AiCostCompare

o3 Deep Research

by OpenAI · openai/o3-deep-research · #311 cheapest of 325 paid models

Prices updated Jul 22, 2026, 2:48 AM UTC · refreshed hourly

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

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

Pricing

Input

$10.00

per 1M tokens

Output

$40.00

per 1M tokens

Blended (3:1)

$17.50

3 input : 1 output

Cache read

$2.50

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for o3 Deep Research with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$17.50$1.06
50%$14.69$0.685−35%
90%$12.44$0.385−64%

*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$0.017$17.00
Document summary8,0001,000$0.12$120.00
Codebase question (RAG)30,0002,000$0.38$380.00
Long-context analysis150,0005,000$1.70$1,700

Specs

Context window

200K

tokens

Max output

100K

tokens

Input modalities

image, text, file

Tokenizer

GPT