body

application/json
​
model
string
required

Corresponding Model Name. We periodically update our models to enhance service quality. Changes may include model on/offlining or capability adjustments. We will strive to notify you via announcements or push messages. For a complete list of available models, please check the Models.

Example:

"Pro/zai-org/GLM-4.7"

​
messages
object[]
required

A list of messages comprising the conversation so far.

Required array length: 1 - 10 elements
​
stream
boolean

If set, tokens are returned as Server-Sent Events as they are made available. Stream terminates with data: [DONE]

Example:

false

​
max_tokens
integer

The maximum number of tokens to generate. Ensure that input tokens + max_tokens do not exceed the model’s context window. As some services are still being updated, avoid setting max_tokens to the window’s upper bound; reserve ~10k tokens as buffer for input and system overhead. See Models(https://cloud.siliconflow.cn/models) for details.

Example:

4096

​
enable_thinking
boolean

Switches between thinking and non-thinking modes. This field supports the following models:

- Pro/zai-org/GLM-5
- Pro/zai-org/GLM-4.7
- deepseek-ai/DeepSeek-V3.2
- Pro/deepseek-ai/DeepSeek-V3.2
- zai-org/GLM-4.6
- Qwen/Qwen3-8B
- Qwen/Qwen3-14B
- Qwen/Qwen3-32B
- Qwen/Qwen3-30B-A3B
- tencent/Hunyuan-A13B-Instruct
- zai-org/GLM-4.5V
- deepseek-ai/DeepSeek-V3.1-Terminus
- Pro/deepseek-ai/DeepSeek-V3.1-Terminus        
- Qwen/Qwen3.5-397B-A17B
- Qwen/Qwen3.5-122B-A10B
- Qwen/Qwen3.5-35B-A3B
- Qwen/Qwen3.5-27B
- Qwen/Qwen3.5-9B
- Qwen/Qwen3.5-4B
Example:

false

​
thinking_budget
integer

Maximum number of tokens for chain-of-thought output. This field applies to most Reasoning models.

Required range: 128 <= x <= 32768
Example:

4096

​
reasoning_effort
enum<string>

This field only applies to deepseek-ai/DeepSeek-V4-Flash. In thinking mode, the default effort for regular requests is high; for certain complex agent-type requests (such as Claude Code, OpenCode), the effort is automatically set to max. In thinking mode, for compatibility reasons, low and medium are mapped to high, and xhigh is mapped to max.

Available options:
high,
max
Example:

"high"

​
min_p
number<float>

Dynamic filtering threshold that adapts based on token probabilities.This field only applies to Qwen3.

Required range: 0 <= x <= 1
Example:

0.05

​
stop

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

Example:

null

​
temperature
number<float>

Determines the degree of randomness in the response.

Example:

0.7

​
top_p
number<float>
default:0.7

The top_p (nucleus) parameter is used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities.

Example:

0.7

​
top_k
number<float>
Example:

50

​
frequency_penalty
number<float>
Example:

0.5

​
n
integer

Number of generations to return

Example:

1

​
response_format
object

An object specifying the format that the model must output.

​
tools
object[]

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

Response

The response from the model. The response header contains the x-siliconcloud-trace-id field, which serves as a unique identifier for tracing requests, facilitating log queries and issue troubleshooting.

​
id
string
​
choices
object[]
​
usage
object
​
created
integer
​
model
string
​
object
enum<string>
Available options:
chat.completion