LLMopenaiPlan: Pro and up

OpenAI: GPT-5.6 Luna Pro

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Anyone in the Project can @-mention OpenAI: GPT-5.6 Luna Pro with the team's shared context - pooled credits, one chat, one memory.

All models

Verdict

GPT-5.6 Luna Pro delivers OpenAI's largest context window yet at 1M tokens, making it the go-to for processing entire codebases, legal documents, or multi-hour transcripts in a single pass. The $1/$6 per Mtok pricing sits between o1 and GPT-4o, positioning it as a mid-tier option for context-heavy work. Reach for this when you need to reason across massive documents but don't need o1's deep reasoning or can't afford Claude's premium rates.

Best for

Full codebase analysis and refactoring
Multi-document legal contract review
Long-form research synthesis across papers
Transcript analysis for 2+ hour meetings
Cost-sensitive long-context summarization

Strengths

The 1M token context window handles documents that would require chunking in GPT-4o or Claude Sonnet. Multimodal support lets you mix PDFs, images, and text in the same context. Pricing undercuts Claude Opus significantly on input tokens while staying cheaper than o1 on output, making it viable for high-volume document processing. OpenAI's infrastructure means consistent sub-2s time-to-first-token even with large contexts.

Trade-offs

Without published benchmarks, performance on reasoning-heavy tasks relative to o1 or Claude Sonnet 4.5 remains unproven. The $6/Mtok output cost adds up fast for generation-heavy workflows—summarizing a 500k token document into 10k tokens costs $60 in output alone. Early access means tooling integrations and fine-tuning options lag behind GPT-4o. Vision capabilities likely trail GPT-4o given the focus on context length over modality depth.

Specifications

Provider: openai
Category: llm
Context length: 1,050,000 tokens
Max output: 128,000 tokens
Modalities: file, image, text
License: proprietary
Released: 2026-07-09

Pricing

Input: $1.00/Mtok
Output: $6.00/Mtok
Model ID: openai/gpt-5.6-luna-pro

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

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

$44.00

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 Architecture Review

Review this codebase for architectural issues. Identify circular dependencies, overly coupled modules, and functions exceeding 50 lines. Suggest three concrete refactorings with file paths and line numbers.

Open in a Project →

Multi-Contract Comparison

Compare these five vendor contracts. Flag any clauses where liability caps, termination terms, or IP ownership differ. List missing standard protections present in some but not all agreements.

Open in a Project →

Research Paper Synthesis

Synthesize these twelve papers on transformer attention mechanisms. What consensus exists on computational efficiency? Where do authors disagree on scaling laws? Cite paper titles when referencing claims.

Open in a Project →

Meeting Transcript Action Items

Extract all action items from this 3-hour board meeting transcript. Group by owner, include the timestamp and context for each decision, and flag any unresolved debates that need follow-up.

Open in a Project →

Technical Spec Gap Analysis

Compare this PRD against the engineering implementation docs. List features specified but not implemented, implementation details that exceed the spec, and any ambiguous requirements needing clarification.

Open in a Project →