Change log, by what changed

Context window changes

A context ceiling moved. Chunking, truncation and retrieval budgets that were sized against the old ceiling are now sized against nothing in particular, so revisit them before you widen anything.

How much a model will accept or return has changed.

4 entries . window ends 2026-09-24

By provider

OpenAI: 2
Anthropic: 2

Recommended action

Other views

Context window changes over twelve months

Tracked provider changes, Oct 2025 to Sep 2026

New version
Weight refresh
Deprecation
Pricing, context and tool changes share these three colours and always carry a label.

The same timeline as a list, 4 changes

2026-08-05 OpenAI, Context change: gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna
2026-04-30 Anthropic, Context change: claude-sonnet-4-5-20250929, claude-sonnet-4-20250514
2026-03-13 Anthropic, Context change: claude-opus-4-6, claude-sonnet-4-6
2026-03-05 OpenAI, Context change: gpt-5.4, gpt-5.4-pro

Every entry

Context window changes, newest first

OpenAIContext change5 August 2026

gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna

OpenAI states that Fast mode now supports long context requests exceeding 272K tokens for the GPT-5.6 models.

RAG: Dropping the chunking you added for the old ceiling changes what sits in the context window. Ragas defines faithfulness as the share of claims in a response that can be inferred from the retrieved context, so the score moves with the context as well as with the model.
Summarisation: Summarising a whole document rather than a set of chunks changes the expected output for every case. Galtea warns against updating ground truth to match model behaviour.

Rerun the suiteIf you split long inputs to stay under the old ceiling, run a long document case end to end before removing that chunking.

Source: OpenAI, OpenAI API changelog . verified 2026-09-22

AnthropicContext change30 April 2026

claude-sonnet-4-5-20250929, claude-sonnet-4-20250514

Anthropic retired the 1M token context window beta, context-1m-2025-08-07, for Claude Sonnet 4.5 and Claude Sonnet 4. The beta header now has no effect on these models, and requests exceeding the standard 200k token context window return an error. Anthropic says to migrate to Claude Sonnet 4.6 or Claude Opus 4.6, where the 1M context window is included at standard pricing with no beta header required.

RAG: A smaller usable window changes how much retrieved text reaches the model. Ragas defines faithfulness as the share of claims in a response that can be inferred from the retrieved context, so the scorer reads what was actually passed in, not what was retrieved.

Plan a migrationFind any request that still sends the context-1m-2025-08-07 header to these two ids, then either shorten the input or move the feature to a model where the 1M window is standard.

Source: Anthropic, Claude API release notes . verified 2026-09-22

AnthropicContext change13 March 2026

claude-opus-4-6, claude-sonnet-4-6

Anthropic took the 1M token context window out of beta for Claude Opus 4.6 and Claude Sonnet 4.6, at standard pricing and with no beta header required. The notes state that the dedicated 1M rate limits were removed and that the media limit was raised to 600 images or PDF pages per request.

RAG: A longer window changes how much retrieved text you put in front of the model. Ragas defines faithfulness as the share of claims in a response that can be inferred from the retrieved context, so the score follows the context you assemble.
Summarisation: Feeding a whole document instead of chunks changes the input to every case, which makes the old run and the new run two different things unless the inputs are tracked. Braintrust tracks every change to a dataset so experiments can pin to specific versions.

Rerun the suiteRemove the 1M beta header from your clients and rerun any long context case, since the separate rate limit pool that used to back those requests is gone.

Source: Anthropic, Claude API release notes . verified 2026-09-22

OpenAIContext change5 March 2026

gpt-5.4, gpt-5.4-pro

OpenAI released GPT-5.4 as a frontier model with a 1M token context window, tool search, computer use and compaction, alongside gpt-5.4-pro.

Agent: Tool search and computer use add steps that the final answer never shows. Arize Phoenix reconstructs tool_path, the ordered tool calls with their arguments, and tool_io, what each tool was called with and what it returned, and warns that a correct looking answer can come from a broken path.
RAG: Compaction changes what the model still has in front of it when it answers. Ragas defines faithfulness as the share of claims in a response that can be inferred from the retrieved context, so a compacted context is a different thing to be faithful to.

Rerun the suiteRun one long input case against gpt-5.4 before you rely on the larger window, and check how compaction changes what the model still has in front of it.

Source: OpenAI, OpenAI API changelog . verified 2026-09-22

The full change log

Sources

Change-log entries restate provider announcements with sources and dates. Impact notes cite public practitioner reports. The site publishes no measurements of its own on any model.

Questions about context window changes

How is a change classified as a context window change?

From what the provider wrote, not from a guess about severity. Where a provider states that weights are unchanged, the entry is not classified as a weight change, and where an unchanged model string starts returning something else, it is.

Is this list complete?

It covers the model families we track for customers, inside a twelve-month window, where the announcement is reachable on the provider's own domain. Anything we cannot reach there is not published, however widely it was reported. Send us a provider link and we will add it.

Do you say what this did to real features?

No. The impact notes say what this kind of change typically touches, each citing a published practitioner source. What it did to your feature is a question only a rerun against your own dataset answers.