{"version":1,"type":"story","url":"https://digestai.news/story/near-ai-cloud-enables-private-github-copilot-inference-through-vscode","json":"https://digestai.news/story/near-ai-cloud-enables-private-github-copilot-inference-through-vscode.json","markdown":"https://digestai.news/story/near-ai-cloud-enables-private-github-copilot-inference-through-vscode.md","slug":"near-ai-cloud-enables-private-github-copilot-inference-through-vscode","headline":"Near AI Cloud enables private GitHub Copilot inference through VSCode extension","summary":"Developers who use GitHub Copilot can now run the assistant on models hosted by Near AI Cloud without sending their code to external servers. The service is accessed through the VS Code “More Providers” extension, which exposes an OpenAI‑compatible API and works with the IDE’s Bring Your Own Key (BYOK) feature that removed the GitHub sign‑in requirement for custom endpoints.\n\nNear AI Cloud protects prompts, model weights, and outputs inside Trusted Execution Environments built on Intel TDX and NVIDIA confidential computing. Each request includes a hardware‑signed attestation, and users may enable client‑side encryption for extra assurance. Pricing is about $0.15‑$0.50 per million input tokens, with higher output rates, and developers can stake NEAR tokens to receive inference credits while keeping their stake. The platform, launched in December 2025, added the SayGm gateway in August 2026 and an OpenRouter integration in September 2026, expanding access options for developers and NEAR token holders.","keyPoints":["Near AI Cloud offers an OpenAI‑compatible API that lets Copilot run models inside TEEs, protecting prompts, weights, and outputs.","Input pricing is about $0.15‑$0.50 per million tokens; users can stake NEAR tokens for inference credits while keeping the stake.","The integration uses VS Code’s “More Providers” extension and BYOK support, removing the GitHub sign‑in requirement for custom endpoints."],"whyItMatters":"It gives developers with strict data policies a way to keep code private while using Copilot, and introduces a token‑staking model that links NEAR’s crypto economy to AI inference.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Near AI Cloud","GitHub","Microsoft","Intel","NVIDIA"],"models":["GLM 5.3 Flash"],"people":[]},"firstPublishedAt":"2026-10-01T15:46:00Z","updatedAt":"2026-10-01T15:46:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"cryptobriefing.com","title":"NEAR AI Cloud brings private inference to GitHub Copilot through a VSCode extension","url":"https://cryptobriefing.com/near-ai-private-inference-github-copilot","publishedAt":"2026-10-01T15:46:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Near AI Cloud enables private GitHub Copilot inference through VSCode extension\", 1 October 2026, https://digestai.news/story/near-ai-cloud-enables-private-github-copilot-inference-through-vscode","publisher":"Digest AI","title":"Near AI Cloud enables private GitHub Copilot inference through VSCode extension","datePublished":"2026-10-01T15:46:00Z","url":"https://digestai.news/story/near-ai-cloud-enables-private-github-copilot-inference-through-vscode"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}