TokenRate

GPT-3.5 Turbo 16k Pricing

Balanced

OpenAI · 16K tokens context

GPT-3.5 Turbo 16k from OpenAI costs $3.00 per 1 million input tokens and $4.00 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 16,385-token context window (approximately 12,289 words) with a 4K-token maximum output. A typical 1,000-token request costs $0.0030 in input charges; a 10,000-token request costs $0.0300.

GPT-3.5 Turbo 16k pricing and capability summary
Input price$3.00 / 1M tokens
Output price$4.00 / 1M tokens
Output / input ratio1.3×
Context window16,385 tokens (~12,289 words)
Maximum output4,096 tokens
Cost per 1K tokens (input)$0.0030
TierBalanced
Last verified

This model offers four times the context length of gpt-3. 5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.

Live pricing from OpenRouter

Input Price

$3.00

per 1 million tokens

Output Price

$4.00

per 1 million tokens

Context Window

16K tokens

max 4K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.004$0.0016
10-page document (2,500 words)3,333$0.01$0.004
1,000 lines of code5,000$0.015$0.006
100K token document100,000$0.30$0.12

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Strong general-purpose performance
  • Strong general-purpose performance
  • Strong general-purpose performance

Limitations

  • Smaller 16K-token context limits long-document use
  • Quality and availability can vary by hosting provider

Best Use Cases

Customer-facing AI apps
Code generation and review
Content creation at scale
Conversational interfaces

Calculate GPT-3.5 Turbo 16k Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact GPT-3.5 Turbo 16k costs — and compare across all models.

Open Calculator →

GPT-3.5 Turbo 16k — FAQ

Related Models

Related Guides