Chat Completions (Gateway)

POST

chat

completions

curl https://api.inquantum.ai/v1/chat/completions \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Say hello in one sentence." }
    ]
  }'

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inquantum.ai/v1",
  apiKey: process.env.PLANCK_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Say hello in one sentence." },
  ],
});

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inquantum.ai/v1",
    api_key=os.environ.get("PLANCK_API_KEY"),
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Say hello in one sentence."},
    ],
)

{
  "id": "chatcmpl_123",
  "object": "chat.completion",
  "created": 1788206400,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 22,
    "completion_tokens": 9,
    "total_tokens": 31,
    "cost_usd": 0.000015
  }
}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":"Hello!"},"finish_reason":null}]}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: {"id":"req_123","object":"chat.completion.chunk","created":1788206401,"model":"gpt-4o-mini","choices":[],"usage":{"prompt_tokens":22,"completion_tokens":2,"total_tokens":24,"cost_usd":0.000009}}

data: [DONE]

This request schema applies when using the Planck AI Gateway with pass‑through billing (credits). In BYOK mode, the standard OpenAI Chat Completions schema is allowed. The schema is defined based on fields that are stable across all provider-model mappings. Learn more about pass‑through billing vs BYOK.

curl https://api.inquantum.ai/v1/chat/completions \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Say hello in one sentence." }
    ]
  }'

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inquantum.ai/v1",
  apiKey: process.env.PLANCK_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Say hello in one sentence." },
  ],
});

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inquantum.ai/v1",
    api_key=os.environ.get("PLANCK_API_KEY"),
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Say hello in one sentence."},
    ],
)

{
  "id": "chatcmpl_123",
  "object": "chat.completion",
  "created": 1788206400,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 22,
    "completion_tokens": 9,
    "total_tokens": 31,
    "cost_usd": 0.000015
  }
}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":"Hello!"},"finish_reason":null}]}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: {"id":"req_123","object":"chat.completion.chunk","created":1788206401,"model":"gpt-4o-mini","choices":[],"usage":{"prompt_tokens":22,"completion_tokens":2,"total_tokens":24,"cost_usd":0.000009}}

data: [DONE]

For runnable SDK examples, raw SSE parsing, cancellation, and mid-stream error handling, see Streaming chat completions. max_tokens and max_completion_tokens are optional on this route. If both are omitted, Planck leaves the output limit unspecified and the selected provider applies its own default. For models that support reasoning, use reasoning_effort and include_reasoning. See Reasoning and thinking for model-specific values and complete OpenAI, cURL, and Anthropic examples.

This endpoint uses the shared AI Gateway error envelope. See the Error Handling & Fallback guide for response examples, retry rules, fallback behavior, and streaming errors.

Body

application/json

messages

object[]

required

Minimum array length: 1

Show child attributes

model

string

required

metadata

Show child attributes

top_logprobs

integer | null

Required range: 0 <= x <= 20

temperature

top_p

user

string

safety_identifier

string

prompt_cache_key

string

cache_control

object

Show child attributes

service_tier

Available options:

auto,

default,

flex,

scale,

priority

modalities

Available options:

text

verbosity

Available options:

low,

medium,

high

reasoning_effort

Available options:

minimal,

low,

medium,

high

max_completion_tokens

integer | null

Required range: -9007199254740991 <= x <= 9007199254740991

frequency_penalty

number | null

default:0

Required range: -2 <= x <= 2

presence_penalty

number | null

default:0

Required range: -2 <= x <= 2

response_format

object

Option 1
Option 2
Option 3

Show child attributes

store

boolean | null

default:false

stream

boolean | null

default:false

stop

logit_bias

object | null

Show child attributes

logprobs

boolean | null

default:false

max_tokens

integer | null

Required range: -9007199254740991 <= x <= 9007199254740991

integer | null

default:1

Required range: 1 <= x <= 128

prediction

object | null

Show child attributes

seed

integer | null

Required range: -9007199254740991 <= x <= 9007199254740991

stream_options

Show child attributes

tools

object[]

Option 1
Option 2

Show child attributes

tool_choice

Available options:

none,

auto,

required

parallel_tool_calls

boolean

default:true

function_call

Available options:

none,

auto

functions

object[]

Required array length: 1 - 128 elements

Show child attributes

Response

200

Request accepted

curl https://api.inquantum.ai/v1/chat/completions \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Say hello in one sentence." }
    ]
  }'

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inquantum.ai/v1",
  apiKey: process.env.PLANCK_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Say hello in one sentence." },
  ],
});

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inquantum.ai/v1",
    api_key=os.environ.get("PLANCK_API_KEY"),
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Say hello in one sentence."},
    ],
)

{
  "id": "chatcmpl_123",
  "object": "chat.completion",
  "created": 1788206400,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 22,
    "completion_tokens": 9,
    "total_tokens": 31,
    "cost_usd": 0.000015
  }
}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":"Hello!"},"finish_reason":null}]}

data: {"id":"chatcmpl_123","object":"chat.completion.chunk","created":1788206400,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: {"id":"req_123","object":"chat.completion.chunk","created":1788206401,"model":"gpt-4o-mini","choices":[],"usage":{"prompt_tokens":22,"completion_tokens":2,"total_tokens":24,"cost_usd":0.000009}}

data: [DONE]

Gateway API

Observability API

Prompt API

Chat Completions (Gateway)

Body

Response