Undominated.ai

Migration guide

Every model with a standard listing and a retirement date, one whose date has passed but which is still served included, and its like-for-like replacement: of the models with no retirement date that keep every recorded capability and, when the retiring model is rated, score at least as high, the one that is cheapest at short prompts. Where none exists, the page says so.

Retirement tracking Methodology

Like-for-like means every input and output modality, tool use and reasoning the retiring model has, a context window and output limit at least as large and on record, and no retirement date of its own. It covers what the catalogue records, not every behaviour. Price is the balanced workload, 3 parts input to 1 part output, in $ per million tokens, for a prompt below every context tier: "cheapest" means cheapest at short prompts. Where a longer prompt makes another model the cheapest (10 of 27 lines), the line names it; how prices rise with prompt size is on Context price cliffs. Scores are LMArena Elo under CC BY 4.0, from the official dataset.

  1. Nano Banana (Gemini 2.5 Flash Image) replaced by Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image): Neither is rated, so this compares recorded capabilities and price, not score; 34% cheaper

    Retirement date · score unrated → unrated · $0.850 → $0.563 per million

  2. ERNIE 4.5 VL 424B A47B replaced by Nex-N2.5-Mini: Neither is rated, so this compares recorded capabilities and price, not score; 93% cheaper

    Retirement date · score unrated → unrated · $0.628 → $0.044 per million

  3. Qwen Plus 0728 replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 86% cheaper

    Over 32K-token prompts, DeepSeek V4 Flash 0731 is the cheapest instead.

    Retirement date · score unrated → unrated · $0.390 → $0.055 per million

  4. Qwen3 235B A22B replaced by DeepSeek V4 Flash 0423: +65.5 score, 86% cheaper

    Retirement date · score 1366.6 → 1432.1 · $0.796 → $0.113 per million

  5. Qwen3 235B A22B Thinking 2507 replaced by DeepSeek V4 Flash 0423: +16.9 score, 85% cheaper

    Retirement date · score 1415.2 → 1432.1 · $0.748 → $0.113 per million

  6. Qwen3 30B A3B Thinking 2507 replaced by gpt-oss-20b: Qwen3 30B A3B Thinking 2507 is unrated, so this compares recorded capabilities and price, not score; 95% cheaper

    Retirement date · score unrated → 1287.7 · $0.750 → $0.036 per million

  7. Qwen3 8B replaced by gpt-oss-20b: Qwen3 8B is unrated, so this compares recorded capabilities and price, not score; 82% cheaper

    Retirement date · score unrated → 1287.7 · $0.202 → $0.036 per million

  8. Qwen3 Coder Plus replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 96% cheaper

    Over 32K-token prompts, DeepSeek V4 Flash 0731 is the cheapest instead.

    Retirement date · score unrated → unrated · $1.30 → $0.055 per million

  9. Qwen3 Max replaced by DeepSeek V4 Flash 0423: +19.7 score, 93% cheaper

    Retirement date · score 1412.4 → 1432.1 · $1.56 → $0.113 per million

  10. Qwen3 Max Thinking replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 96% cheaper

    Over 32K-token prompts, Nemotron 3 Nano 30B A3B is the cheapest instead.

    Retirement date · score unrated → unrated · $1.56 → $0.055 per million

  11. Qwen3 Next 80B A3B Thinking replaced by DeepSeek V4 Flash 0423: +63.8 score, 73% cheaper

    Retirement date · score 1368.3 → 1432.1 · $0.413 → $0.113 per million

  12. Qwen3 VL 235B A22B Thinking replaced by Gemma 4 26B A4B: +33.2 score, 90% cheaper

    Retirement date · score 1400.7 → 1433.9 · $1.30 → $0.127 per million

  13. Qwen3 VL 30B A3B Thinking replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 88% cheaper

    Over 32K-token prompts, Ling 3.0 Flash VL is the cheapest instead.

    Retirement date · score unrated → unrated · $0.468 → $0.055 per million

  14. Qwen3 VL 32B Instruct replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 70% cheaper

    Over 32K-token prompts, Ling 3.0 Flash VL is the cheapest instead.

    Retirement date · score unrated → unrated · $0.182 → $0.055 per million

  15. Qwen3 VL 8B Instruct replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 73% cheaper

    Over 32K-token prompts, Ling 3.0 Flash VL is the cheapest instead.

    Retirement date · score unrated → unrated · $0.202 → $0.055 per million

  16. Qwen3 VL 8B Thinking replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 92% cheaper

    Over 32K-token prompts, Ling 3.0 Flash VL is the cheapest instead.

    Retirement date · score unrated → unrated · $0.660 → $0.055 per million

  17. Qwen3.6 Max Preview replaced by MiMo-V2.6-Flash: +9.6 score, 92% cheaper

    Retirement date · score 1446.8 → 1456.4 · $2.31 → $0.175 per million

  18. Gemini 2.5 Flash replaced by Gemini 3.5 Flash Lite: +17.7 score, same price

    Retirement date · score 1417.0 → 1434.7 · $0.850 → $0.850 per million

  19. Gemini 2.5 Flash Lite replaced by Muse Spark 1.2 Contributor: Neither is rated, so this compares recorded capabilities and price, not score; 29% cheaper

    Retirement date · score unrated → unrated · $0.175 → $0.125 per million

  20. Gemini 2.5 Pro replaced by Gemini 3.6 Flash: +21.7 score, 56% cheaper

    Retirement date · score 1457.8 → 1479.5 · $3.44 → $1.50 per million

  21. Laguna S 2.1 replaced by DeepSeek V4 Flash 0731: Neither is rated, so this compares recorded capabilities and price, not score; 28% cheaper

    Retirement date · score unrated → unrated · $0.125 → $0.090 per million

  22. Laguna XS 2.1 replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 56% cheaper

    Over 32K-token prompts, Nemotron 3.5 Lightning is the cheapest instead.

    Retirement date · score unrated → unrated · $0.125 → $0.055 per million

  23. Seed 1.6 replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 92% cheaper

    Over 32K-token prompts, Ling 3.0 Flash VL is the cheapest instead.

    Retirement date · score unrated → unrated · $0.688 → $0.055 per million

  24. Seed 1.6 Flash replaced by Qwen3.7 Flash: Neither is rated, so this compares recorded capabilities and price, not score; 58% cheaper

    Over 32K-token prompts, Ling 3.0 Flash VL is the cheapest instead.

    Retirement date · score unrated → unrated · $0.131 → $0.055 per million

  25. Seed-2.0-Code replaced by Muse Spark 1.2 Contributor: Neither is rated, so this compares recorded capabilities and price, not score; 89% cheaper

    Retirement date · score unrated → unrated · $1.13 → $0.125 per million

  26. GLM 4.5 replaced by DeepSeek V4 Flash 0423: +1.8 score, 89% cheaper

    Retirement date · score 1430.3 → 1432.1 · $1.00 → $0.113 per million

  27. GLM 4.7 replaced by MiMo-V2.6-Flash: +20.9 score, 76% cheaper

    Retirement date · score 1435.5 → 1456.4 · $0.738 → $0.175 per million

Dates are the catalogue's, as of 2026-10-06. Direct API and partner schedules can differ; check the notice on Retirement tracking before migrating.

Evidence & Ask
Markdown for LLMs