Retired Jul 2026
o3-deep-research
A specialized o3 variant, released June 2025, fine-tuned for autonomous research that synthesizes hundreds of online sources into comprehensive reports.
Key Specifications
- Context window
- 200K tokens
- Max output
- 100K tokens
- Knowledge cutoff
- web search available
- Released
- Inputs
- Text, image
- Capabilities Show details
- Reasoning Thinks before it answers, always on or as a switchable mode. Web search Search the web for up-to-date information. Code execution Write and execute code in a sandboxed environment. File upload Process uploaded documents, spreadsheets, and other files. MCP Connect to services via Model Context Protocol.
Hosted API pricing
| Provider | Input /1M tokens | Output /1M tokens | Cached input /1M | Cost at 10M in + 2M out | |
|---|---|---|---|---|---|
Azure
|
$10.00 | $40.00 | $2.50 | $180.00 | View |
Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.
Similarly priced models
The models nearest o3-deep-research by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs o3-deep-research |
|---|---|---|---|---|---|---|
Claude Opus 4.7
Anthropic
|
$8.3333 | $5.00 | $25.00 | 1M | Jan 2026 | −44% |
|
Claude Opus 4.8
Anthropic
|
$8.3333 | $5.00 | $25.00 | 1M | Jan 2026 | −44% |
|
Claude Opus 5
Anthropic
|
$8.3333 | $5.00 | $25.00 | 1M | May 2026 | −44% |
|
GPT-5.5
OpenAI
|
$9.1667 | $5.00 | $30.00 | 1M | Dec 2025 | −39% |
|
GPT-4 Turbo
OpenAI
|
$13.3333 | $10.00 | $30.00 | 128K | Dec 2023 | −11% |
|
o3-deep-research
This model
OpenAI
|
$15.00 | $10.00 | $40.00 | 200K | Jun 2024 | |
|
Claude Fable 5
Anthropic
|
$16.6667 | $10.00 | $50.00 | 1M | Jan 2026 | +11% |
|
Claude Fable 5.1
Anthropic
|
$16.6667 | $10.00 | $50.00 | 1M | Jun 2026 | +11% |
|
GPT-6 Astra
OpenAI
|
$16.6667 | $10.00 | $50.00 | 1M | Apr 2026 | +11% |
|
o1
OpenAI
|
$22.50 | $15.00 | $60.00 | 200K | Oct 2023 | +50% |
|
o3-pro
OpenAI
|
$30.00 | $20.00 | $80.00 | 200K | Jun 2024 | +100% |
Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.
Frequently Asked Questions
What is o3-deep-research good for?
Autonomous, multi-step research reports that search and synthesize many online sources, with MCP connectors for private data. It was OpenAI's deep research model.
When is o3-deep-research not a good fit?
Anything new: OpenAI retired it in July 2026. It had no function calling or structured output, took no audio or video input, and its knowledge is dated.
What is the cheapest way to run o3-deep-research?
The cheapest hosted rate is $10.00 / $40.00 per 1M tokens via Azure.
Can I self-host o3-deep-research?
No. OpenAI does not publish the weights; o3-deep-research is available only through hosted APIs.
More from OpenAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
GPT-6 Astra
|
1M | $10.00 | $50.00 |
|
GPT-4 Turbo
|
128K | $10.00 | $30.00 |
|
o1
|
200K | $15.00 | $60.00 |
|
GPT-5.5
|
1M | $5.00 | $30.00 |
|
o3-pro
|
200K | $20.00 | $80.00 |
|
GPT-5 Pro
|
400K | $15.00 | $120.00 |
|
GPT-4
|
8K | $30.00 | $60.00 |
|
GPT-5.2 Pro
|
400K | $21.00 | $168.00 |