isitdeprecated.com
collectors 5/5 ok last sync state ok models 2,715 events 12,850

400

changes shipped in the last two months that nobody announced. Prices moved, context windows shrank, capabilities disappeared — no email, no changelog entry, no error at runtime.

222

price changes

you pay more for the same call

226

capacity cuts

prompts truncate, no error

87

capabilities removed

a feature quietly went away

259

announced retirements

these ones you were told about

Evidence behind the numbers: 74 models confirmed against the provider's own API, 123 with dates taken from the provider's own documentation (extracted by a model, so labelled inferred), the remaining 2518 from third-party catalogs only. Every model page says which of the three it rests on.

Biggest silent changes

ImpactProvider What changedDetected
truncationgemini-99% ctx · gemini/gemini-2.5-pro-preview-tts: context_tokens cut 1,048,576 to 8,1922026-09-16
truncationopenrouter-98% max out · openrouter/moonshotai/kimi-k3:batch: max_output_tokens cut 943,718 to 16,3842026-09-22
truncationbedrock_converse-97% max out · zai.glm-4.7-flash: max_output_tokens cut 128,000 to 4,000 +1 alias2026-09-21
costdeepseek31.35x price · deepseek/deepseek-v4.1-flash: cache_read_price_per_mtok $0.0010/Mtok to $0.03/Mtok2026-09-27
cost~deepseek31.35x price · ~deepseek/deepseek-flash-latest: cache_read_price_per_mtok $0.0010/Mtok to $0.03/Mtok2026-09-27
costopenrouter31.35x price · openrouter/deepseek/deepseek-v4.1-flash: cache_read_price_per_mtok $0.0010/Mtok to $0.03/Mtok2026-09-28
truncationthedrummer-97% max out · thedrummer/unslopnemo-12b: max_output_tokens cut 1,024,000 to 32,768 inferred2026-08-24
truncationopenai-97% max out · openai/gpt-4.1-nano: max_output_tokens cut 942,818 to 32,7682026-08-30
truncationnvidia-96% max out · nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens cut 461,059 to 16,3842026-08-28
costopenrouter28.12x price · openrouter/deepseek/deepseek-v4-pro-0813: cache_read_price_per_mtok $0.0088/Mtok to $0.25/Mtok2026-09-27
costdeepseek27.79x price · deepseek/deepseek-v4-pro-0813: cache_read_price_per_mtok $0.0088/Mtok to $0.24/Mtok2026-09-27
truncationazure_ai-96% max out · azure_ai/grok-4.3: max_output_tokens cut 200,000 to 8,1922026-09-28
cost~deepseek22.14x price · ~deepseek/deepseek-pro-latest: cache_read_price_per_mtok $0.0078/Mtok to $0.17/Mtok2026-09-27
truncationbedrock_converse-95% max out · deepseek.v3.2: max_output_tokens cut 163,840 to 8,000 inferred2026-09-21
costdeepseek20.00x price · deepseek/deepseek-v4.1-flash: cache_read_price_per_mtok $0.0030/Mtok to $0.06/Mtok2026-09-25
cost~deepseek20.00x price · ~deepseek/deepseek-flash-latest: cache_read_price_per_mtok $0.0010/Mtok to $0.02/Mtok2026-09-29
cost~deepseek19.64x price · ~deepseek/deepseek-pro-latest: cache_read_price_per_mtok $0.01/Mtok to $0.25/Mtok2026-09-23
costqwen16.87x price · qwen/qwen3.8-27b: input_price_per_mtok $0.02/Mtok to $0.42/Mtok2026-09-30
Ranked by size of the change, not by when we noticed it. One row per real upstream change — aliases collapse.

All 400 changes →  ·  Check your own models →

Announced retirements

The part providers do tell you about. Included for completeness — it is the smaller half of the problem.

ModelVendorSunset RemainingSeverity
google/gemini-omni-flash-previewgoogleT-0dcritical
bedrock/amazon.nova-canvasbedrockT-0dcritical
amazon/nova-canvasamazonT-0dcritical
openai/gpt-5.4-cyberopenaiT-1dcritical
azure/mai-image-2.5azureT-1dcritical
azure/mai-image-2.5-flashazureT-1dcritical
azure/mai-image-2.5-proazureT-1dcritical
alibaba/qwen3-coder-30b-a3b-instructalibabaT-1dcritical
mistral/pixtral-12b-2409mistralT-1dcritical
google/gemini-2.5-flash-imagegoogleT-2dcritical
Earliest announced date across sources. Where catalogs disagree we show the soonest — erring early is the safe direction.

Full calendar →