LLMopenaiPlan: Pro and up

OpenAI: GPT-5.6 Luna

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

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

All models

Verdict

GPT-5.6 Luna offers OpenAI's largest context window yet at 1.05M tokens, making it the go-to choice for processing entire codebases, legal document sets, or multi-chapter manuscripts in a single pass. The $0.10/$0.60 per Mtok pricing undercuts GPT-4o significantly while maintaining multimodal support across text, images, and files. Reach for Luna when context length is your bottleneck and you need OpenAI's reasoning quality across massive inputs without splitting documents.

Best for

Processing entire codebases in one context
Multi-document legal analysis and synthesis
Long-form manuscript editing and feedback
Cross-referencing large technical documentation sets
Session-long conversations with deep memory

Strengths

The 1.05M token window handles what previously required RAG pipelines or chunking strategies — ingest a 400-page technical manual and ask questions across all sections without retrieval overhead. Multimodal support means you can mix screenshots, diagrams, and text within that massive context. Pricing at $0.10 input makes it economical to load large corpora repeatedly during iterative workflows. OpenAI's instruction-following remains sharp even at scale, maintaining coherence across references 800k tokens apart.

Trade-offs

Without public benchmarks, performance on reasoning-heavy tasks relative to o1 or Claude Sonnet 4.5 remains unproven in head-to-head tests. The $0.60 output cost adds up quickly for generation-heavy use cases — a 10k token summary of your 500k token input costs $6 in output alone. Early-access models often show regression on edge cases that established models handle reliably. If your task fits in 200k tokens, Claude Sonnet 4.5 delivers better-documented performance at comparable cost.

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: $0.20/Mtok
Output: $1.20/Mtok
Model ID: openai/gpt-5.6-luna

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

$8.80

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

I've uploaded our complete application codebase. Review the overall architecture, identify tight coupling between modules, and suggest three high-impact refactorings that would improve maintainability. Reference specific files and line ranges in your analysis.

Open in a Project →

Multi-Contract Legal Analysis

I've provided five vendor contracts. Identify any conflicting terms around liability caps, termination clauses, and data ownership. Create a table showing how each contract handles these three areas, then flag the two highest-risk discrepancies.

Open in a Project →

Technical Documentation Synthesis

I've uploaded our API documentation, internal wiki pages, and architecture decision records. Create a unified guide for new engineers covering authentication flow, database schema decisions, and deployment pipeline. Cross-reference the source documents for each claim.

Open in a Project →

Manuscript Developmental Edit

I've uploaded my complete 90,000-word novel manuscript. Analyze pacing across all chapters, flag any character motivation inconsistencies, and suggest where the middle act drags. Provide specific chapter and scene references for each note.

Open in a Project →

Session-Long Research Assistant

I'm researching the economic impact of remote work policies 2020-2024. As I share articles and data, help me build a structured argument with supporting evidence. Track all sources and flag when new information contradicts earlier claims we've discussed.

Open in a Project →

Compare with

Compare OpenAI: GPT-5.6 Luna with…

More language models

See all language models →