--- title: GPT-5.6's Context Window: 922K In, 128K Out Tokens description: GPT-5.6 shipped a ~1.05M-token context window (922K input, 128K output) on the o200k_base encoding. What changes for existing integrations. date: 2026-08-12T00:00:00.000Z category: ai-productivity tags: tokens, gpt, context-windows, openai --- ## Quick Answer GPT-5.6 reached general availability with a context window reported at roughly 1.05M tokens: up to 922K input tokens and 128K output tokens. It uses the `o200k_base` encoding, not the older `cl100k_base` encoding GPT-3.5 and GPT-4 used. Re-check any chunking logic sized for a smaller window, and any token counter tied to the old encoding. ## What's actually changing GPT-5.6 (the Sol, Terra, and Luna variants) reached general availability on 2026-07-09 with a context window aggregated across multiple 2026 model-tracking sources at roughly 1.05M tokens, split into up to 922K input tokens and 128K output tokens, figures that match [OpenAI's own model documentation](https://platform.openai.com/docs/models). That figure is paraphrased from third-party tracking, not confirmed against OpenAI's own primary announcement post directly, and is stated honestly as such here. What is more mechanically certain: GPT-5.6 shares the `o200k_base` encoding that GPT-4o introduced, not the `cl100k_base` encoding that GPT-3.5 and the GPT-4 family used. A prompt that tokenizes to a given count under `cl100k_base` does not tokenize to the same count under `o200k_base`. Any system that estimates cost or truncates input based on a `cl100k_base` count will be wrong for GPT-5.6 calls specifically. ## Structural Comparison Matrix | Operational Aspect | Before (GPT-4 family) | After (GPT-5.6) | | :----------------------------------- | :-------------------- | :-------------------------------------- | | **Context window** | 128K-200K tokens | ~1.05M tokens (922K input, 128K output) | | **Tokenizer encoding** | `cl100k_base` | `o200k_base` | | **Chunking/summarization threshold** | Sized for ~128K | Needs re-sizing for a near-1M window | ## Fix it: re-check chunking logic and token counting A near-1M context window changes the entire "when do I need to chunk or summarize" calculus for any integration built against the smaller GPT-4-family windows. Code that split documents into 100K-token chunks to stay under an older limit may no longer need to split at all, which is a real architecture simplification, not just a bigger number to note. The encoding change matters just as much for cost estimation. If your integration counts tokens client-side before sending a request, whether to enforce a budget or warn a user, that logic needs an `o200k_base`-aware tokenizer for GPT-5.6 calls specifically. This site's own [AI Token Counter](/tools/ai-token-counter/) currently implements `cl100k_base` only, accurate for GPT-3.5 and GPT-4-family models but not for GPT-5.6, and that limitation is disclosed directly on the tool's own comparison table rather than left for a reader to discover after the fact. Once you have a real count, the [LLM Pricing Calculator](/tools/llm-pricing-calculator/) turns it into an actual cost across GPT-5.6's four pricing tiers. A bigger context window does not mean cheaper calls. See [Same Prompt, Different Bill](/ai-productivity/same-prompt-different-bill-gpt-claude-gemini/) for how GPT-5.6's pricing and caching changes interact with this larger window. ## Confirmed version The `o200k_base` encoding and the shared GPT-4o lineage are well-documented technical facts. The specific 922K input / 128K output split is paraphrased, aggregated from 2026 model-tracking sources (including Wikipedia's GPT-5.6 entry and wavespeed.ai's release-date tracking), general-availability date 2026-07-09, not confirmed against OpenAI's own announcement post directly. Browse more coverage in the [AI Productivity](/ai-productivity) archive, or start from [The 2026 LLM Token & Pricing Reset](/ai-productivity/2026-llm-token-pricing-reset/) hub.