isitdeprecated.com
collectors 5/5 ok last sync state ok models 1,987 events 1,226

Unannounced changes to AI APIs

Price moves, context-window cuts, removed capabilities and vanished models — grouped so one upstream change is one row, and ranked by how big the change is rather than when we spotted it.

ImpactProvider What changedDetected
truncationfireworks_ai-88% max out · fireworks_ai/accounts/fireworks/models/kimi-k2p5: max_output_tokens cut 262,144 to 32,768 +9 aliases inferred2026-07-31
costdeepseek6.43x price · deepseek/deepseek-v4-flash-0731: cache_read_price_per_mtok $0.0028/Mtok to $0.02/Mtok2026-08-01
truncationdeepseek-83% max out · deepseek/deepseek-v4-flash-0731: max_output_tokens cut 384,000 to 65,536 inferred2026-08-01
truncationfireworks_ai-75% max out · fireworks_ai/accounts/fireworks/models/gpt-oss-120b: max_output_tokens cut 131,072 to 32,768 +1 alias2026-06-18
costcohere_chat4.00x price · command-r7b-12-2024: output_price_per_mtok $0.04/Mtok to $0.15/Mtok2026-06-18
truncationazure-74% ctx · azure/gpt-5.4-mini-2026-03-17: context_tokens cut 1,050,000 to 272,000 +3 aliases2026-07-30
truncationopenai-74% ctx · gpt-5.4-mini-2026-03-17: context_tokens cut 1,050,000 to 272,000 +3 aliases2026-07-30
costmistral3.75x price · mistral/mistral-medium-latest: input_price_per_mtok $0.40/Mtok to $1.50/Mtok2026-06-26
costmistral3.75x price · mistral/mistral-medium-latest: output_price_per_mtok $2.00/Mtok to $7.50/Mtok2026-06-26
capabilitygeminilost code_execution, file_search, service_tier · gemini/gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search, service_tier +1 alias2026-06-27
capabilityvertex_ai-language-modelslost code_execution, file_search, service_tier · gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search, service_tier +2 aliases2026-06-27
truncationopenai-53% max out · gpt-5-pro-2025-10-06: max_output_tokens cut 272,000 to 128,000 +1 alias2026-06-26
costsambanova2.00x price · sambanova/MiniMax-M2.7: output_price_per_mtok $1.20/Mtok to $2.40/Mtok2026-06-26
costsambanova2.00x price · sambanova/MiniMax-M2.7: input_price_per_mtok $0.30/Mtok to $0.60/Mtok2026-06-26
capabilityvertex_ai-language-modelslost code_execution, file_search · vertex_ai/gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search2026-06-27
capabilityopenrouterlost code_execution, file_search · openrouter/google/gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search +1 alias2026-06-27
costnvidia2.00x price · nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.10/Mtok to $0.20/Mtok2026-08-01
costfireworks_ai1.86x price · fireworks_ai/accounts/fireworks/models/glm-5p2: cache_read_price_per_mtok $0.14/Mtok to $0.26/Mtok +1 alias2026-07-20
costnvidia1.64x price · nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $2.20/Mtok to $3.60/Mtok2026-08-01
truncationfireworks_ai-35% max out · fireworks_ai/accounts/fireworks/models/glm-5p1: max_output_tokens cut 202,800 to 131,072 +1 alias inferred2026-06-18
costfireworks_ai1.50x price · fireworks_ai/accounts/fireworks/models/gpt-oss-20b: output_price_per_mtok $0.20/Mtok to $0.30/Mtok2026-06-18
truncationazure_ai-32% ctx · azure_ai/gpt-5.4-mini-2026-03-17: context_tokens cut 400,000 to 272,000 +3 aliases2026-07-30
costfireworks_ai1.40x price · fireworks_ai/accounts/fireworks/models/gpt-oss-20b: input_price_per_mtok $0.05/Mtok to $0.07/Mtok2026-06-18
truncationsambanova-4% ctx · sambanova/MiniMax-M2.7: context_tokens cut 204,800 to 196,6082026-06-26
truncationz-ai-2% max out · z-ai/glm-5.2: max_output_tokens cut 131,072 to 128,0002026-08-01
capabilityperplexitylost preset · perplexity/preset/advanced-deep-research: capabilities lost preset +3 aliases inferred2026-06-27
costopenrouteropenrouter/xiaomi/mimo-v2-flash: cache_read_price_per_mtok $0.0000/Mtok to $0.01/Mtok2026-05-21
availabilityfireworks_aifireworks_ai/accounts/fireworks/models/whisper-v3-turbo is no longer listed by this source — calls to it are expected to fail2026-06-23
availabilityfireworks_aifireworks_ai/accounts/fireworks/models/whisper-v3 is no longer listed by this source — calls to it are expected to fail2026-06-23
availabilityanthropicclaude-instant-1.0 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropicclaude-instant-1.2 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropicclaude-1.0 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropicclaude-instant-1.1 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityazuregpt-4o version 2024-05-13 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropicclaude-1.1 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropicclaude-1.2 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropicclaude-1.3 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-sonnet-4-20250514 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-3-7-sonnet-20250219 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityazure[one catalog only — docs, litellm, openrouter still list it] gpt-4o-mini is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityazure[one catalog only — docs, litellm, openrouter still list it] o4-mini is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-3-sonnet-20240229 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs still list it] claude-2.1 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityazure[one catalog only — docs, litellm, openrouter still list it] gpt-4o is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-3-5-sonnet-20241022 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-3-opus-20240229 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityazure[one catalog only — docs, litellm, openrouter still list it] gpt-4.1-nano is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityazure[one catalog only — docs, litellm, openrouter still list it] gpt-4.1 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-3-5-sonnet-20240620 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-3-haiku-20240307 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityazure[one catalog only — docs, litellm, openrouter still list it] gpt-4.1-mini is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-3-5-haiku-20241022 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs still list it] claude-2.0 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
availabilityanthropic[one catalog only — docs, litellm still list it] claude-opus-4-20250514 is no longer listed by this source — calls to it are expected to fail inferred2026-08-01
54 changes · dashed chip = inferred by a heuristic, not observed directly

Announced deprecations

Changes that came with a published date. Separated out because they are a different problem: you were told.

ImpactProvider What changedDetected
availabilityopenaicomputer-use-preview-2025-03-11: retires 2026-07-23 (9 days ago) +17 aliases inferred2026-08-01
availabilityopenaigpt-5.2-chat-latest: retires 2026-08-10 (in 9 days) +3 aliases2026-08-01
availabilityanthropicclaude-opus-4-1-20250805: retires 2026-08-05 (in 4 days) inferred2026-08-01
availabilityopenaift-babbage-002: retires 2026-10-23 (in 83 days) +27 aliases inferred2026-08-01
availabilityopenaibabbage-002: retires 2026-09-28 (in 58 days) +3 aliases inferred2026-08-01
availabilityopenaisora-2-2025-10-06: retires 2026-09-24 (in 54 days) +4 aliases inferred2026-08-01
availabilitybedrock_converseeu.anthropic.claude-haiku-4-5-20251001-v1:0: retires 2026-10-15 (in 75 days)2026-08-01
availabilityopenaigpt-5-2025-08-07: retires 2026-12-11 (in 132 days) +5 aliases inferred2026-08-01
availabilityopenaichatgpt-image-latest: retires 2026-12-01 (in 122 days) +2 aliases inferred2026-08-01
availabilityazuregpt-4o-mini: retires 2027-10-01 (in 426 days) +1 alias inferred2026-08-01
availabilityopenaiv1/prompts: retires 2026-11-30 (in 121 days) inferred2026-08-01
availabilityopenaigpt-4o-audio: retires 2027-01-20 (in 172 days) +8 aliases inferred2026-08-01
availabilityazuregpt-4.1-mini: retires 2027-10-14 (in 439 days) +1 alias inferred2026-08-01
availabilityazureazure/gpt-4.1-2025-04-14: retires 2026-11-04 (in 95 days) +5 aliases2026-08-01
availabilityz-aiz-ai/glm-4.5: retires 2026-12-31 (in 152 days)2026-08-01
availabilityz-aiz-ai/glm-5-turbo: retires 2098-12-31 (in 26450 days) +1 alias2026-08-01