isitdeprecated.com
collectors 5/5 ok last sync state ok models 2,476 events 6,902

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.

345

price changes

you pay more for the same call

130

capacity cuts

prompts truncate, no error

39

capabilities removed

a feature quietly went away

203

announced retirements

these ones you were told about

Evidence behind the numbers: 66 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 2287 from third-party catalogs only. Every model page says which of the three it rests on.

Biggest silent changes

ImpactProvider What changedDetected
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
truncationqwen-94% max out · qwen/qwen3-next-80b-a3b-instruct: max_output_tokens cut 262,144 to 16,384 +1 alias2026-08-19
truncationwatsonx-94% max out · watsonx/meta-llama/llama-4-maverick-17b: max_output_tokens cut 128,000 to 8,192 inferred2026-09-06
truncationopenrouter-94% max out · openrouter/anthropic/claude-sonnet-4.5: max_output_tokens cut 1,000,000 to 64,0002026-09-06
truncationvertex_ai-94% ctx · vertex_ai/xai/grok-4.1-fast-non-reasoning: context_tokens cut 2,000,000 to 128,000 +1 alias inferred2026-09-10
truncationvertex_ai-94% max out · vertex_ai/xai/grok-4.1-fast-non-reasoning: max_output_tokens cut 2,000,000 to 128,000 +1 alias inferred2026-09-10
costdeepseek15.00x price · deepseek/deepseek-v4-pro: cache_read_price_per_mtok $0.0036/Mtok to $0.05/Mtok2026-08-11
truncationthinkingmachines-93% max out · thinkingmachines/inkling: max_output_tokens cut 471,859 to 32,7682026-09-10
truncationqwen-93% max out · qwen/qwen3-235b-a22b-2507: max_output_tokens cut 235,929 to 16,384 +5 aliases2026-09-09
costdeepseek12.14x price · deepseek-v4-pro: cache_read_price_per_mtok $0.0036/Mtok to $0.04/Mtok +1 alias2026-08-21
costz-ai11.00x price · z-ai/glm-5.2: output_price_per_mtok $0.22/Mtok to $2.42/Mtok2026-08-10
costz-ai10.86x price · z-ai/glm-5.2: input_price_per_mtok $0.07/Mtok to $0.76/Mtok2026-08-10
costz-ai10.77x price · z-ai/glm-5.2: cache_read_price_per_mtok $0.01/Mtok to $0.14/Mtok2026-08-10
truncationnovita-91% ctx · novita/meta-llama/llama-3.3-70b-instruct: context_tokens cut 131,072 to 12,2882026-08-28
costxai10.00x price · xai/grok-code-fast-1-0825: cache_read_price_per_mtok $0.02/Mtok to $0.20/Mtok +2 aliases2026-08-12
capabilityarcee-ailost frequency_penalty, logit_bias, logprobs, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, top_logprobs · arcee-ai/trinity-large-thinking: capabilities lost frequency_penalty, logit_bias, logprobs, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, top_logprobs inferred2026-08-31
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
gov-east-1/anthropic.claude-3-haiku-20240307gov-east-1T-0dcritical
gov-west-1/anthropic.claude-3-haiku-20240307gov-west-1T-0dcritical
amazon/gov.anthropic.claude-3-haiku-20240307amazonT-0dcritical
amazon/nova-sonicamazonT-4dcritical
amazon/nova-premieramazonT-4dcritical
openai/sora-2openaiT-14dcritical
openai/sora-2-2025-10-06openaiT-14dcritical
openai/sora-2-2025-12-08openaiT-14dcritical
openai/sora-2-proopenaiT-14dcritical
openai/sora-2-pro-2025-10-06openaiT-14dcritical
Earliest announced date across sources. Where catalogs disagree we show the soonest — erring early is the safe direction.

Full calendar →