Long context helps when you stuff contracts, exports, support history, or large files into the prompt. It also makes bills jump. Compare window size and input price together, and decide whether retrieval would be cheaper than stuffing the whole document every time.
ソース基準: NextModel curated catalog and OpenRouter context metadata when available. · 更新日 2026-07-01
Context
まず候補リストから始め、実際のプロンプトで試し、本番ルーティング前に月額コストを比較します。
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
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...
比較表
本番候補を絞り込むとき、フォールバック方針を作るとき、モデル経済性を比べるときに使います。
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| OpenAI: GPT-5.4openai/gpt-5.4 | OpenAI | $0.362 / 1M tokens | $2.17 / 1M tokens | 1.1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| OpenAI: GPT-5.4 Proopenai/gpt-5.4-pro | OpenAI | $4.34 / 1M tokens | $26.04 / 1M tokens | 1.1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| OpenAI: GPT-5.5openai/gpt-5.5 | OpenAI | $0.723 / 1M tokens | $4.34 / 1M tokens | 1.1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-luna | OpenAI | $0.029 / 1M tokens | $0.174 / 1M tokens | 1.1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| OpenAI: GPT-5.6 Solopenai/gpt-5.6-sol | OpenAI | $0.723 / 1M tokens | $4.34 / 1M tokens | 1.1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| OpenAI: GPT-5.6 Terraopenai/gpt-5.6-terra | OpenAI | $0.289 / 1M tokens | $1.74 / 1M tokens | 1.1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
| Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash | $0.043 / 1M tokens | $0.362 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated | |
| Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | $0.072 / 1M tokens | $0.434 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 1000-3000ms | Catalog | Platform curated |
FAQ
No. Bigger windows help with big inputs. Cost, latency, retrieval design, and answer quality still decide whether it is a good idea.
When most of the document is irrelevant to each question. Pull the useful chunks, send less context, and keep a smaller model if quality holds.
Multiply average input tokens (including stuffed documents) by input price, then add output. Long inputs dominate the bill more often than people expect.
ランキング