I noticed 1M context window is default and no way not to use it. If your context is at 500-900k tokens every prompt, you’re gonna hit limits fast.

▲ Wowfunhappy 6 hours ago | parent | next [-]

I had to double check that they'd removed the non-1M option, and... WTF? This is what's in `/config` → `model`

    1. Default (recommended)    Opus 4.6 with 1M context · Most capable for complex work
    2. Sonnet                   Sonnet 4.6 · Best for everyday tasks
    3. Sonnet (1M context)      Sonnet 4.6 with 1M context · Billed as extra usage · $3/$15 per Mtok
    4. Haiku                    Haiku 4.5 · Fastest for quick answers

So there's an option to use non-1M Sonnet, but not non-1M Opus?

Except wait, I guess that actually makes sense, because it says Sonnet 1M is billed as extra usage... but also WTF, why is Sonnet 1M billed as extra usage? So Opus 1M is included in Max, but if you want the worse model with that much context, you have to pay extra? Why the heck would anyone do that?

The screen does also say "For other/previous model names, specify with --model", so I assume you can use that to get 200K Opus, but I'm very confused why Anthropic wouldn't include that in the list of options.

What a strange UX decision. I'm not personally annoyed, I just think it's bizarre.

▲

retrofuturism 5 hours ago | parent [-]

`/model opus` sets it to the original non-1M Opus... for now.

	▲	windexh8er 4 hours ago \| parent [-]
		Thanks. I quickly burned through $100 in credit when I started using Opus 4.6 in OpenCode via OpenRouter. My session stopped and was getting an error not representative of credit availability, so was surprised after a few minutes when I finally realized Opus just destroyed those credits on a bullshit reasoning loop it got stuck in. Anthropic seems to know that the expanded context is better for their bottom line as they've defaulted it now. And as others have said it's very easy to burn token usage on the $100/month plan. It's getting to the point where it's going to very much make sense to do model routing when using coding tooling.

▲ aberoham 6 hours ago | parent | prev | next [-]

export CLAUDE_CODE_DISABLE_1M_CONTEXT=1

▲

teaearlgraycold 6 hours ago | parent [-]

Anthropic is not building good will as a consumer brand. They've got the best product right now but there's a spring charging behind me ready to launch me into OpenCode as soon as the time is right.

▲

kylecazar 6 hours ago | parent [-]

Would you use Opus if you switched to OpenCode?

▲

teaearlgraycold 6 hours ago | parent [-]

I'd like to use Opus with OpenCode right now to combine the best TUI agent app with the best LLM. But my understanding is Anthropic will nuke me from orbit if I try that.

▲

joecot 5 hours ago | parent | next [-]

You can use Opus with OpenCode anytime you want, just not with the Claude plan. You can use it via API with any provider, including Anthropic's API. You can use it with Github Copilot's plan. The only thing you can't do without getting banned is use OpenCode with one of Claude's plans.

	▲	nurettin 2 hours ago \| parent [-]
		I keep seeing this "you can use the inconvenient and unpredictably costly way all you want" pedantic kneejerk response so often lately. It's like saying well humans can fly with a paraglider. It is correct and useless. Most here won't have cash to burn with unbounded opus api usage.

▲

corford 5 hours ago | parent | prev [-]

OpenCode with a Copilot Business sub and Opus 4.6 as the model works well

	▲	teaearlgraycold 3 hours ago \| parent [-]
		I'm looking at their plans (https://github.com/features/copilot/plans) it seems like the limits might be pretty low, even with the Pro+ plan which is 2x the cost of Claude Pro. It seems like Claude Pro might be 10-20x the Opus tokens for only twice the price.

▲ nextaccountic 3 hours ago | parent | prev | next [-]

do you pay for the full context every prompt? what happened with the idea of caching the context server side?

	▲	davesque 3 hours ago \| parent [-]
		You don't. Most of the time (after the first prompt following a compaction or context clear) the context prefix is cached, and you pay something like 10% of the cost for cached tokens. But your total cost is still roughly the area under a line with positive slope. So increases quadratically with context length.

▲ zhangchen 3 hours ago | parent | prev [-]

[dead]