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 rate | Effective blended $/1M | Example 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
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.017 | $17.00 |
| Document summary | 8,000 | 1,000 | $0.12 | $120.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.38 | $380.00 |
| Long-context analysis | 150,000 | 5,000 | $1.70 | $1,700 |
Specs
Context window
200K
tokens
Max output
100K
tokens
Input modalities
image, text, file
Tokenizer
GPT