AiCostCompare

GPT-3.5 Turbo 16k

by OpenAI · openai/gpt-3.5-turbo-16k · #243 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:37 AM UTC · refreshed hourly

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...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash

Pricing

Input

$3.00

per 1M tokens

Output

$4.00

per 1M tokens

Blended (3:1)

$3.25

3 input : 1 output

Cache read

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for GPT-3.5 Turbo 16k (no cache-read rate published — hits billed as normal input).

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$3.25$0.31
50%$3.25$0.31−0%
90%$3.25$0.31−0%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.0027$2.70
Document summary8,0001,000$0.028$28.00
Codebase question (RAG)30,0002,000$0.098$98.00
Long-context analysis150,0005,000$0.47$470.00

Specs

Context window

16K

tokens

Max output

4K

tokens

Input modalities

text

Tokenizer

GPT