GPT-3.5 Turbo (older v0613)
VerifiedEfficient chat model for general text and conversation tasks.
About GPT-3.5 Turbo (older v0613)
This version belongs to the GPT-3.5 series and uses a transformer architecture optimized for dialogue. OpenAI trained it on large text datasets before applying reinforcement learning from human feedback. The weights remain proprietary and access occurs only through hosted endpoints.
It handles instruction following and multi-turn conversations with lower latency than earlier GPT-3 variants. The 4095-token limit suits shorter documents and exchanges while keeping costs modest. Users commonly integrate it into customer support bots, content drafting tools, and simple question-answering systems.
Capabilities
How GPT-3.5 Turbo (older v0613) compares
GPT-3.5 Turbo (older v0613) (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · GPT-3.5 Turbo (older v0613) ranks #108 of 141
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Customer Support Chatbots
This model handles routine conversational queries and instruction following effectively for building responsive support agents that manage common user issues without complex reasoning.
Document Summarization
It performs well at condensing articles, reports, or transcripts into key points using its text summarization capability within the available context window.
Simple Script Generation
The model assists with creating basic code snippets and following step-by-step instructions for automation tasks or quick prototypes in various programming languages.
Strengths & limitations
Strengths
- +Fast and efficient responses
- +Strong general language tasks
- +Versatile instruction handling
- +Cost-effective for chat use
Limitations
- –Small 4k token context window
- –Text-only modality
- –Older version with earlier knowledge cutoff
Cost calculator
Estimate what GPT-3.5 Turbo (older v0613) would cost for your usage.
Based on GPT-3.5 Turbo (older v0613)'s $1.00/1M input · $2.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "openai/gpt-3.5-turbo-0613",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: openai/gpt-3.5-turbo-0613
Editor's verdict
GPT-3.5 Turbo (older v0613) is OpenAI's proprietary language models with a 4K-token context window.
At $2.00 per 1M output tokens, it is mid-priced for its class.
It is available through OpenAI's API and aggregators like OpenRouter.
Best suited to fast and efficient responses and strong general language tasks.
Frequently asked questions
This version supports a context length of 4095 tokens as specified in its technical details.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other GPT models
Sibling versions in the GPT family from OpenAI.
Similar models
Other language models worth comparing.