GPT 3.5 Turbo 0613
Neural Network
GPT 3.5 Turbo 0613 is a fast OpenAI model for chat and coding, available via API in BotHub.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works GPT 3.5 Turbo 0613?
GPT 3.5 Turbo 0613 is a fast OpenAI model that understands and generates natural language and code, optimized for dialogue and classic text completion tasks. The 0613 index indicates a fixed version snapshot: the model's behavior does not change over time, which is convenient when predictability is required. Training data is limited to September 2021, which is worth noting. In BotHub, the model is available without a VPN or foreign card: you pay with a Russian card in rubles only for consumed tokens, which do not expire. A unified OpenAI-compatible API allows you to switch to any of over 250 other models without rewriting the integration; correspondence is encrypted via AES-GCM and not saved, and for companies, there is a contract, invoice, EDI, and admin panel with limits. Use GPT 3.5 Turbo for chatbots and support where response speed is important, for code analysis and completion, for drafting emails and product descriptions, for streaming processing of similar texts — classification, brief summaries, paraphrasing — and as an economical step in multimodal scenarios.Frequently asked questions about GPT 3.5 Turbo 0613
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
gpt-3.5-turbo-0613 is an OpenAI text model for dialogues, summarization, text rewriting, email drafts, simple code, and data extraction. It accepts not only text but also documents with images as input. The 4095-token context is suitable for short queries and mass repetitive tasks via API.
Up to 3685 tokens per response. Keep in mind that the total window is 4095 tokens, which includes both your prompt and the response: the longer the prompt, the less space remains. It is more convenient to generate large materials in parts, passing only the necessary fragment.
A separate reasoning mode before answering is not noted in our data — the model responds immediately. If step-by-step logic is needed, ask it to write out the solution step-by-step directly in the prompt. For complex multi-step tasks, you can switch to a reasoning model in BotHub.
Yes, function calling and structured JSON output are supported. This is convenient for integrations when the response needs to be passed directly into code, a table, or a database. Connection is via the unified OpenAI-compatible BotHub API, so you can change the model without rewriting the integration.
According to our data, in addition to text, images and documents are accepted as input, so you can attach a file or picture. Audio and video are not noted in the data. The model responds with text: for generating images, video, or sound, switch to a specialized model in the same window.
The language of prompts and responses is not noted in our data, so we will not promise specific quality — test the model with your typical query, it takes a minute. The BotHub interface is in Russian, payment is in rubles, and access from the Russian Federation is possible without a VPN or foreign card.