No longer supported

This model is legacy (released November 2023) and is no longer actively maintained or recommended by OpenAI. Consider using their current flagship model instead.

legacyfastllm Proprietary

GPT-3.5-turbo-1106

by OpenAI· Released November 2023· Cutoff September 2021

GPT-3.5-turbo-1106 is a legacy version of OpenAI's GPT-3.5 Turbo model, released in November 2023. It introduced improved instruction following, JSON mode, and parallel function calling compared to earlier GPT-3.5 Turbo versions. This model is now deprecated in favor of newer GPT-3.5 Turbo updates.

Official Site API Docs

Input cost

$1.00 per 1M tokens

Output cost

$2.00 per 1M tokens

Context window

16,385 tokens

Max output

4,096 tokens

Modalities

text

License

proprietary

Capabilities

Function CallingJSON ModeParallel Function CallingStreamingCode GenerationChat Completions

Best For

Cost-effective chat and text generation tasks requiring function calling or structured outputs.

Strengths

Low cost per token
Fast inference speed
Supports parallel function calling
Good instruction following

Limitations

Legacy model, no longer updated
Lower accuracy than GPT-4 models
Limited context window compared to newer models
No vision or multimodal support

Use Cases

Customer support chatbots

Content generation

Code assistance

Data extraction and formatting

Language translation

Summarization

Virtual assistants

Improvements Over Previous Model

Introduced JSON mode for structured outputs
Added parallel function calling support
Improved instruction following over previous GPT-3.5 Turbo versions
Lower latency compared to earlier models

Back to all models