Current practical defaults
Claude Opus 4.8: 1,000,000 tokens. Claude Opus 4.8 supports a 1M-token context window and up to 128K output tokens via the standard Messages API. Claude Sonnet 4.6: 1,000,000 tokens. Claude Sonnet 4.6 supports a 1M-token context window and up to 64K output tokens. Claude Haiku 4.5: 200,000 tokens. Claude Haiku 4.5 supports a 200K-token context window and up to 64K output tokens. GPT-4.1: 1,047,576 tokens. GPT-4.1 supports a ~1M-token context window and up to 32K output tokens. OpenAI's current flagship text model. GPT-4.1 mini: 1,047,576 tokens. GPT-4.1 mini matches the full model's 1M context at lower cost. Good for high-volume context workflows. GPT-4o: 128,000 tokens. GPT-4o supports a 128K context window and up to 16K output tokens. ChatGPT product limits can differ by plan. Gemini 2.5 Pro: 1,048,576 tokens. Gemini 2.5 Pro supports a 1M-token context window and up to 65K output tokens. Gemini 2.5 Flash: 1,048,576 tokens. Gemini 2.5 Flash supports a 1M-token context window and up to 65K output tokens. Optimised for price-performance. Mistral Large 3: 256,000 tokens. Mistral Large 3 is Mistral's flagship model with a 256K-token context window. Mistral Small 4: 256,000 tokens. Mistral Small 4 is a multimodal hybrid model with a 256K-token context window. Lower cost than Large. Sonar: 128,000 tokens. Perplexity Sonar documents a 128K context length for web-grounded search queries. Sonar Pro: 200,000 tokens. Perplexity Sonar Pro documents a larger context window for deeper research queries. Local LLM: 32,768 tokens. Local-model limits depend on the model and runtime. The calculator default is editable.
Treat these as planning numbers, not a permanent spec. Vendors update models, plans, and product surfaces, so any serious workflow should keep the limits in one updateable place.
How to budget a bundle
Start by estimating the source tokens. Reserve space for your instructions, follow-up question, and expected answer. Then trim the source bundle until the important material fits comfortably.
A smaller, curated bundle usually beats a maximum-size dump because the model can focus on the documents that actually support the task.
Why Riflet tracks this
Riflet shows token estimates while you select files, so token budgeting happens before export instead of after an AI rejects the upload or loses focus.
For teams, putting context limits in an updateable config also makes monthly model-limit updates simpler.
Build better AI context with Riflet
Collect the files, notes, websites, and docs that matter. Export one portable bundle for any AI.
Download Riflet freeFrequently asked questions
Is context window sizes by ai model only useful for developers?
No. The same context principles apply to research, writing, legal review, client work, product planning, and any workflow where the AI needs project-specific source material.
Does more context always produce better AI output?
No. Relevant, well-structured context usually beats a large dump of loosely related files. Large context windows make preparation more important, not less important.
Where does Riflet fit in this workflow?
Riflet is the assembly step. It helps gather source material, filter it, estimate the token budget, and export one portable file for the AI tool you choose.
Does Riflet replace RAG or AI project features?
Not always. RAG is useful for large retrieval systems. AI project features are useful inside one platform. Riflet is best when you want explicit, portable context you can inspect before using.