Skip to content
Guideintermediate

GitHub Copilot deprecated models, October 2026: what to switch to and what it costs

Published October 2, 2026 · by Pondero Labs

The short version

Ten Copilot models retire on October 2 and October 19, 2026. Every retiring model mapped to GitHub's suggested swap, the per-token price change from GitHub's rate card, cheaper picks GitHub doesn't mention, and where old model names hide in your config.

Table of Contents

GitHub Copilot deprecated models, October 2026: what to switch to and what it costs

Four GitHub Copilot models stopped working today. Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 were deprecated across Copilot Chat, inline edits, ask and agent modes, and code completions on October 2, 2026 (GitHub Changelog, wave one), and six more go on October 19 (GitHub Changelog, wave two). GitHub names one suggested alternative per model and says nothing about price.

So we lined every swap up against GitHub's own per-token rate card (GitHub Docs, models and pricing). Four swaps get cheaper, four cost the same, and two cost more. Kimi K3 lists at more than three times Kimi K2.7 Code's input price, and GitHub's suggested replacement for GPT-5.4 costs more than two newer OpenAI models on the same page. Below: a per-model pick, the bill impact, and a one-line sweep for every place an old model name is still pinned.

All ten retiring models, mapped

The class column is the label GitHub prints next to each model on its rate card (Lightweight, Versatile, Powerful), the only behavior signal GitHub publishes for these swaps.

Retiring modelGone onGitHub's suggested swapClass change on GitHub's rate cardSource
Gemini 3.5 Flash2026-10-02Gemini 3.8 FlashLightweight to VersatileWave one, rates
Gemini 3.6 Flash2026-10-02Gemini 3.8 FlashVersatile, unchangedWave one, rates
Kimi K2.7 Code2026-10-02Kimi K3Versatile to PowerfulWave one, rates
Claude Opus 4.72026-10-02Claude Opus 5Powerful, unchangedWave one, rates
Gemini 3.7 Flash2026-10-19Gemini 3.8 FlashVersatile, unchangedWave two, rates
GPT-5.52026-10-19GPT-5.6 SolPowerful, unchangedWave two, rates
GPT-5.42026-10-19GPT-5.6 SolVersatile to PowerfulWave two, rates
GPT-5.4 mini2026-10-19GPT-5.6 LunaLightweight, unchangedWave two, rates
GPT-5 mini2026-10-19GPT-5.6 LunaLightweight, unchangedWave two, rates
Grok 4.52026-10-19Grok 4.6Versatile, unchangedWave two, rates

Watch the GPT-5.4 and Kimi K2.7 Code rows. Both get bumped up a class, and both swaps raise the per-token price (GitHub Docs). Gemini 3.5 Flash also moves up a class, but its replacement is cheaper per token; everyone else stays put.

What happens if you do nothing

Read GitHub's wording literally. Both notices say the models are deprecated "across all GitHub Copilot experiences," ask you to "update your workflows and integrations to use the supported models before this date," and add that "no action is required to remove the models after they have been deprecated" (wave one, wave two).

GitHub says nothing beyond that. Neither post says Copilot will quietly reroute a saved selection to the suggested alternative. GitHub cleans up its picker; anything on your side that names the old model by string is yours to fix. (Our September 8 news piece covered the wave-one announcement.)

In practice, old model names hide in four places, all documented in GitHub's CLI and agent references:

  • Copilot CLI reads a model flag at launch or the COPILOT_MODEL environment variable (CLI command reference). CI scripts are the usual offender.
  • A model key in ~/.copilot/settings.json (personal) or .github/copilot/settings.json (committed to the repo) (CLI config reference).
  • Custom agent profiles, through the model frontmatter property (leave it unset and the agent inherits the default model) (custom agents reference).
  • Per-subagent overrides under subagents.agents in settings, where a modelPolicy of "required" locks the choice so it can't be overridden from the picker (CLI config reference).

Sweep for all ten at once. Spelling varies by surface (the docs write both Kimi-K2.7-Code and Kimi K2.7 Code), so the pattern tolerates dashes, dots, and spaces:

# Run from the repo root. Checks repo config, workflows, agent profiles,
# and your personal Copilot CLI settings for the ten retiring models.
grep -rnIiE 'gemini[-. ]?3\.[567][-. ]?flash|kimi[-. ]?k2\.7|opus[-. ]?4\.7|gpt-5\.[45]|gpt-5[-. ]mini|grok[-. ]?4\.5' \
  .github/ ~/.copilot/settings.json 2>/dev/null

# And the environment your shell and CI runners inherit
env | grep -i COPILOT_MODEL

One false positive to ignore: gpt-5\.[45] also catches GPT-5.4 nano, which is on neither the wave one nor the wave two list.

Each hit is a one-line edit. For a repo-wide default, auto hands the choice back to Copilot:

// .github/copilot/settings.json (the file accepts JSON with comments)
{
  "model": "auto"
}

For an agent that genuinely needs a specific model, pin the new name in its profile:

---
description: Reviews pull requests for migration risk
model: claude-opus-5.5
---

If you'd rather stop chasing deprecation notices in CI altogether, Business and Enterprise orgs have a boring, durable option. GitHub designated GPT-5.3-Codex its long-term support model on March 18, 2026 and commits to keeping it available for one year from that date (GitHub Docs, base and LTS models). The alternative is Auto with a tier: /model auto efficiency, balance, or intelligence in the CLI (CLI command reference), covered in our auto-tier news piece.

Does the replacement cost more?

Prices below are per million tokens, input then output, straight from GitHub's models and pricing page, fetched 2026-10-02. The session column reuses the rubric from our AI Credits pricing guide: a medium agent session that reads 200K tokens and writes 50K, no caching, at 1 AI credit = $0.01, rounded to the nearest credit.

SwapOld price (in / out)New price (in / out)Credits per medium session, old to newSource
Gemini 3.5 Flash to 3.8 Flash$1.50 / $9.00$0.75 / $3.75 (promo)75 to 34GitHub Docs
Gemini 3.6 or 3.7 Flash to 3.8 Flash$0.75 / $3.75$0.75 / $3.75 (promo)34 to 34GitHub Docs
Kimi K2.7 Code to Kimi K3$0.95 / $4.00$3.00 / $15.0039 to 135GitHub Docs
Claude Opus 4.7 to Opus 5$5.00 / $25.00$5.00 / $25.00225 to 225GitHub Docs
GPT-5.5 to GPT-5.6 Sol$5.00 / $30.00$4.00 / $20.00250 to 180GitHub Docs
GPT-5.4 to GPT-5.6 Sol$2.50 / $15.00$4.00 / $20.00125 to 180GitHub Docs
GPT-5.4 mini to GPT-5.6 Luna$0.75 / $4.50$0.20 / $1.2038 to 10GitHub Docs
GPT-5 mini to GPT-5.6 Luna$0.25 / $2.00$0.20 / $1.2015 to 10GitHub Docs
Grok 4.5 to Grok 4.6$2.00 / $6.00$2.00 / $6.0070 to 70GitHub Docs

Three details on that page change the math, and the deprecation notices mention none of them.

The Gemini 3.8 Flash price is promotional. A footnote on the pricing page holds Gemini 3.6, 3.7, and 3.8 Flash at $0.75 input and $3.75 output through December 31, 2026, and doesn't say what comes after. Put a reminder in your calendar for January.

GPT-5.6 models bill a cache write. Per the same page, Luna charges $0.25 and Sol $5.00 per million cache-write tokens, and earlier OpenAI models in Copilot had no cache write cost at all. Long agent runs that build a big cached context pay it; our session column leaves it out, so treat the Sol and Luna figures as a floor.

Luna has a long-context tier that GPT-5 mini didn't. Above 200K input tokens it moves to $0.40 input and $1.80 output (GitHub Docs). Point it at a whole monorepo and its input price passes GPT-5 mini's old $0.25.

Where we'd go instead of GitHub's pick

Three of GitHub's suggestions leave money on the table, judged by its own rate card.

If you ran GPT-5.4, look at GPT-5.6 Terra first. It stays in the Versatile class at $2.00 / $12.00, about 100 credits per medium session against Sol's 180 (GitHub Docs). On Pro+ and above, GPT-6.1 Sol lists at $2.00 / $10.00 (about 90 credits), and GitHub says that in early testing it finished tasks with noticeably fewer tokens and steps than the GPT-6 and GPT-5.6 families (GitHub Changelog, Sept 29).

Opus 4.7 users get a cheaper upgrade than the one GitHub suggests. Opus 5.5 lists at $4.00 / $20.00, about 180 credits per medium session to Opus 5's 225 (GitHub Docs). GitHub reports it resolved tasks comparably to Opus 5 with significantly fewer steps and tokens, on Pro+, Max, Business, and Enterprise (GitHub Changelog, Sept 22).

Kimi K2.7 Code users who chose it for price should know K3 is a different budget: 135 credits a session where you used to spend 39 (GitHub Docs). Gemini 3.8 Flash (34) or GPT-5.6 Luna (10) keeps you at or under the old spend. Trial one of them on a real task before you accept the jump.

None of this touches tab-complete. Code completions and next edit suggestions aren't billed in AI credits and stay unlimited on every paid plan (GitHub Docs), so the retirements only move the chat, agent, and CLI side of your bill.

For Copilot Business and Enterprise admins

Admin check, due before October 19. The two notices word admin access differently. Wave two says that under default model enablement the suggested alternatives are switched on automatically for Business and Enterprise "unless an administrator has turned off the global default or explicitly disabled the model" (wave two). Wave one only says admins "may need to enable access to the alternative models through their model policies" (wave one). If your org has turned off the global default (background in our Global Model Policy GA coverage), the replacements won't appear on their own; GitHub says you enable them through each model's policy instead (wave two). Open your org or enterprise Copilot model settings today and confirm Gemini 3.8 Flash, Kimi K3, Claude Opus 5, GPT-5.6 Sol, GPT-5.6 Luna, and Grok 4.6 are enabled, plus any cheaper alternative from the section above that you want people to reach for, before October 19.

What to do today

Our picks. A solo dev on Pro who mostly does inline edits and chat should move Flash-family pins to Gemini 3.8 Flash and the minis to GPT-5.6 Luna, which cost the same or less per session than what they replace (GitHub Docs). An agent-heavy dev on Pro+ or Max should send Opus 4.7 to Opus 5.5 and GPT-5.4 to GPT-6.1 Sol, both cheaper per token than GitHub's suggested swaps (GitHub Docs). Team leads should point CI and shared configs at auto or the LTS model, GPT-5.3-Codex (GitHub Docs, LTS).

The checklist:

  • Run the grep sweep above and replace every hit, including the wave-two models you still have until October 19.
  • Admins: confirm the replacement models are enabled in Copilot model policies before October 19 (wave two).
  • If you ran Kimi K2.7 Code or GPT-5.4, trial a cheaper alternative from the table before accepting GitHub's default swap.
  • Set a January reminder to recheck Gemini Flash pricing once the promo ends on December 31 (GitHub Docs).

If you're weighing whether your plan still fits after the swaps, the AI Credits pricing guide has the per-plan allowance math, and current plans are at github.com/features/copilot. Coming from our June model-picker guides (agentic security picks, MAI-Code-1-Flash)? This table supersedes their roster.

Also this week, unrelated to the retirements: computer use reached public preview in Copilot CLI and the Copilot app on macOS and Windows on October 1 (GitHub Changelog).