GPT-3.5 Turbo

OpenAI

DEPRECATED. OpenAI's widely-adopted cost-effective model released March 2023. Optimized for chat via Chat Completions API with natural language and code generation capabilities. Features 16K context window (20 pages of text). Significantly cheaper than GPT-4 family while maintaining solid performance for most common use cases. Priced at $0.50 per 1M input tokens and $1.50 per 1M output (60% cheaper than previous pricing). Enhanced with better steerability, improved function calling, and extended context. Widely deployed in production applications globally. GPT-4o-mini now recommended upgrade for better performance at similar cost. OpenAI has deprecated it: access to the gpt-3.5-turbo snapshots is scheduled to shut down on October 23, 2026.

Strengths

Extremely cost-effective - $0.50 per 1M input tokens
Widely deployed and battle-tested in production
16K context window handles most common use cases
Function calling enables tool use and structured outputs
Fast response times compared to GPT-4 family
Strong performance on general chat and basic coding tasks
Available via Azure and OpenAI directly

Caveats

DEPRECATED - OpenAI shuts down access on October 23, 2026
Migrate before the shutdown date; OpenAI names gpt-3.5-turbo-compat as the substitute snapshot
Outperformed by GPT-4o-mini at similar cost ($0.15 vs $0.50 input)
Significantly weaker than GPT-4o/GPT-5 series on complex reasoning
16K context smaller than modern models (GPT-4o: 128K)
No vision or multimodal capabilities
Knowledge cutoff September 2021 older than GPT-4 family
Consider migrating to GPT-4o-mini for better quality at lower cost

Vendor: OpenAI
Context Window: 16,385 tokens
Max Output: 4,096 tokens
License: Proprietary
Release Date: 2023-03-21
Modalities: text

Benchmark	Score	Max
livebench_instruction_following	74.5	100.0
livebench_coding	27.7	100.0
livebench_language	28.6	100.0

Capabilities

Vision

Audio

Video

Tool Use

Resources

API Documentation

Pricing

$0.50 per 1M input tokens, $1.50 per 1M output tokens