GPT-3.5 Turbo overview
The model is no longer available on AI/ML API. Its replacement is GPT-5.6 Terra.
GPT-3.5 Turbo specs
- Model ID
openai/gpt-3.5-turbo- Developer
- OpenAI
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Fast and cost-efficient OpenAI model for a wide range of text generation and conversation tasks.
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.
Use cases
GPT-3.5 Turbo is documented as suited to cheaper chat and non-chat tasks. It is also described as useful for chat and traditional completion tasks, including applications that need natural language or code generation.
It is optimized for chat using the Chat Completions API, so it fits conversational assistants and other chat-based applications.
The model is also documented for use in functions that convert natural language into structured outputs, such as API calls or database queries.
It can be used for fine-tuning to improve instruction-following and consistent output formatting, including cases like terse responses, a fixed response language, code completion, or JSON generation.
Capabilities
- Function calling
- Streaming
- Structured outputs
GPT-3.5 Turbo benchmarks by 
Artificial Analysis
See how GPT-3.5 Turbo scores on independent evaluations. Data retrieved Nov 4, 2026.
Benchmark results
Compare 9 models available on AI/ML API across 3 independent benchmarks.
GPQA Diamond
Graduate-level science questions written to resist web search.
MMLU-Pro
Multiple-choice knowledge and reasoning across 14 subjects.
MATH-500
Competition mathematics problems.
Models similar to GPT-3.5 Turbo
Related guide
GPT-3.5 Turbo FAQ
What is the context window of GPT-3.5 Turbo?
GPT-3.5 Turbo has a 16,000 tokens context window.
What inputs and outputs does GPT-3.5 Turbo support?
GPT-3.5 Turbo takes text as input and returns text.
What is the model ID for GPT-3.5 Turbo?
Use openai/gpt-3.5-turbo as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
When was GPT-3.5 Turbo released?
GPT-3.5 Turbo became available on August 7, 2025.
How much does GPT-3.5 Turbo cost?
GPT-3.5 Turbo is priced at input $0.65 / 1M tokens, output $1.95 / 1M tokens.
Does GPT-3.5 Turbo support streaming?
Yes, GPT-3.5 Turbo can stream responses as they are generated.
Who created GPT-3.5 Turbo?
GPT-3.5 Turbo was built by OpenAI.
Is GPT-3.5 Turbo a reasoning-focused model?
No. Its listed capabilities are function calling, streaming, and structured outputs, not dedicated reasoning.
Is GPT-3.5 Turbo currently accessible via API?
No. GPT-3.5 Turbo was withdrawn from AI/ML API on 2026-10-23 and is no longer available through the API.
Does GPT-3.5 Turbo support calling external tools or functions?
Yes. It supports function calling, tools, and parallel tool calls.