No longer supported

This model is deprecated (released November 2023) and is no longer actively maintained or recommended by OpenAI.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

deprecatedfrontierllm Proprietary

GPT-4-1106-preview

by OpenAI· Released November 2023· Cutoff April 2023

GPT-4-1106-preview is an early version of GPT-4 Turbo, featuring a 128K context window and updated knowledge cutoff of April 2023. It introduced JSON mode, reproducible outputs, and parallel function calling, offering improved instruction following and lower pricing compared to GPT-4. This model has been superseded by newer GPT-4 Turbo versions.

Official Site API Docs

Input cost

$0.01 per 1K tokens

Output cost

$0.03 per 1K tokens

Context window

128K tokens

Max output

4096 tokens

Modalities

text

License

proprietary

Capabilities

Function CallingJSON ModeReproducible OutputsParallel Function CallingStreamingCode GenerationInstruction Following

Best For

Complex tasks requiring large context windows, structured data extraction, and advanced function calling.

Strengths

Largest context window (128K tokens) at time of release
Improved instruction following over GPT-4
Lower pricing than GPT-4 base model

Limitations

Deprecated and no longer recommended for new applications
May not match performance of newer GPT-4 Turbo versions
Limited to text-only input (no vision)

Use Cases

Long document analysis and summarization

Complex code generation and debugging

Data extraction and structured output generation

Chatbots with extensive conversation history

Automated report generation

Multi-step reasoning tasks

API orchestration with parallel function calls

Improvements Over Previous Model

Introduced 128K context window (vs 8K/32K for GPT-4)
Lower pricing: $0.01/$0.03 per 1K tokens (vs $0.03/$0.06 for GPT-4)
Added JSON mode for structured outputs
Added reproducible outputs via seed parameter
Added parallel function calling
Updated knowledge cutoff to April 2023 (vs September 2021)

Back to all models