OpenAI Chat Format - DGrid AI Docs

Create chat completion

curl --request POST \
  --url https://api.dgrid.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
}
'

{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "<string>",
        "content": "<string>",
        "reasoning_content": "<string>",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123,
      "text_tokens": 123,
      "audio_tokens": 123,
      "image_tokens": 123
    },
    "completion_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123
    }
  },
  "system_fingerprint": "<string>"
}

POST

chat

completions

Create chat completion

curl --request POST \
  --url https://api.dgrid.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
}
'

{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "<string>",
        "content": "<string>",
        "reasoning_content": "<string>",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123,
      "text_tokens": 123,
      "audio_tokens": 123,
      "image_tokens": 123
    },
    "completion_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123
    }
  },
  "system_fingerprint": "<string>"
}

This page uses the same chat/completions operation as Create chat completion, with the playground above pre-filled for the generic chat schema. The notes below describe how to use this endpoint to request Gemini-backed image generation from an OpenAI-compatible client.

Include an image-generation model in model (such as gemini-2.0-flash-preview-image-generation), set stream as needed, and supply your prompt through messages. Optionally include contents for additional Gemini-style multimodal context alongside messages.

Provider-specific notes

Field	Type	Required	Description
`model`	string	Yes	Image-generation model identifier, e.g. `gemini-2.0-flash-preview-image-generation`.
`messages[].content`	string	Yes	Prompt text describing the desired image.
`contents`	array	No	Optional Gemini-style content array for additional multimodal context, not part of the standard OpenAI chat schema.

The contents field is a DGrid extension layered on top of the standard chat completions schema — it lets you pass Gemini-native parts (such as inlineData) alongside the OpenAI-style messages array when the target model supports it.

Example: requesting an image

{
  "model": "gemini-2.0-flash-preview-image-generation",
  "stream": false,
  "messages": [
    {
      "role": "user",
      "content": "Generate an image of a futuristic city skyline at sunset."
    }
  ]
}

Response fields

The response follows the standard chat completions shape. The generated image is embedded directly in the assistant message content:

choices

array

Returned choice entries.

Show choice properties

index

integer

Choice index.

message

object

Assistant message object.

Show message properties

role

string

Message role, typically assistant.

content

string

Message content. For image-output models, this is a markdown image reference embedding the generated image as a base64 data URI, e.g. ![generated image](data:image/png;base64,...).

finish_reason

string

Finish reason, e.g. stop.

usage

object

Token usage summary.

Example response

200

{
  "id": "chatcmpl-abc123",
  "model": "gemini-2.0-flash-preview-image-generation",
  "object": "chat.completion",
  "created": 1719859200,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "![generated image](data:image/png;base64,<base64-encoded-image-bytes>)"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 0,
    "total_tokens": 12
  }
}

Authorizations

Authorization

string

header

required

Your DGrid API key. All endpoints use Authorization: Bearer <DGRID_API_KEY>.

Body

application/json

model

string

required

Target model ID in provider/model-name format.

Example:

"openai/gpt-4o"

messages

object[]

required

Conversation message list.

Show child attributes

temperature

number

default:1

Sampling temperature.

top_p

number

default:1

Nucleus sampling value.

integer

default:1

Number of choices to generate.

stream

boolean

default:false

Enable SSE streaming.

max_tokens

integer

Maximum token count.

max_completion_tokens

integer

Max completion-only tokens.

presence_penalty

number

default:0

Presence penalty.

frequency_penalty

number

default:0

Frequency penalty.

logit_bias

object

Token bias configuration.

stop

Stop sequence string or array.

tools

object[]

Tool definitions.

tool_choice

Tool selection behavior. Defaults to auto.

response_format

object

Response schema or JSON mode config.

seed

integer

Deterministic seed.

user

string

End-user identifier.

Response

Chat completion result.

string

Completion identifier.

object

string

Always chat.completion.

created

integer

Creation timestamp.

model

string

Model that served the request.

choices

object[]

Returned choices.

Show child attributes

usage

object

Token usage breakdown.

Show child attributes

system_fingerprint

string

Gemini Native Format

Create image

⌘I

​Provider-specific notes

​Example: requesting an image

​Response fields

​Example response

Authorizations

Body

Response

Provider-specific notes

Example: requesting an image

Response fields

Example response