openai / Chat

GPT-5 Mini Deep

openai/gpt-5-mini-high

GPT-5 Mini with high thinking — deeper reasoning

Catalog status

Enabled

Research checked

2026-10-06

Price / performance

What it costs to get this result

Benchmark

Humanity's Last Exam · Source-reported results, not a composite ranking. Prices use the average of TokenBazaar input and output rates per million tokens; actual spend depends on usage. Test configurations differ.

GPT-5 Mini Deep21% · 10 sourced models

Blended price / 1M tokens · log scale

● Current model● Other modelsDashed line: price/score frontier among plotted models

Compare sourced models on this benchmark

Benchmark results

11 reported results

Results are source-attributed, not TokenBazaar measurements. Different tests and thinking variants are not interchangeable.

11 of 11 results

AA Intelligence Index

Intelligence · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. Intelligence Index | 17 | 13* |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

17index

AA-Briefcase v1.1

Agentic · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. AA-Briefcase v1.1 | 424 | |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

424score

GDPval-AA v2.1

Agentic · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. GDPval-AA v2.1 | 770 | |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

770score

AutomationBench-AA

Agentic · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. AutomationBench-AA | 6% | |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

Terminal-Bench 4.0

Coding · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. Terminal-Bench 4.0 | 0% | |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

SciCode

Science · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. SciCode | 39% | |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

39%

Humanity's Last Exam

Reasoning · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. Humanity's Last Exam | 21% | 9% |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

21%

GDP.pdf

Knowledge-Work · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. GDP.pdf | 8% | |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

CritPt

Science · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. CritPt | 0% | 0% |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

AA-Omniscience

Knowledge · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. AA-Omniscience | −17 | −29 |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

-17score

AA-LCR v1.1

Long-Context-Reasoning · Third-party report

Test conditions and source

Published configuration: reasoning_effort: high. Source-reported result, not the catalog default unless the effort matches. AA-LCR v1.1 | 72% | 45% |

Tested model: openai/gpt-5-mini-high

Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison · Checked 2026-10-06

72%

Model specifications

Context window

400K

Published provider limit

Maximum output

128K

Published provider limit

Knowledge cutoff

May 31, 2024

Upstream model

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text

Image

Output

Text

Exact model ID: openai/gpt-5-mini-high
Model type: Chat
Context window: 400,000 tokens
Maximum output: 128,000 tokens
Knowledge cutoff: May 31, 2024

A context window is the total conversation budget, not a separate maximum input allowance; generated output and reasoning can use that budget. Published provider limits are not independently tested TokenBazaar request limits.

Versions and thinking levels

Choose from 4 enabled versions. The exact ID determines the version and its price; benchmark scores do not carry over between variants.

GPT-5 Mini₹12.00 in / ₹96.00 out per 1M tokens

GPT-5 Mini DeepSelected₹12.00 in / ₹96.00 out per 1M tokens

GPT-5 Mini Fast₹12.00 in / ₹96.00 out per 1M tokens

GPT-5 Mini Max₹12.00 in / ₹96.00 out per 1M tokens

Features and tool support

TokenBazaar’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Reasoning configuration

The catalog version determines the requested reasoning effort.

Selected effort: high. Reasoning level is not a measured intelligence or speed score.

Coding and agent workflows

Text/code generation and customer-managed tool loops.

Coding benchmark results do not establish a hosted terminal, sandbox, autonomous browser or guaranteed task success.

Streaming answers

Available

Incremental text through TokenBazaar’s chat endpoint; Claude also has native Messages access.

Customer-defined function tools

Limited

Only customer-defined function tools are forwarded. Model/protocol compatibility applies; your application authorizes and executes every tool.

Forced or named tool selection

Limited

The chat route accepts auto, none and required. A named-tool choice is not forwarded; exact model compatibility is not independently tested.

Images and PDFs

Limited

The chat bridge accepts image/PDF content. Provider input modalities are listed separately; file size, content and model limits still apply.

Hosted web search / browsing

Not exposed

No provider-hosted web search or web-fetch tool is exposed. Customer-owned search can be implemented as an authorized function tool.

Hosted code execution / computer use

Not exposed

No built-in execution environment or computer-control tool is provided. Code generation is not code execution.

Hosted file search / persistent assistants

Not exposed

No hosted file-search index, Assistants endpoint or persistent provider agent is exposed.

Batch / fine-tuning / cached-price discounts

Not exposed

No public batch or fine-tuning endpoint, or separate cached-token discount, is offered here.

TokenBazaar pricing

50% OFF

Market price

₹24.00 in / ₹192.00 out per 1M tokens

Input / 1M tokens

₹12.00

Output / 1M tokens

₹96.00

Test in Playground Get API key

Usage-based billing. Caching, batch discounts and provider subscription-tier limits are not included.

API access

https://tokenbazaar.in/api/public

POST /v1/chat/completions

TokenBazaar input: Text, Image/PDF content through the chat bridge
TokenBazaar output: Text

Requests require a TokenBazaar API key and sufficient wallet balance.

Integration documentation

Streaming and customer-defined function tools are routed through the chat API; compatibility varies by model. Image/PDF input is accepted by the bridge, but model vision support needs provider confirmation. Hosted search and computer-use tools are not enabled; public Responses, Assistants, Batch and fine-tuning endpoints are not exposed.

Explore similar models

GPT-6 Luna GPT-5 GPT-5 Nano

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenBazaar. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Provider model specifications
Vendor-reported
Last checked 2026-10-06
Artificial Analysis - GPT-5 mini vs GPT-5 nano comparison
Third-party report
Last checked 2026-10-06

Research notes (1)

Published provider limits; maximum-capacity requests have not been independently exercised through TokenBaazar. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.