Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> 400,000 context window

> 128,000 max output tokens

> Input $1.25

> Output $10.00

Source: https://platform.openai.com/docs/models/gpt-5

If this performs well in independent needle-in-haystack and adherence evaluations, this pricing with this context window alone would make GPT-5 extremely competitive with Gemini 2.5 Pro and Claude Opus 4.1, even if the output isn't a significant improvement over o3. If the output quality ends up on-par or better than the two major competitors, that'd be truly a massive leap forward for OpenAI, mini and nano maybe even more so.



Being on-par with competitors is somehow a "massive leap" for OpenAI now? How far have they fallen...


Are you kidding? If GPT 5 is really on par with Opus 4.1, it means now OpenAI is offering the same product but 10 times cheaper. In any other industry it's not just a massive leap. It's "all competitors are out of market in a few months if they can't release something similar."


goalpost shifting for GPT5? I remember it was supposed to be AGI


Who said that?


Soon™


You also have to count the cost of having to verify your identity to use the API


It's only a video face scan and your legal ID to SamA, what could possibly go wrong


Oh they haven’t integrated the retinal scan tech yet eh?


Wait, is this real?


Yes, [1] though a bit vague given "Some organizations may already have access to these models and capabilities without having to go through the Verification process."

I never verified but have access to all models including image gen, for example.

[1] https://help.openai.com/en/articles/10910291-api-organizatio... [2] https://help.openai.com/en/articles/10362446-api-reasoning-m...


Let's not forget that SamA's other business venture is creating the World's largest biometric database.

So it's all for sale the moment the VC money stops keeping that unprofitable company with overpaid engineers afloat.


To clarify, you need to verify identity to use the GPT-5 API?

I understand for image generation, but why for text generation?


Because they want to contribute to the fascism of mass surveillance


OpenRouter (and potentially Azure in the near future) are options if verifying for enterprise API use is too hard to stomach.


Neither will be. Both OpenRouter and Azure (through requiring and enterprise agreement, only available to large orgs with 500+ devices) require it for o3 to this very day, and already do so for GPT-5, the main model under discussion in this thread (sure, not mini and nano, but those aren't where 95% of the attention is focused on).


openrouter requires an openai api key.


Where did you get that from? I am currently using GPT-5 via OpenRouter and never added an OpenAI key to my account there. Same for any previous OpenAI model. BYOK is an option, not a necessity.


You had to use your own key for o3 at least.

> Note that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations

https://openrouter.ai/api/v1/models


> {"id":"openai/gpt-5-chat","canonical_slug":"openai/gpt-5-chat-2025-08-07","hugging_face_id":"","name":"OpenAI: GPT-5 Chat","created":1754587837,"description":"GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":"0.00000125","completion":"0.00001","request":"0","image":"0","audio":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000125"},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","seed","structured_outputs"]},

If you look at the JSON you linked, it does not enforce BYOK for openai/gpt-5-chat, nor for openai/gpt-5-mini or openai/gpt-5-nano.


Did I say GPT-5? I said o3. :) That was a rebuttal to you saying you have never needed to add your key to use an OpenAI model before.


Fair, I should not have said "any".


It does for the model this thread is about: openai/gpt-5.


What's openai/gpt-5 vs openai/gpt-5-chat?


you can also use https://nano-gpt.com/ if privacy is necessary


Interesting that gpt-5 has Oct 01, 2024 as knowledge cut-off while gpt-5-mini/nano it's May 31, 2024.

gpt-4.1 family had 1M/32k input/output tokens. Pricing-wise, it's 37% cheaper input tokens, but 25% more expensive on output tokens. Only nano is 50% cheaper on input and unchanged on output.


Needle in a haystack is not a good evaluation though - even famously bad llama 4 does well on that benchmark.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: