LLMopenaiPlan: Pro and up

OpenAI: GPT-5 Mini (batch)

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

Anyone in the Project can @-mention OpenAI: GPT-5 Mini (batch) with the team's shared context - pooled credits, one chat, one memory.

All models

Verdict

GPT-5 Mini delivers OpenAI's latest reasoning architecture at batch pricing that undercuts real-time alternatives by 50%. The 400K context window handles book-length documents and multi-file codebases without chunking. Vision support covers screenshots and diagrams. Trade-off: batch-only means 24-hour turnaround, ruling out interactive workflows. Reach for this when you're processing large volumes overnight—document analysis pipelines, code review queues, or research synthesis—and cost matters more than latency.

Best for

  • Overnight document processing pipelines
  • Cost-sensitive code review automation
  • Multi-file codebase analysis
  • Batch research paper summarization
  • Screenshot and diagram interpretation at scale

Strengths

The 400K context window eliminates chunking headaches for long documents and lets you feed entire codebases in one pass. Batch pricing at $0.13 input / $1.00 output cuts costs in half versus real-time GPT-5 Mini, making high-volume workflows economically viable. Vision support handles technical diagrams and UI screenshots without separate preprocessing. OpenAI's GPT-5 reasoning architecture brings improved logical consistency to multi-step analysis tasks.

Trade-offs

Batch-only processing means 24-hour turnaround, which kills any interactive or user-facing use case. No public benchmarks yet make it hard to gauge performance against Claude Sonnet 4.5 or Gemini 2.0 Flash on specific tasks. The $1.00 output price climbs fast on verbose responses—a 10K-token summary costs $1, so careless prompting erodes the input savings. Vision capabilities lag behind GPT-4o's detail recognition in our spot checks.

Specifications

Provider
openai
Category
llm
Context length
400,000 tokens
Max output
128,000 tokens
Modalities
text, image, file
License
proprietary
Released
2025-08-07

Pricing

Input
$0.13/Mtok
Output
$1.00/Mtok
Model ID
openai/gpt-5-mini:batch

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Estimated monthly spend
$6.82
17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider-level routing data is not available yet for this model.

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Codebase Security Audit

Review this codebase for security vulnerabilities, focusing on authentication flows, data validation, and SQL injection risks. List findings by severity with file locations and remediation steps.
Open in a Project →

Multi-Document Research Synthesis

Synthesize these research papers into a 2-page summary covering methodology overlaps, conflicting findings, and consensus conclusions. Include a table comparing key metrics across studies.
Open in a Project →

Batch Screenshot Analysis

Analyze these product screenshots and extract: main navigation structure, primary CTAs, form field requirements, and accessibility issues. Return as JSON with screenshot filenames as keys.
Open in a Project →

Technical Documentation Generation

Generate API documentation for this codebase including: endpoint descriptions, parameter schemas, response examples, error codes, and rate limit guidance. Use OpenAPI 3.0 format.
Open in a Project →

Compare with

More language models

See all language models

Data last verified 7 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.