impulse

o3 Deep Research

Frontier lab
API id o3-deep-researchReleased 26 Jun 2025 (Jun 2025)
Azure OpenAI retires it on 19 Nov 2026 (today). 1 host keeps serving it.
Input / 1M
$10.00
at OpenAI
Output / 1M
$40.00
at OpenAI
Context window
200K
tokens
Max output
100K
tokens per reply
Hosts
2
5 listings
Released
Jun 2025
26 Jun 2025

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$10.00$40.00
Cached input
75% off input
$2.50

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$5,325
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$4,440
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$8,100
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$33,600
Use your own numbers

Where to run it

2 hosts serve o3 Deep Research. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
o3-deep-research
$10.00 / $40.00
o3-deep-research
$10.00 / $40.00
Retires 19 Nov 2026
Show 3 more listings: regions, snapshots and variants
OpenAI
2025-06-26
o3-deep-research-2025-06-26
$10.00 / $40.00
Azure OpenAI
eu
o3-deep-research
$11.00 / $44.00
+10% vs headline
Retires 19 Nov 2026
us
o3-deep-research
$11.00 / $44.00
+10% vs headline
Retires 19 Nov 2026

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
ImagesTextPDFs
Produces
Text
Features
PDF inputPrompt caching

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

  • GPT-6.2 Astra
    OpenAI · on OpenAI
    $8.00 / $40.00
    Has every key capability
    9% less
  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    73% less
  • GPT-6.2 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    77% less

Other frontier labs

  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
    9% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    77% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    83% less
  • Claude Opus 5.5
    Anthropic · on Anthropic
    $4.00 / $20.00
    Has every key capability
    54% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    77% less
  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    88% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    89% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    90% less

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="o3-deep-research", input="Hello")
print(response.output_text)

Quick answers

How much does o3 Deep Research cost?

On OpenAI, o3 Deep Research costs $10.00 per million input tokens and $40.00 per million output tokens. Cached input costs $2.50 per million tokens.

Which APIs offer o3 Deep Research?

o3 Deep Research runs on 2 APIs: OpenAI and Azure OpenAI.

What is o3 Deep Research's context window?

200K tokens, with up to 100K tokens in one reply.

Is o3 Deep Research being retired?

Azure OpenAI retires it on 19 Nov 2026. 1 host keeps serving it.

What are cheaper alternatives to o3 Deep Research?

Models that cost less and keep most of what it can do: GPT-6.2 Astra on OpenAI (9% less), Claude Fable 5.2 on Anthropic (9% less), Gemini 4 Carbon on Google AI Studio (77% less) and Kimi K3.1 Pro on Databricks (77% less). Savings are on a mix of 3 input tokens to 1 output token.

When was o3 Deep Research released?

OpenAI released it on 26 Jun 2025.

What is o3 Deep Research's API model id?

Use o3-deep-research with OpenAI.

Sources

Raw catalog entry for o3-deep-research on OpenAI
{
  "cache_read_input_token_cost": 0.0000025,
  "input_cost_per_token": 0.00001,
  "litellm_provider": "openai",
  "max_input_tokens": 200000,
  "max_output_tokens": 100000,
  "mode": "responses",
  "output_cost_per_token": 0.00004,
  "fedramp_uplift_multiplier": 1.1,
  "source": "https://developers.openai.com/api/docs/models/o3-deep-research",
  "supported_endpoints": [
    "/v1/batch",
    "/v1/responses"
  ],
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_function_calling": false,
  "supports_native_streaming": true,
  "supports_parallel_function_calling": false,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": false,
  "supports_tool_choice": false,
  "supports_vision": true,
  "supports_pdf_input": true,
  "deprecation_date": "2026-07-23",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-sol"
}