NeuralBridgeDocumentation

GPT 4o

unofficialchat
DeveloperOpenai
Identifieropenai/gpt-4o-11594

GPT 4o specifications

Context window128K
Max output tokens16384
Release date2024-05-13
InputText
OutputText

GPT 4o pricing in rubles

You pay for what you use, per token and per unit. The final request cost is returned in the API response.

TypePrice
Input tokens500per 1M tokens
Output tokens2000per 1M tokens

Prices are in rubles and may change with exchange rates.

What GPT 4o can do

GPT 4o API: connection and code examples

The service exposes a single OpenAI-compatible API. Set our base_url and the key from your dashboard.

OpenAI Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.neuralbridge.ru/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4o-11594",
    messages=[{"role": "user", "content": "Привет! Расскажи о себе."}],
)

print(response.choices[0].message.content)

Python (requests)

import requests

response = requests.post(
    "https://api.neuralbridge.ru/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "openai/gpt-4o-11594",
        "messages": [{"role": "user", "content": "Привет! Расскажи о себе."}],
    },
)

print(response.json()["choices"][0]["message"]["content"])

cURL

curl https://api.neuralbridge.ru/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-11594",
    "messages": [{"role": "user", "content": "Привет! Расскажи о себе."}]
  }'

API endpoints

POST /v1/chat/completionsprimaryChat Completions
The main chat endpoint: takes a message history and returns the model reply. Supports streaming and regular modes.
POST /v1/responsesResponses
Alternative chat format with state and structured output.
POST /v1/messagesMessages
Anthropic format: the same chat for clients and SDKs written for Claude.
POST /v1/converseConverse
Amazon Bedrock Converse format, for clients written against it.
POST /v1/converse-streamConverse Stream
Streaming variant of the Bedrock Converse format.
POST /v1/generateContentGenerate Content
Google Gemini format, for clients and SDKs written against it.
POST /v1/streamGenerateContentStream Generate Content
Streaming variant of the Gemini format.

Supported request parameters

ParameterDefaultAllowed valuesDescription
temperature1Controls how varied the answer is: higher values make the output more random, lower values more predictable.
top_p1Nucleus sampling: only the most probable tokens whose probabilities add up to P are considered.
max_tokensUpper limit on the number of tokens the model may generate in its answer.
presence_penalty0Penalizes tokens that already appeared in the text, nudging the model toward new topics.
frequency_penalty0Penalizes tokens in proportion to how often they already appeared — fights repetition.
stopList of stop strings: generation halts as soon as the model produces any of them.
seedPins randomness: repeating a request with the same seed and parameters returns the same result.
response_formatResponse format: plain text or strict JSON following a given schema.
streamfalseDeliver the answer as a stream while it is generated instead of one chunk at the end.
tools
parallel_tool_calls
Language:РусскийEnglishУкраїнськаБеларускаяҚазақшаOʻzbekchaКыргызчаТоҷикӣՀայերենAzərbaycancaTürkmençeRomânăDeutschFrançaisEspañolItalianoPortuguêsPolskiNederlandsTürkçeΕλληνικά