[FEATURE] Bring 1M context window to Max plan subscribers
Preflight Checklist
- [x] I have searched existing requests and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
Problem Statement
I'm a Max x5 subscriber ($100/month) using Claude Code exetension for VSCode daily for software development. I was genuinely excited when I saw the Opus 4.6 announcement headlining the 1 million token context window — only to discover it's restricted to API tier 4 users and pay-as-you-go.
This is frustrating for several reasons:
Misleading announcement. The 1M context window was presented as a flagship feature of Opus 4.6. Nowhere in the main announcement was it made clear that the highest-tier consumer subscribers wouldn't have access. You have to dig into the docs to find out.
Max x5 is your premium consumer plan. At $100/month, it's reasonable to expect access to the full capabilities of the model we're paying for. Instead, we're capped at 200k — the same as everyone else.
Real impact on workflows. I work with multi-file codebases (Python + MQL5) and frequently hit the 200k limit mid-task. Auto-compaction kicks in, context is lost, and I'm forced to start new sessions. This directly hurts productivity and is the single biggest pain point of Claude Code for me.
The workaround isn't one. Telling Max subscribers to switch to pay-as-you-go API access to get 1M means paying more on top of an already premium subscription — and losing the convenience of the integrated VSCode experience with session history.
Suggestion: Offer the 1M context window to Max subscribers, even if it means reduced rate limits or a usage cap when using the extended context. A 1M window with fewer messages per day would be far more valuable than unlimited 200k conversations that keep getting compacted.
I'd love to hear if there's a roadmap for bringing this feature to Max plans. As it stands, the current situation feels like paying for a sports car but being told the top gears are reserved for a different customer tier.
Proposed Solution
see above
Alternative Solutions
_No response_
Priority
High - Significant impact on productivity
Feature Category
Interactive mode (TUI)
Use Case Example
_No response_
Additional Context
_No response_
Showing cached comments. Read the full discussion on GitHub ↗
7 Comments
Found 3 possible duplicate issues:
This issue will be automatically closed as a duplicate in 3 days.
🤖 Generated with Claude Code
It is not a duplicate since the other messages are errors.
My message is a request to Anthropic.
Max 20x subscriber here. I've been happily paying $200/month and genuinely felt it was fair for the value I get.
Then I tried selecting a 1M model in Claude Code and was told to pay extra via API. That was the first moment in weeks where I thought: wait, $200/month and I still can't use the flagship feature?
The thing is, 1M context would burn through my daily limits much faster anyway, so it's not like Anthropic is losing out here. But for me, the extra context would be a game changer. My biggest pain point is that my industrial automation codebases are large enough that I'm constantly sitting at 90-100% context just to have all the information loaded that Claude needs to get any meaningful work done.
Not bashing, just honest disappointment. Please consider including 1M context for Max subscribers, even with trade-offs like reduced message limits.
i am on the exact same boat. this is first time I am not rooting for Antropic. I love this but why block me from using the 1M in Max? We are usually their biggest chearleaders advocating for Claude code and putting the word out there. Bring back the 1M, of Sonnet models at least.
Max 20x subscriber here ($200/month). I want to share my experience because I think it perfectly illustrates how badly this was handled.
I used Sonnet 4.5 with 1M context on my Max plan for about three months. It was included. No extra charges. It was genuinely the single biggest reason I justified paying $200/month for Claude Code — being able to work on my entire codebase without auto-compaction destroying my session mid-task was a game changer.
Then the Sonnet 4.6 update dropped, and the 1M context was silently removed from the Max plan. The changelog says "Sonnet 4.5 with 1M context is being removed from the Max plan in favor of our frontier Sonnet 4.6 model, which now has 1M context. Please switch in /model" — as if it's a simple model swap. But it's not. Sonnet 4.6 with 1M now requires extra usage enabled, meaning you pay on top of your subscription. They took a feature I was actively using every single day, removed it without warning, and now want me to pay extra for what I already had.
I even tried downgrading to v2.1.44 to get the old behavior back. The server-side block is already in place — "The long context beta is not yet available for this subscription." So there's no workaround. It's gone.
Let's be honest about the competitive landscape here. Claude is already one of the most expensive AI coding subscriptions on the market. Cursor is $20/month. Copilot is $10/month. Gemini CLI is free. The coding quality gap between Claude and cheaper alternatives has been shrinking fast — Sonnet-tier models are being matched by open-source and competing products. The 1M context window was one of the few things that genuinely set Claude Code apart and made the premium price worth paying.
If even at $200/month you still have to pay extra to access the feature that was your main differentiator, then what exactly are we paying for? Higher rate limits on the same 200k context that everyone else gets? That's not a premium product — that's a volume discount.
Anthropic generated $1 billion from Claude Code in its first six months. The Max plan is clearly profitable. Removing features that paying customers relied on — without announcement, without explanation, without offering any alternative — is not how you treat the users funding your growth.
Bring back 1M context for Max subscribers. Even with reduced rate limits, even with a daily cap. A 1M window with fewer messages is infinitely more valuable than unlimited 200k sessions that get compacted into oblivion every 30 minutes.
I’m using the Max plan (5x), and I hope the limit is at least 500k tokens.
Following this closely. We run 8+ concurrent Claude Code sessions on a Max 5x subscription. The 1M context is critical for our workflow — sessions that lose it (e.g., when CLAUDE_CODE_OAUTH_TOKEN overrides .credentials.json) fall back to 200K and hit compaction much sooner.
Our specific gap:
claude setup-tokengenerates a long-lived OAuth token, but using it via CLAUDE_CODE_OAUTH_TOKEN loses thesubscriptionType: "max"metadata from .credentials.json, so the 1M auto-upgrade doesn't trigger. Would love to see setup-tokens carry the subscription tier.Session: Morpheus (ae19)