OAI really trying to push folks to either the ad infested tier for gen chat (ChatGPT Go) or Pro ($100/month) for code.
I guess the $20 Plus plan is the red-headed step child now.
Meanwhile, Z.ai coder is what…$9/month? Hmmm.
I don’t have a local rig powerful enough to natively run a good coder (Qwen 3 next), but “I am altering the deal, pray I do not alter it any further” is THE perfect use case for running your shit locally.
PS: It looks like Pro and Plus tiers have gone up a smidge too? Eg: last I checked they were $20 and $100; they now show $30 and $155. I cancelled my account so OAI gifted me a free month (lol) but seriously…fuck that.
It’s not entirely unexpected, all the AI companies have been heavily subsidising inference to get customers.
I don’t use Codex but I’ve been experimenting with ECA and I can track my token API costs across Gemini and Anthropic. I’m mostly using Gemini and a heavy days usage would be £1.50 in API costs and I’m certainly not doing that every day. I have to wonder if these Codex users are conscious of how many tokens they are burning underneath or just YOLOing everything until the computer says no?
ECA allows you to mix and match models to sub-agents and I could certainly see me offloading some tasks like code exploration to a locally hosted models and saving the expensive reasoning tokens for planning.
Absolutely true. If I had to pull a number out of thin air, I’d say they were still probably under-charging what it actually costs them to run these things by an order of magnitude or two. So right now, Codex pro costs $150…but in a year or two? $300-400 or even $500? I can see them slowly ratcheting it up. It’s the same old story we’ve seen played out before (eg: Uber, Spotify, Netflix etc).
Doesn’t mean it’s one we should particularly want to see repeat tho.
Like you, I like the notion of mixing and matching local agents for grunt work and off-loading the thinking to API or SOTA. I hadn’t heard of ECA - that looks like it’s right up my alley. Thanks for that
PS: Just to let you know - ECA is fucking amazing! Thank you VERY much for that. I’m currently using Sonnet 4.6 via OpenRouter API to boss around my local Qwen3-4… so far so good :)
Right now, I can see -
Sonnet 4.6 API is not too bad at all at moment
- 1,000,000 context $3/M input tokens / $15/M output tokens
GLM 5.1 is STUPID cheap for what it is (promo?)
- 202.8K context $1.395/M input tokens / $4.40/M output tokens
And Gemma 4 31B is just taking the piss
- 262.1K context $0.14/M input tokens / $0.40/M output tokens
(or FREE via Google…but you know…ZDR)
Called it.
$300 fucking dollary-doos, my son. Yeah, nah.
How is Gemini 4 open source for coding? Seems to run well even on mid tier gpu’s
I’ve used Gemma4-31B for agentic coding and its actually very good as far as local models go. Its less verbose than qwen3.5 so it ends up being faster too. Gemma4-26B can do agentic but its noticeably worse so you have to go slow with it. I haven’t had any coherence issues like other commenters mention but I’ve only been using higher quality quants from unsloth on llama.cpp
Ola. I tried Gemma 31B tonight for coding.
Don’t bother. It chews files up when it should read them and needs constant micromanagement. The typical toddler hopped up on sugar issue
Stick with Qwen 3 Next. It’s still a toddler on a sugar rush, but it’s beyond the “shitting its pants and then using it to paint on the walls” stage (mostly).
Honestly, I think this is a PsyOP by OAI and Anthropic to make people git gud LOL.
Assuming you mean gemma4, I used the 26b for a while. While it was decent at coding, it would drandomly just go insane and start going in loops repeating sentences or words until I killed it
I genuinely haven’t tried it. Can someone here comment on it?
PS: I take it you mean Gemma not Gemini?
wow I love that my brain has been autocorrecting Gemma to Gemini for the last week
