GPT-3.5 Turbo 1106 API

Input / 1M tokens$0.88~~$1.00~~

Output / 1M tokens$1.76~~$2.00~~

LLMOpenAI12% below official128K context

Loading playground…

About GPT-3.5 Turbo 1106

GPT-3.5 Turbo 1106 by OpenAI is available on API Many from $0.88 per million input tokens and $1.76 per million output tokens, and you call it with the same API key you use for every other model.

It accepts OpenAI-style chat requests with streaming and tools, has a 128K context window and can return up to 16,000 tokens per response.

You pay only for successful results: failed or rejected requests are refunded automatically, and every call is recorded in your console with its exact cost.

Related models

−12%

GPT-3.5 Turbogpt-3.5-turbo

LLMOpenAI128K context

$0.44 in · $1.32 outTry it

−12%

GPT-3.5 Turbo 0125gpt-3.5-turbo-0125

LLMOpenAI128K context

$0.44 in · $1.32 outTry it

−12%

GPT-3.5 Turbo 0613gpt-3.5-turbo-0613

LLMOpenAI

$1.32 in · $2.64 outTry it

−12%

GPT-3.5 Turbo 16kgpt-3.5-turbo-16k

LLMOpenAI

$2.64 in · $7.92 outTry it

−12%

GPT-3.5 Turbo 16k 0613gpt-3.5-turbo-16k-0613

LLMOpenAI

$2.64 in · $7.92 outTry it

−12%

GPT-3.5 Turbo Instructgpt-3.5-turbo-instruct

LLMOpenAI

$1.32 in · $1.76 outTry it

New−12%

GPT-6.1 Solgpt-6.1-sol

LLMOpenAI922K contextPrompt caching

$1.76 in · $8.80 outTry it

−12%

GPT-6 Solgpt-6-sol

LLMOpenAI922K contextPrompt caching

$1.76 in · $8.80 outTry it

Frequently asked questions

How much does the GPT-3.5 Turbo 1106 API cost?

GPT-3.5 Turbo 1106 starts at $0.88 per million input tokens and $1.76 per million output tokens on API Many. The price table on this page lists every tier; you are charged only for successful requests.

How do I call GPT-3.5 Turbo 1106?

Create an API key in the console, then send a request to /v1/chat/completions with "model": "gpt-3.5-turbo-1106". The API tab has copy-ready examples in cURL, Python and Node.js.

Is this the official GPT-3.5 Turbo 1106 model?

Yes. Requests are forwarded to the model maker or an authorized channel with the same parameters, so the output matches the official API.

What happens if a request fails?

Failed, rejected or timed-out requests are not charged. Reserved balance is released automatically and the reason is shown in the call record.