Chat completions with Gemini

Create a Gemini chat completion

curl --request POST \
  --url https://gengen.farm/api/gengen/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-3.5-flash-lite",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise technical assistant."
    },
    {
      "role": "user",
      "content": "Explain idempotency in two sentences."
    }
  ]
}
'

import requests

url = "https://gengen.farm/api/gengen/v1/chat/completions"

payload = {
    "model": "gemini-3.5-flash-lite",
    "messages": [
        {
            "role": "system",
            "content": "You are a concise technical assistant."
        },
        {
            "role": "user",
            "content": "Explain idempotency in two sentences."
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gemini-3.5-flash-lite',
    messages: [
      {role: 'system', content: 'You are a concise technical assistant.'},
      {role: 'user', content: 'Explain idempotency in two sentences.'}
    ]
  })
};

fetch('https://gengen.farm/api/gengen/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {}
  ],
  "usage": {}
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

POST

chat

completions

Create a Gemini chat completion

curl --request POST \
  --url https://gengen.farm/api/gengen/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-3.5-flash-lite",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise technical assistant."
    },
    {
      "role": "user",
      "content": "Explain idempotency in two sentences."
    }
  ]
}
'

import requests

url = "https://gengen.farm/api/gengen/v1/chat/completions"

payload = {
    "model": "gemini-3.5-flash-lite",
    "messages": [
        {
            "role": "system",
            "content": "You are a concise technical assistant."
        },
        {
            "role": "user",
            "content": "Explain idempotency in two sentences."
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gemini-3.5-flash-lite',
    messages: [
      {role: 'system', content: 'You are a concise technical assistant.'},
      {role: 'user', content: 'Explain idempotency in two sentences.'}
    ]
  })
};

fetch('https://gengen.farm/api/gengen/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {}
  ],
  "usage": {}
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

Use the OpenAI-compatible Chat Completions endpoint with gemini-3.8-flash, gemini-3.7-flash, or gemini-3.5-flash-lite.

Property	Value
Method	`POST`
Endpoint	`/api/gengen/v1/chat/completions`
Models	`gemini-3.8-flash`, `gemini-3.7-flash`, `gemini-3.5-flash-lite`
Streaming	Server-Sent Events (SSE)

Non-streaming request

curl --request POST \
  --url https://gengen.farm/api/gengen/v1/chat/completions \
  --header 'Authorization: Bearer gengen_live_xxxxxxxxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-3.5-flash-lite",
    "messages": [
      {
        "role": "system",
        "content": "You are a concise technical assistant."
      },
      {
        "role": "user",
        "content": "Explain idempotency in two sentences."
      }
    ],
    "reasoning_effort": "minimal",
    "max_tokens": 512,
    "stream": false
  }'

The response uses the OpenAI-compatible choices and usage fields.

{
  "id": "google-response-id",
  "object": "chat.completion",
  "model": "gemini-3.5-flash-lite",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Idempotency means repeating the same operation produces the same intended effect. It prevents retries from creating duplicate changes."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 32,
    "completion_tokens": 28,
    "total_tokens": 60
  }
}

Streaming request

Set stream to true. GENGEN returns text/event-stream, emits partial Chat Completions chunks, includes final usage, and terminates the stream with data: [DONE].

curl --no-buffer --request POST \
  --url https://gengen.farm/api/gengen/v1/chat/completions \
  --header 'Authorization: Bearer gengen_live_xxxxxxxxxxxxxxxx' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-3.8-flash",
    "messages": [
      {
        "role": "user",
        "content": "Write a one-line product description."
      }
    ],
    "stream": true,
    "stream_options": {
      "include_usage": true
    }
  }'

data: {"id":"google-response-id","object":"chat.completion.chunk","model":"gemini-3.8-flash","choices":[{"index":0,"delta":{"content":"A fast"},"finish_reason":null}]}

data: {"id":"google-response-id","object":"chat.completion.chunk","model":"gemini-3.8-flash","choices":[],"usage":{"prompt_tokens":16,"completion_tokens":8,"total_tokens":24}}

data: [DONE]

This is unidirectional text streaming over SSE. It is separate from the bidirectional Gemini Live API.

Reasoning level

Gemini 3.8 Flash and Gemini 3.7 Flash accept low, medium, or high and default to medium. Gemini 3.5 Flash-Lite also accepts minimal, defaults to minimal, and recommends it for extraction and other straightforward, latency-sensitive tasks.

Gemini 3.5 Flash-Lite constraints

Gemini 3.5 Flash-Lite ignores custom temperature, top_p, and top_k values. It rejects frequency_penalty and presence_penalty, and the final non-system message must not use the assistant role.

Parameters

Parameter	Type	Description
`messages`	array	Required conversation history. `system` and `developer` messages become the Gemini system instruction; text, image, video, and audio parts are supported.
`reasoning_effort`	string	`low`, `medium`, or `high` for Gemini 3.8 Flash and Gemini 3.7 Flash; Gemini 3.5 Flash-Lite also supports `minimal`.
`temperature`	number	Sampling temperature. Gemini 3.5 Flash-Lite ignores custom values.
`top_p`	number	Nucleus-sampling threshold from `0` to `1`. Gemini 3.5 Flash-Lite ignores custom values.
`top_k`	number	Restricts sampling to the most likely K tokens. Gemini 3.5 Flash-Lite ignores custom values.
`max_tokens` / `max_completion_tokens`	integer	Maximum generated tokens.
`stop`	string or string[]	One or more stop sequences.
`frequency_penalty`	number	Penalizes repeated token frequency. Not supported by Gemini 3.5 Flash-Lite.
`presence_penalty`	number	Penalizes tokens already present in the output. Not supported by Gemini 3.5 Flash-Lite.
`seed`	integer	Best-effort deterministic sampling seed.
`response_format`	object	Use `json_object` or `json_schema` for structured output.
`stream`	boolean	Enables SSE streaming.
`providerOptions.google`	object	Advanced Google `generationConfig`, `safetySettings`, `tools`, and `toolConfig`. Normalized parameters above take precedence.

The API fixes candidateCount to 1 so the OpenAI-compatible response always contains one generated choice. Google may not produce identical output for repeated requests with the same seed. See the Gemini 3.8 Flash, Gemini 3.7 Flash and Gemini 3.5 Flash-Lite model pages for details. Gemini 3.8 Flash defaults to medium reasoning and rejects minimal, unsupported reasoning levels, and thinkingBudget overrides. Use low, medium, or high.

Function calling and built-in tools

Function calling, Code execution, and Computer use are supported for all three Gemini models. See Function calling and Gemini tools for complete requests, multi-turn result submission, thought signature preservation, streaming behavior, and billing.

Authorizations

Authorization

string

header

required

A workspace API key beginning with gengen_live_.

Body

application/json

model

enum<string>

required

Public Gemini text model ID.

Available options:

gemini-3.8-flash,

gemini-3.7-flash,

gemini-3.5-flash-lite

messages

object[]

required

Conversation messages. System and developer messages become the Gemini system instruction.

Minimum array length: 1

Show child attributes

reasoning_effort

enum<string>

Gemini thinking level. minimal is supported by Gemini 3.5 Flash-Lite but not Gemini 3.8 Flash or Gemini 3.7 Flash. Gemini 3.8 Flash defaults to medium and rejects thinking budgets.

Available options:

minimal,

low,

medium,

high

temperature

number

Sampling temperature. Higher values increase variation. Custom values are ignored by Gemini 3.5 Flash-Lite.

top_p

number

Nucleus-sampling probability threshold. Custom values are ignored by Gemini 3.5 Flash-Lite.

Required range: 0 <= x <= 1

top_k

number

Limits sampling to the most likely K tokens. Custom values are ignored by Gemini 3.5 Flash-Lite.

Required range: x >= 1

max_tokens

integer

Maximum output token count. max_completion_tokens is an accepted alias.

Required range: x >= 1

max_completion_tokens

integer

Maximum output token count.

Required range: x >= 1

stop

One or more sequences that stop generation.

frequency_penalty

number

Penalizes tokens according to how often they already appear. Gemini 3.5 Flash-Lite rejects this parameter.

presence_penalty

number

Penalizes tokens that have already appeared at least once. Gemini 3.5 Flash-Lite rejects this parameter.

seed

integer

Best-effort sampling seed. Identical outputs are not guaranteed.

response_format

object

Show child attributes

stream

boolean

default:false

Return Server-Sent Events when true.

stream_options

object

Streaming compatibility options.

Show child attributes

tools

object[]

Function declarations. Chat uses nested function objects; Responses uses flat function declarations. Built-in tools belong in providerOptions.google.tools.

tool_choice

auto, none, required, or a named function object. The function name must be declared in tools.

Available options:

auto,

none,

required

parallel_tool_calls

boolean

Omit or use true. Gemini can return multiple calls; false is rejected.

providerOptions

object

Show child attributes

Response

An OpenAI-compatible chat completion or SSE stream.

string

object

string

Allowed value: "chat.completion"

created

integer

model

string

choices

object[]

usage

object

Reference

BytePlus

OpenAI

Kling

Higgsfield

MiniMax

Happy Horse

Google

WonderClip

Flash VSR

Wan

Qwen

Chat completions with Gemini

Non-streaming request

Streaming request

Reasoning level

Gemini 3.5 Flash-Lite constraints

Parameters

Function calling and built-in tools

Authorizations

Body

Response

​Non-streaming request

​Streaming request

​Reasoning level

​Gemini 3.5 Flash-Lite constraints

​Parameters

​Function calling and built-in tools

Authorizations

Body

Response

Non-streaming request

Streaming request

Reasoning level

Gemini 3.5 Flash-Lite constraints

Parameters

Function calling and built-in tools