Chat completion

Creates a model response using DeepSeek models. Supports chat, reasoning, and specialized models for various tasks.

How To Use

Simply specify the model name in your request payload. All other parameters remain the same across different models.

Actual API Endpoint: POST /v1/chat/completions

Supported Models

Chat: deepseek-chat

Reasoning: deepseek-reasoner, deepseek-r1, deepseek-r1-250528

Distill: deepseek-r1-distill-llama-70b, deepseek-r1-distill-llama-8b

V3 series: deepseek-v3, deepseek-v3-fast, deepseek-v3.1, deepseek-v3.1-fast, deepseek-v3.1-terminus, deepseek-v3.2, deepseek-v3.2-exp, deepseek-v3.2-fast

Other: deepseek-ocr

Request

Authorization

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/jsonRequired

Examples

DeepSeek ChatDeepSeek R1 ReasoningDeepSeek V3DeepSeek Reasoner

{
    "model": "deepseek-chat",
    "max_tokens": 1024,
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Hello!"
        }
    ]
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200OK

application/json

Successful response

Bodyapplication/json

Example

{
    "id": "string",
    "object": "chat.completion",
    "created": 0,
    "model": "string",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "system",
                "content": "string",
                "name": "string",
                "tool_calls": [
                    {
                        "id": "string",
                        "type": "function",
                        "function": {
                            "name": "string",
                            "arguments": "string"
                        }
                    }
                ],
                "tool_call_id": "string"
            },
            "finish_reason": "stop",
            "logprobs": {},
            "content_filter_results": {
                "hate": {
                    "filtered": true,
                    "severity": "string"
                },
                "self_harm": {
                    "filtered": true,
                    "severity": "string"
                },
                "sexual": {
                    "filtered": true,
                    "severity": "string"
                },
                "violence": {
                    "filtered": true,
                    "severity": "string"
                },
                "jailbreak": {
                    "filtered": true,
                    "detected": true
                },
                "protected_material_code": {
                    "filtered": true,
                    "detected": true
                },
                "protected_material_text": {
                    "filtered": true,
                    "detected": true
                }
            }
        }
    ],
    "usage": {
        "prompt_tokens": 0,
        "completion_tokens": 0,
        "total_tokens": 0,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "audio_tokens": 0
        },
        "completion_tokens_details": {
            "reasoning_tokens": 0,
            "audio_tokens": 0,
            "accepted_prediction_tokens": 0,
            "rejected_prediction_tokens": 0
        }
    },
    "system_fingerprint": "string",
    "prompt_filter_results": [
        {
            "prompt_index": 0,
            "content_filter_results": {
                "hate": {
                    "filtered": true,
                    "severity": "string"
                },
                "self_harm": {
                    "filtered": true,
                    "severity": "string"
                },
                "sexual": {
                    "filtered": true,
                    "severity": "string"
                },
                "violence": {
                    "filtered": true,
                    "severity": "string"
                },
                "jailbreak": {
                    "filtered": true,
                    "detected": true
                },
                "protected_material_code": {
                    "filtered": true,
                    "detected": true
                },
                "protected_material_text": {
                    "filtered": true,
                    "detected": true
                }
            }
        }
    ]
}

🟠400Bad Request

🟠401Unauthorized

🟠429Too Many Requests

🔴500Internal Server Error

How To Use#

Supported Models#

Request

Request Code Samples

Responses

How To Use

Supported Models