How do you start calling GPT-4 Turbo?

Use the model ID gpt-4-turbo-2024-04-09 through the OpenAI-compatible chat completions endpoint. Vision requests support JSON mode and function calling.

What is the max output length for gpt-4-turbo-2024-04-09?

gpt-4-turbo-2024-04-09 supports up to 4096 output tokens per request. Plan your prompts to stay within this limit, and use the max_tokens or max_completion_tokens parameter to control output length.

Does gpt-4-turbo-2024-04-09 have a free tier?

GPT-4 Turbo is billed per use and the record publishes no free-tier allowance. The current published rates are input $10.0000 per 1M tokens and output $30.0000 per 1M tokens. Trial credit or promotional quota is tied to your account rather than to the model, so check the console before planning around a free tier.

What is the rate limit for gpt-4-turbo-2024-04-09?

gpt-4-turbo-2024-04-09 rate limits vary by your MixRoute subscription plan. Check your plan details in the console for requests per minute (RPM) and tokens per minute (TPM) limits. Run a small load test before production to confirm your effective quota.

How much does prompt caching save on gpt-4-turbo-2024-04-09?

gpt-4-turbo-2024-04-09 supports prompt caching, which can significantly reduce costs for repeated prompts with shared prefixes. The cache read price is substantially lower than the standard input price. Check the current pricing page for the exact cache hit discount ratio for gpt-4-turbo-2024-04-09.

Model detail

GPT-4 Turbo 20240409

Provided by OpenAI

Pay-as-you-go

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

Model specs

Model ID: gpt-4-turbo-2024-04-09

Context length: 128K
Max output: 4.096K
I/O modalities
Released: 2024-04

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$10.0000 /1M Tokens

Completion

$30.0000 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Vision-capable GPT-4 with JSON mode and function calling

Use GPT-4 Turbo for tasks requiring vision capabilities, JSON mode, and function calling. It is the next generation of GPT-4 with training data up to December 2023.

What should you check before using it?

Consider GPT-4o for better speed and cost

GPT-4o offers better performance at lower cost. Test your vision and function calling tasks to determine if GPT-4 Turbo is still the right choice. Knowledge cutoff: 2023-12-01.

Why use it through MixRoute?

Swap the base URL, keep the GPT-4 Turbo client

MixRoute serves GPT-4 Turbo on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID gpt-4-turbo-2024-04-09 and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

GPT-4 Turbo supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Structured output

GPT-4 Turbo can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.

Streaming

GPT-4 Turbo supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Vision input

GPT-4 Turbo can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

OpenAI SDK

Call GPT-4 Turbo through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 128K

Output tokens Max per request 4.096K

Requests / month

Cache hit rate –

This model has no cache-read price; caching is not counted

FAQ

GPT-4 Turbo is the next generation of GPT-4 with vision capabilities, JSON mode, and function calling. Its training data goes up to December 2023.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

gpt-4-turbo-2024-04-09

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs