Skip to main content

Top news

Investing in the public benefit Anthropic NewsOct 18Popular Musk Pledges SpaceX Shares to ‘Every Kid in America’ Bloomberg TechnologyOct 19Popular Websites are closing their doors to AI agents The Verge AIOct 17 This is the new ChatGPT Voice, powered by GPT Live OpenAI on YouTubeOct 18 How AI giants will reshape global philanthropy Axios AIOct 19 Gemini 4 Argon Really Surprised Me Two Minute PapersOct 19 Google Gemini 4 agents just beat Minecraft with no human intervention Engadget AIOct 19 Who could it be? 🧐 Google on YouTubeOct 18 Anthropic gives outside AI watchdog “employee-like” access Ars Technica AIOct 18 What are self-replicating ‘AI worms’, and why is Anthropic worried about them? The Guardian AIOct 18

Cost tip Coding Analysis and data WritingIntermediate · 5 min

Reduced pricing for GPT-4 Turbo input and output tokens

GPT-4 Turbo is now 3x cheaper for input and 2x cheaper for output tokens compared to GPT-4.

ChatGPTParaphrased

Tip

Open in ChatGPT Open in Claude

Utilize GPT-4 Turbo for cost savings on API calls.

Utilize GPT-4 Turbo for cost savings on API calls.

Savings

3x cheaper for input tokens, 2x cheaper for output tokens.

How

By using the `gpt-4-1106-preview` model in the API.

What it does and when to use it

Developers can significantly reduce costs by using GPT-4 Turbo, which offers 3x cheaper input tokens and 2x cheaper output tokens compared to the previous GPT-4 model. This makes advanced capabilities more accessible.

Why it works

OpenAI has optimized GPT-4 Turbo's performance, allowing them to offer it at a lower price point for API usage.

When not to use it

When using older GPT-4 models or when the specific features of GPT-4 Turbo are not required and a cheaper model suffices.

Sources and credit

New models and developer products announced at DevDay ↗OpenAI News · OpenAI News · Nov 6, 2023 · paraphrased

First seen on Subvolts Nov 6, 2023. Updated Sep 11, 2026. Spotted a problem? Tell us.

Where it shows up

New models and developer products announced at DevDayOpenAI · OpenAI News · Nov 6, 2023

Related in the PlaybookPlaybook →

The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.

Cost tipReduce GPT-6 Luna costs with cached tokensUse cached input tokens to lower costs for high-volume tasks. · 5 min
Setting tipControl GPT-6 Luna reasoning effort for efficiencyAdjust reasoning_effort to balance model performance and cost for focused tasks. · 1 min
Model pickGPT-4o fine-tuning for custom applicationsFine-tune GPT-4o for higher performance and accuracy in specific use cases. · 15 min
ToolGPT-3.5 Turbo fine-tuning APICustomize GPT-3.5 Turbo models with your own data for improved performance on specific tasks. · 15 min
Cost tipManage GPT-6 Luna costs for large token promptsBe aware of increased pricing for prompts exceeding 272K input tokens. · 5 min
Cost tipUnderstand GPT-6 Luna pricing for batch and fast modesBatch and Flex modes offer 50% rates, while Fast mode doubles costs. · 5 min

Questions people ask

Which AI tools does this work with?: The sources used it with ChatGPT.
Where did this come from?: OpenAI News (OpenAI News). Subvolts collected, normalized and credited it; the link above opens the original.