token.app › OpenAI › GPT-3.5 Turbo 16k

GPT-3.5 Turbo 16k pricing & benchmarks

GPT-3.5 Turbo 16k is available from OpenAI at $3.00 per million input tokens and $4.00 per million output tokens ($3.25 blended at 3:1). It accepts up to 16,385 tokens of context. 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. Training data: up...

Pricing
Per million tokens · OpenRouter
Input$3.00
Output$4.00
Blended (3:1)$3.25
Specification
openai/gpt-3.5-turbo-16k
Context window16K
Max output4K
ReleasedAug 2023
LicenceProprietary
Modalitiesin:text, out:text
No independently-run benchmark scores are published for GPT-3.5 Turbo 16k yet. We show nothing rather than reprinting an unverified figure.
Where to run GPT-3.5 Turbo 16k
2 hosts · all priced within ~5% of each other. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
HostBlended $/1MIn / OutContextUptime 24h
OpenAI $3.25 $3.00 / $4.00 16K 99.8%
Azure $3.25 $3.00 / $4.00 16K 99.7%
Host prices and uptime from OpenRouter, synced 2026-08-08.
Compare GPT-3.5 Turbo 16k
GPT-3.5 Turbo 16k vs Qwen3.8 Max GPT-3.5 Turbo 16k vs DeepSeek V4 Flash 0731 GPT-3.5 Turbo 16k vs Claude Opus 5 GPT-3.5 Turbo 16k vs Gemini 3.6 Flash GPT-3.5 Turbo 16k vs Kimi K3 GPT-3.5 Turbo 16k vs Grok 4.5 GPT-3.5 Turbo 16k vs Claude Sonnet 5 GPT-3.5 Turbo 16k vs GLM 5.2
FAQ
How much does GPT-3.5 Turbo 16k cost?
GPT-3.5 Turbo 16k costs $3.00 per million input tokens and $4.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $3.25 per million tokens.
What is GPT-3.5 Turbo 16k's context window?
GPT-3.5 Turbo 16k accepts up to 16,385 tokens of context, and can generate up to 4,096 output tokens.