Calculate the cost of using o4-mini-deep-research from OpenAI for your AI applications
Pricing data last updated:
Mode: Responses
Max: 200,000 tokens
Max: 100,000 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
o4-mini-deep-research is a responses model from OpenAI, one of 22 responses models they offer. It is priced at $2.00 per 1M input tokens and $8.00 per 1M output tokens, ranking 72 out of 143 responses models by cost and cheaper than 43% of models in this category. o4-mini-deep-research supports vision, reasoning, prompt caching — one of only 3 responses models with this combination. It accepts up to 200K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 200,000 input tokens. The maximum output length is 100,000 tokens.
At $2.00 per 1M input tokens and $8.00 per 1M output tokens, o4-mini-deep-research ranks 72 out of 143 responses models by input cost. It is competitively priced compared to the median of $2.00 for responses models, and is cheaper than 43% of models in this category.
o4-mini-deep-research is one of 22 OpenAI responses models, one of only 3 responses models combining prompt caching, reasoning, vision.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs o4-mini-deep-research |
|---|---|---|---|---|
| gpt-5.2-codex | Azure | $1.75 | $14.00 | -12% |
| gpt-5.3-codex | Azure | $1.75 | $14.00 | -12% |
| openai.gpt-5.6-terra | Bedrock Mantle | $2.20 | $13.20 | +10% |
Similar responses models from other providers
No. o4-mini-deep-research costs $2.00 per 1M input tokens while gpt-5.2-codex costs $1.75 per 1M input tokens, making gpt-5.2-codex 12% more affordable for input. However, o4-mini-deep-research may offer different capabilities or performance characteristics that justify the price difference.
o4-mini-deep-research input pricing is $2.00 per 1M tokens, which is 0% at the median of $2.00 for responses models. It ranks 72 out of 143 responses models by input cost, making it cheaper than 43% of models in this category. For output, it costs $8.00 per 1M tokens compared to the median of $12.00.
Among OpenAI's 22 responses models, o4-mini-deep-research ranks 7 by input cost. Its combination of prompt caching, reasoning, vision is shared by only 2 other responses models.
The most comparable responses models to o4-mini-deep-research are: gpt-5.2-codex from Azure ($1.75/1M input tokens); gpt-5.3-codex from Azure ($1.75/1M input tokens); openai.gpt-5.6-terra from Bedrock Mantle ($2.20/1M input tokens); openai.gpt-6-sol from Bedrock Mantle ($2.20/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
You can monitor OpenAI service health in real time on the Bifrost OpenAI Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
o4-mini-deep-research is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $2.00 and generating 1M output tokens costs $8.00.