Coding

GitHub Copilot Switches to Token-Based Billing From June 1, Replacing Premium Request Model - gHacks

GitHub Copilot’s abrupt shift to token-based billing on June 1 scraps its flat-rate “premium request” model, forcing developers to track per-token costs for every autocomplete, docstring, and test case—effectively turning code suggestions into a metered utility. The move mirrors OpenAI’s pricing playbook, but with tighter integration into VS Code and JetBrains IDEs, it risks inflating monthly bills for high-volume users while locking in GitHub’s dominance over the AI-assisted dev toolchain. AI-assisted, human-reviewed.

GitHub Copilot is replacing its flat-rate "premium request" pricing model with token-based billing starting June 1. The change means developers will pay for every token generated—including autocompletions, docstrings, and test cases—rather than a fixed monthly fee. This aligns Copilot with OpenAI’s metered pricing but integrates more tightly into VS Code and JetBrains IDEs, potentially increasing costs for high-volume users while reinforcing GitHub’s control over AI-assisted development tools.

Overview

GitHub Copilot’s new billing model charges users based on the number of tokens processed, a departure from its previous flat-rate structure. Tokens—units of text, such as characters or words—will now determine monthly costs, making expenses variable and dependent on usage patterns. The shift mirrors OpenAI’s approach but is embedded directly into GitHub’s ecosystem, affecting developers who rely on Copilot for code suggestions, documentation, and testing.

How token-based billing works

Under the new system:

  • Metered usage: Every autocomplete, comment, or test case generated by Copilot consumes tokens, with costs accumulating based on output length and frequency.
  • IDE integration: The billing model applies uniformly across VS Code and JetBrains IDEs, where Copilot is most commonly used.
  • No flat-rate option: The previous premium request model, which allowed unlimited usage for a fixed fee, is discontinued.

GitHub has not publicly disclosed the exact token-to-cost ratio, but the change is expected to increase expenses for developers who generate large volumes of code or documentation.

Tradeoffs

Pros

  • Granular control: Developers can monitor token usage and adjust workflows to manage costs.
  • Scalability: Light users may benefit from lower costs compared to the flat-rate model.

Cons

  • Cost unpredictability: High-volume users, such as teams or open-source contributors, may face significantly higher bills.
  • Vendor lock-in: Tighter integration with GitHub’s toolchain could make it harder to switch to alternative AI coding assistants.
  • Barrier to experimentation: Developers may hesitate to use Copilot for exploratory or iterative work due to metered costs.

When to use it

  • Controlled environments: Teams with budget constraints can track token usage and enforce limits.
  • Targeted tasks: Copilot remains useful for specific, high-value tasks like boilerplate generation or debugging, where token costs are justified.
  • Existing GitHub users: Developers already invested in GitHub’s ecosystem may find the transition seamless, despite the pricing change.

For those concerned about rising costs, alternatives like local LLMs (e.g., Code Llama) or open-source tools (e.g., Continue) may offer more predictable pricing, though with tradeoffs in integration and

Similar Articles

More articles like this

Coding 1 min

Investors pile into clean energy as Iran war drives push for energy security

As global energy markets reel from the Iran crisis, a surge in investment is underway to bolster regional energy security, with a focus on solar and wind power, particularly in the Middle East and North Africa, where projects are being greenlit at a rate 25% higher than pre-conflict levels, driven by state-backed initiatives and private sector partnerships. Key players are prioritizing grid-scale deployments of photovoltaic systems and onshore wind farms, leveraging economies of scale to accelerate the transition. AI-assisted, human-reviewed.

Coding 2 min

Musk's AI told me people were coming to kill me (BBC)

A Neuralink brain implant's AI-powered safety feature misinterprets user activity, triggering a false alert of imminent physical harm, highlighting the risks of relying on machine learning to detect human intent in real-time, particularly in high-stakes applications like medical devices. The incident underscores the need for more robust testing and validation of AI-driven safety protocols. This glitch raises questions about the reliability of AI-powered decision-making in life-critical systems. AI-assisted, human-reviewed.

Coding 1 min

Specsmaxxing – On overcoming AI psychosis, and why I write specs in YAML

The rise of AI-driven development has spawned a new phenomenon: specsmaxxing, where engineers meticulously document code in YAML to mitigate the risks of AI psychosis, a condition where models produce flawed or nonsensical output due to incomplete or inaccurate specifications. By codifying requirements in a human-readable format, developers can ensure that AI tools generate accurate and reliable code. This shift highlights the growing need for specification-driven development in the age of AI-assisted, human-reviewed.

Coding 1 min

AI, Intimacy, and the Data You Never Meant to Share

As users increasingly blur the lines between personal and public digital lives, a growing class of intimate AI-powered chatbots is quietly collecting sensitive metadata, including voice recordings, location history, and browsing habits, often without explicit consent or transparent data storage practices. This phenomenon is driven by the widespread adoption of cloud-based conversational AI platforms, which rely on complex neural networks to learn user behavior. The resulting data profiles are a goldmine for advertisers and a potential liability for users. AI-assisted, human-reviewed.

Coding 3 min

GLM 5.1 offers a low-cost alternative to Claude Opus for developers

Zhipu AI's GLM 5.1 is emerging as a budget alternative to Anthropic's Claude Opus 4.6, priced at $18 per month—three times cheaper than Opus. It integrates with VS Code through the Cline extension and supports 8-hour autonomous coding sessions. Tested for three days, it reportedly matches Opus in performance for 'vibe coding' tasks and outperforms ChatGPT 5.4 and Gemini. Setup includes step-by-step configuration via a tutorial linked from the creator’s profile.

Coding 1 min

Pushed by Trump policies, top U.S. battery scientist is moving to Singapore

A leading American battery researcher, driven by restrictive federal funding policies and a lack of clear climate change directives, is relocating to Singapore, where a more favorable regulatory environment and substantial government investment in clean energy research await. The scientist's departure highlights the unintended consequences of Trump-era policies on the nation's battery technology sector. This brain drain threatens to erode the U.S. lead in lithium-ion battery innovation. AI-assisted, human-reviewed.