DeepSeek V3

curl --request POST \
  --url https://http.llm.model-cluster.on-prem.clusters.yotta-uat.cluster.s9t.link/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'id: <id>' \
  --data '
{
  "model": "deepseek-v3",
  "messages": [
    {
      "role": "user",
      "content": "How do I delete a team member from an org given user and org tables?"
    }
  ],
  "stream": true,
  "max_tokens": 1024,
  "temperature": 0.7,
  "top_p": 1
}
'

{
  "id": "chatcmpl-deepseek-abc123",
  "object": "chat.completion",
  "created": 1699014493,
  "model": "deepseek-v3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "To delete a team member from an organization, you'll need to handle the relationship between user and org tables. Here's a typical approach:\n\n```sql\n-- Option 1: Delete from junction table\nDELETE FROM user_org_memberships \nWHERE user_id = ? AND org_id = ?;\n\n-- Option 2: Update user record\nUPDATE users \nSET org_id = NULL \nWHERE user_id = ? AND org_id = ?;\n```\n\nThe exact implementation depends on your database schema design."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 156,
    "total_tokens": 174,
    "reasoning_tokens": 0
  },
  "system_fingerprint": "deepseek-v3-20241201"
}

POST

chat

completions

curl --request POST \
  --url https://http.llm.model-cluster.on-prem.clusters.yotta-uat.cluster.s9t.link/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'id: <id>' \
  --data '
{
  "model": "deepseek-v3",
  "messages": [
    {
      "role": "user",
      "content": "How do I delete a team member from an org given user and org tables?"
    }
  ],
  "stream": true,
  "max_tokens": 1024,
  "temperature": 0.7,
  "top_p": 1
}
'

{
  "id": "chatcmpl-deepseek-abc123",
  "object": "chat.completion",
  "created": 1699014493,
  "model": "deepseek-v3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "To delete a team member from an organization, you'll need to handle the relationship between user and org tables. Here's a typical approach:\n\n```sql\n-- Option 1: Delete from junction table\nDELETE FROM user_org_memberships \nWHERE user_id = ? AND org_id = ?;\n\n-- Option 2: Update user record\nUPDATE users \nSET org_id = NULL \nWHERE user_id = ? AND org_id = ?;\n```\n\nThe exact implementation depends on your database schema design."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 156,
    "total_tokens": 174,
    "reasoning_tokens": 0
  },
  "system_fingerprint": "deepseek-v3-20241201"
}

Authorizations

Authorization

string

header

required

JWT token for authentication - Use your API token as the Bearer token

Headers

string

default:e04b66b0-e8ac-410e-b028-b25716a91a92

required

Model UUID for the request (DeepSeek V3 model identifier)

Body

application/json

messages

object[]

required

Array of messages in the conversation

Show child attributes

messages.role

enum<string>

required

The role of the message sender

Available options:

system,

user,

assistant

messages.content

string

required

The content of the message

model

enum<string>

default:deepseek-v3

required

Model identifier for DeepSeek V3

Available options:

deepseek-v3

stream

boolean

default:false

Whether to stream the response

temperature

number

default:0.7

Sampling temperature (0.0 to 2.0). Lower values for analytical tasks, higher for creative work

Required range: 0 <= x <= 2

max_tokens

integer

default:1024

Maximum number of tokens to generate

Required range: 1 <= x <= 65536

top_p

number

default:1

Nucleus sampling parameter for controlling response diversity

Required range: 0 <= x <= 1

top_k

integer

default:50

Top-k sampling parameter for vocabulary selection

Required range: 1 <= x <= 100

stop

string[] | null

Sequences where the API will stop generating further tokens

Maximum array length: 4

frequency_penalty

number

default:0

Penalty for frequent tokens to reduce repetition

Required range: -2 <= x <= 2

presence_penalty

number

default:0

Penalty for new tokens to encourage topic diversity

Required range: -2 <= x <= 2

repetition_penalty

number

default:1

Penalty for repeating tokens (DeepSeek-specific parameter)

Required range: 0.1 <= x <= 2

do_sample

boolean

default:true

Whether to use sampling for generation

seed

integer | null

Random seed for reproducible outputs

reasoning_mode

boolean

default:false

Enable enhanced reasoning capabilities for complex problems

Response

Successful chat completion

Option 1
Option 2

Response for non-streaming chat completion

string

Unique identifier for the completion

Example:

"chatcmpl-deepseek-abc123"

object

enum<string>

Object type

Available options:

chat.completion

Example:

"chat.completion"

created

integer

Unix timestamp of when the completion was created

Example:

1699014493

model

string

The model used for completion

Example:

"deepseek-v3"

choices

object[]

Show child attributes

choices.index

integer

required

Index of the choice

Example:

0

choices.message

object

required

Show child attributes

choices.message.role

enum<string>

required

Role of the message sender

Available options:

assistant

Example:

"assistant"

choices.message.content

string

required

Generated text content

Example:

"To delete a team member from an organization, you'll need to handle the relationship between user and org tables. Here's a typical approach:\n\n```sql\n-- Option 1: Delete from junction table\nDELETE FROM user_org_memberships \nWHERE user_id = ? AND org_id = ?;\n\n-- Option 2: Update user record\nUPDATE users \nSET org_id = NULL \nWHERE user_id = ? AND org_id = ?;\n```\n\nThe exact implementation depends on your database schema design."

choices.finish_reason

enum<string>

required

Reason for finishing the generation

Available options:

stop,

length,

content_filter,

tool_calls

Example:

"stop"

usage

object

Show child attributes

usage.prompt_tokens

integer

required

Number of tokens in the prompt

Example:

18

usage.completion_tokens

integer

required

Number of tokens in the completion

Example:

156

usage.total_tokens

integer

required

Total number of tokens used

Example:

174

usage.reasoning_tokens

integer | null

Additional tokens used for reasoning (if reasoning_mode enabled)

Example:

0

system_fingerprint

string | null

System fingerprint for the model version

Example:

"deepseek-v3-20241201"

Qwen 2.5 72B DeepSeek R1

⌘I

API Documentation

Inference APIs

Training APIs

Authorizations

Headers

Body

Response