OpenAI: o3-deep-research

Research model for long-horizon investigation, synthesis, and analytical reports

Source-linked o Closed weights Released 2024-06-26

API record Report

InputT

OutputT

Input price$9/M

Output price$36/M

Context200K

Max output100K

Providers6

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering o3-deep-research
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Poe	`openai/o3-deep-research`	200K	100K	$9	$36	$2.2	ReasoningTools	Docs ↗
OpenAI	`o3-deep-research`	200K	100K	$10	$40	$2.5	ReasoningTools	Docs ↗
Kilo Gateway	`openai/o3-deep-research`	200K	100K	$10	$40	$2.5	ReasoningTools	Docs ↗
OpenRouter	`openai/o3-deep-research`	200K	100K	$10	$40	$2.5	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`openai/o3-deep-research`	200K	100K	$10	$40	$2.5	ReasoningTools	Docs ↗
NanoGPT	`openai/o3-deep-research`	200K	100K	$11	$44	$5.5	Reasoning	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $9/M

Across 6 priced providers

Median input $10/M

Midpoint of listed rates

Highest input $11/M

1.2× the lowest listed rate

Output range $36 – $44

Per million output tokens

Poe $9/MLowest

OpenAI $10/M

Kilo Gateway $10/M

OpenRouter $10/M

Vercel AI Gateway $10/M

NanoGPT $11/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

? Structured output Unknown

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: OpenAI
Model family: o
Knowledge cutoff: 2024-05
License: Not documented
Release date: 2024-06-26
Model ID: openai/o3-deep-research

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Jul 30, 2026Price Completion40.0 → 36.0

Jul 30, 2026Price Prompt10.0 → 9.0

Jul 30, 2026Price Completion36.0 → 40.0

Jul 30, 2026Price Prompt9.0 → 10.0

Jul 30, 2026Price Completion40.0 → 36.0

Jul 30, 2026Price Prompt10.0 → 9.0

Jul 30, 2026Price Completion36.0 → 40.0

Jul 30, 2026Price Prompt9.0 → 10.0

Jul 30, 2026Price Completion40.0 → 36.0

Jul 30, 2026Price Prompt10.0 → 9.0

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Models.devcatalog ↗Poe documentationprovider documentation ↗OpenAI documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Vercel AI Gateway documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/openai/o3-deep-research

curl

curl "https://model.kyssta.lol/api/v1/models/openai/o3-deep-research"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is o3-deep-research?

Research model for long-horizon investigation, synthesis, and analytical reports. It is published by OpenAI and catalogued here from Models.dev.

How much does o3-deep-research cost?

Listed input pricing starts at $9 per million tokens from Poe, rising to $11 across 6 listed providers.

What is the context length of o3-deep-research?

o3-deep-research accepts up to 200K tokens of context and returns up to 100K output tokens.

Does o3-deep-research support tool calling and structured output?

Provider catalogs list support for tool calling, reasoning, and image input.

Which providers serve o3-deep-research?

6 providers list this model: Poe, OpenAI, Kilo Gateway, OpenRouter, Vercel AI Gateway, NanoGPT.

Are the weights for o3-deep-research open?

No. This model is served through hosted APIs only.

When was o3-deep-research released?

The catalog records a release date of 2024-06-26, last verified Sep 11, 2026.

More models from OpenAI

View all →

GPT-4o (2024-08-06)

GPT model for general reasoning, writing, coding, and tool-assisted tasks

128K ctx $2.5/M in GPT-4.1 mini

Affordable GPT-4.1 lane for fast coding help and structured extraction

1.04758M ctx $0.4/M in GPT-5.3 Codex Spark

Coding-optimized GPT model for repository edits, reviews, and agentic software work

128K ctx $1.75/M in Whisper Large v3 Turbo

Speech transcription model for accurate audio-to-text and captioning workflows

448 ctx $0.002/M in