isitdeprecated.com
collectors 5/5 ok last sync state ok models 2,476 events 6,924

AI API changes: September 2026

195 changes shipped without an announcement, and 51 that came with a published date. Compiled automatically from provider catalogs and endpoints; every figure below links to the model it came from.

44

capacity cuts

context or output shrank

115

price changes

same call, different bill

11

capabilities lost

51

announced

deprecations with a date

Unannounced, biggest first

ImpactProvider What changedDetected
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
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
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
costgryphe10.00x price · gryphe/mythomax-l2-13b: output_price_per_mtok $0.06/Mtok to $0.60/Mtok2026-09-01
costopenrouter9.23x price · openrouter/mistralai/mixtral-8x22b-instruct: output_price_per_mtok $0.65/Mtok to $6.00/Mtok2026-09-06
truncationmistralai-88% max out · mistralai/mistral-medium-3-5:batch: max_output_tokens cut 209,715 to 26,214 inferred2026-09-04
truncationvertex_ai-language-models-88% ctx · gemini-live-2.5-flash-native-audio: context_tokens cut 1,048,576 to 131,072 inferred2026-09-10
truncationz-ai-88% max out · z-ai/glm-4.6: max_output_tokens cut 131,072 to 16,384 +2 aliases2026-09-09
truncationmistralai-88% ctx · mistralai/mistral-medium-3-5:batch: context_tokens cut 262,144 to 32,768 inferred2026-09-04
truncation~z-ai-86% max out · ~z-ai/glm-latest: max_output_tokens cut 943,718 to 128,000 inferred2026-09-08
truncationqwen-86% max out · qwen/qwen3-30b-a3b-instruct-2507: max_output_tokens cut 235,929 to 32,000 +1 alias2026-09-10
truncation~z-ai-86% max out · ~z-ai/glm-flash-latest: max_output_tokens cut 943,718 to 131,072 +3 aliases inferred2026-09-09
truncationdeepseek-86% max out · deepseek/deepseek-v4-flash-0731: max_output_tokens cut 943,718 to 131,0722026-09-06
truncationmeta-llama-86% max out · meta-llama/llama-3.3-70b-instruct: max_output_tokens cut 115,200 to 16,3842026-09-03
costgryphe6.67x price · gryphe/mythomax-l2-13b: input_price_per_mtok $0.06/Mtok to $0.40/Mtok2026-09-01
truncationnvidia-82% max out · nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens cut 182,520 to 32,7682026-09-04
costopenrouter5.56x price · openrouter/qwen/qwen-2.5-coder-32b-instruct: output_price_per_mtok $0.18/Mtok to $1.00/Mtok2026-09-06
truncationopenrouter-80% ctx · openrouter/anthropic/claude-sonnet-4.5: context_tokens cut 1,000,000 to 200,0002026-09-06
truncationdeepseek-77% max out · deepseek/deepseek-chat-v3.1: max_output_tokens cut 144,900 to 32,768 +1 alias2026-09-08
costdeepseek4.23x price · deepseek/deepseek-chat-v3.1: cache_read_price_per_mtok $0.13/Mtok to $0.55/Mtok +1 alias2026-09-03
truncationnebius-76% ctx · nebius/Qwen/Qwen2.5-VL-72B-Instruct: context_tokens cut 131,072 to 32,0002026-09-06
truncationnebius-76% max out · nebius/Qwen/Qwen2.5-VL-72B-Instruct: max_output_tokens cut 131,072 to 32,0002026-09-06
truncation~z-ai-75% max out · ~z-ai/glm-latest: max_output_tokens cut 943,718 to 235,929 +1 alias inferred2026-09-04
capabilityvertex_ai-language-modelslost pdf_input, prompt_caching, response_schema, url_context · gemini-live-2.5-flash-native-audio: capabilities lost pdf_input, prompt_caching, response_schema, url_context inferred2026-09-10
truncationopenai-75% ctx · gpt-realtime-mini: context_tokens cut 128,000 to 32,0002026-09-03
costqwen3.91x price · qwen/qwen3.5-35b-a3b: input_price_per_mtok $0.08/Mtok to $0.31/Mtok2026-09-05
costopenrouter3.83x price · openrouter/qwen/qwen3-235b-a22b-thinking-2507: output_price_per_mtok $0.60/Mtok to $2.30/Mtok2026-09-06
truncationnvidia-74% ctx · nvidia/nemotron-3-super-120b-a12b: context_tokens cut 1,000,000 to 262,144 +1 alias2026-09-09
costqwen3.79x price · qwen/qwen3-14b: output_price_per_mtok $0.24/Mtok to $0.91/Mtok +1 alias2026-09-08
costz-ai3.72x price · z-ai/glm-5.2: cache_read_price_per_mtok $0.05/Mtok to $0.19/Mtok2026-09-10
costopenrouter3.67x price · openrouter/qwen/qwen-2.5-coder-32b-instruct: input_price_per_mtok $0.18/Mtok to $0.66/Mtok2026-09-06
truncationqwen-72% max out · qwen/qwen3.5-35b-a3b: max_output_tokens cut 235,929 to 65,536 +3 aliases2026-09-06
costopenrouter3.57x price · openrouter/deepseek/deepseek-chat-v3-0324: output_price_per_mtok $0.28/Mtok to $1.00/Mtok2026-09-06
costopenrouter3.51x price · openrouter/mistralai/mistral-small-3.1-24b-instruct: input_price_per_mtok $0.10/Mtok to $0.35/Mtok2026-09-06
costopenrouter3.50x price · openrouter/qwen/qwen3-235b-a22b-2507: output_price_per_mtok $0.10/Mtok to $0.35/Mtok2026-09-06
costz-ai3.45x price · z-ai/glm-5.2: output_price_per_mtok $0.88/Mtok to $3.04/Mtok2026-09-10
costz-ai3.45x price · z-ai/glm-5.2: input_price_per_mtok $0.28/Mtok to $0.97/Mtok2026-09-10
costopenrouter3.33x price · openrouter/mistralai/devstral-2512: output_price_per_mtok $0.60/Mtok to $2.00/Mtok2026-09-06
costbedrock3.20x price · eu.anthropic.claude-3-5-haiku-20241022-v1:0: input_price_per_mtok $0.25/Mtok to $0.80/Mtok2026-09-10
costbedrock3.20x price · eu.anthropic.claude-3-5-haiku-20241022-v1:0: output_price_per_mtok $1.25/Mtok to $4.00/Mtok2026-09-10
costqwen3.20x price · qwen/qwen2.5-vl-72b-instruct: input_price_per_mtok $0.25/Mtok to $0.80/Mtok +1 alias2026-09-03
costbedrock3.20x price · eu.anthropic.claude-3-5-haiku-20241022-v1:0: cache_read_price_per_mtok $0.03/Mtok to $0.08/Mtok2026-09-10
costopenrouter3.18x price · openrouter/deepseek/deepseek-chat: output_price_per_mtok $0.28/Mtok to $0.89/Mtok2026-09-06
truncationopenrouter-68% max out · openrouter/anthropic/claude-haiku-4.5: max_output_tokens cut 200,000 to 64,0002026-09-06
costopenrouter3.08x price · openrouter/mistralai/mixtral-8x22b-instruct: input_price_per_mtok $0.65/Mtok to $2.00/Mtok2026-09-06
capabilitynvidialost logprobs, structured_outputs, top_logprobs · nvidia/nemotron-3-super-120b-a12b: capabilities lost logprobs, structured_outputs, top_logprobs2026-09-09
truncation~deepseek-67% max out · ~deepseek/deepseek-v4-flash-latest: max_output_tokens cut 393,216 to 131,072 +1 alias inferred2026-09-04
costdeepseek2.80x price · deepseek/deepseek-v4-flash-0731: output_price_per_mtok $0.10/Mtok to $0.28/Mtok2026-09-07
costdeepseek2.80x price · deepseek/deepseek-v4-flash-0731: cache_read_price_per_mtok $0.0100/Mtok to $0.03/Mtok2026-09-07
costdeepseek2.80x price · deepseek/deepseek-v4-flash-0731: input_price_per_mtok $0.05/Mtok to $0.14/Mtok2026-09-07
costopenrouter2.67x price · openrouter/mistralai/devstral-2512: input_price_per_mtok $0.15/Mtok to $0.40/Mtok2026-09-06
costdeepseek2.63x price · deepseek/deepseek-v4-pro-0813: cache_read_price_per_mtok $0.02/Mtok to $0.06/Mtok2026-09-08
costqwen2.44x price · qwen/qwen3-235b-a22b-2507: input_price_per_mtok $0.09/Mtok to $0.22/Mtok2026-09-09
truncation~deepseek-58% max out · ~deepseek/deepseek-v4-flash-latest: max_output_tokens cut 943,718 to 393,216 inferred2026-09-07
costfireworks_ai2.36x price · fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731: output_price_per_mtok $0.28/Mtok to $0.66/Mtok +1 alias2026-09-01
truncationmoonshotai-57% max out · moonshotai/kimi-k2-thinking: max_output_tokens cut 235,929 to 100,352 +1 alias2026-09-10
cost~z-ai2.34x price · ~z-ai/glm-latest: cache_read_price_per_mtok $0.10/Mtok to $0.23/Mtok2026-09-06
costopenrouter2.29x price · openrouter/deepseek/deepseek-chat: input_price_per_mtok $0.14/Mtok to $0.32/Mtok2026-09-06
costdeepseek2.20x price · deepseek/deepseek-chat-v3.1: input_price_per_mtok $0.25/Mtok to $0.55/Mtok +1 alias2026-09-03
costopenrouter2.09x price · openrouter/qwen/qwen3-235b-a22b-thinking-2507: input_price_per_mtok $0.11/Mtok to $0.23/Mtok2026-09-06
costbedrock_converse2.05x price · qwen.qwen3-coder-480b-a35b-v1:0: input_price_per_mtok $0.22/Mtok to $0.45/Mtok2026-09-06
capabilityz-ailost logit_bias, min_p · z-ai/glm-5: capabilities lost logit_bias, min_p2026-09-10
truncationqwen-50% max out · qwen/qwen3.6-27b: max_output_tokens cut 262,144 to 131,072 +5 aliases2026-09-09
truncationqwen-50% max out · qwen/qwen3-14b: max_output_tokens cut 16,384 to 8,192 +3 aliases2026-09-08
truncationwatsonx-50% max out · watsonx/bigscience/mt0-xxl-13b: max_output_tokens cut 8,192 to 4,096 inferred2026-09-06
truncationwatsonx-50% ctx · watsonx/bigscience/mt0-xxl-13b: context_tokens cut 8,192 to 4,096 inferred2026-09-06
capabilitymeta-llamalost logprobs, top_logprobs · meta-llama/llama-3.1-70b-instruct: capabilities lost logprobs, top_logprobs2026-09-04
capabilityxiaomilost logprobs, top_logprobs · xiaomi/mimo-v2.5: capabilities lost logprobs, top_logprobs2026-09-02
truncationz-ai-50% max out · z-ai/glm-5.2: max_output_tokens cut 262,144 to 131,072 +7 aliases2026-09-02
capabilityqwenlost logprobs, top_logprobs · qwen/qwen3-32b: capabilities lost logprobs, top_logprobs2026-09-01
truncationgryphe-50% max out · gryphe/mythomax-l2-13b: max_output_tokens cut 7,372 to 3,6862026-09-01
costz-ai2.00x price · z-ai/glm-5.3-flash: cache_read_price_per_mtok $0.01/Mtok to $0.03/Mtok2026-09-10
costz-ai2.00x price · z-ai/glm-5.3-flash: output_price_per_mtok $0.25/Mtok to $0.50/Mtok2026-09-10
costz-ai2.00x price · z-ai/glm-5.3-flash: input_price_per_mtok $0.07/Mtok to $0.15/Mtok2026-09-10
costdeepseek2.00x price · deepseek/deepseek-v4-flash-vision-exp: cache_read_price_per_mtok $0.0070/Mtok to $0.01/Mtok +11 aliases2026-09-08
costdeepseek2.00x price · deepseek/deepseek-v4-flash-vision-exp: output_price_per_mtok $0.66/Mtok to $1.32/Mtok +11 aliases2026-09-08
costdeepseek2.00x price · deepseek/deepseek-v4-flash-vision-exp: input_price_per_mtok $0.22/Mtok to $0.44/Mtok +11 aliases2026-09-08
costqwen2.00x price · qwen/qwen3.6-35b-a3b: input_price_per_mtok $0.05/Mtok to $0.10/Mtok2026-09-03
costgoogle2.00x price · google/gemini-3.7-flash:batch: input_price_per_mtok $0.19/Mtok to $0.38/Mtok2026-09-02
costgoogle2.00x price · google/gemini-3.7-flash:batch: cache_read_price_per_mtok $0.02/Mtok to $0.04/Mtok2026-09-02
costgoogle2.00x price · google/gemini-3.7-flash:batch: output_price_per_mtok $0.94/Mtok to $1.88/Mtok2026-09-02
costqwen2.00x price · qwen/qwen3.8-2.4t-a95b:batch: cache_read_price_per_mtok $0.25/Mtok to $0.50/Mtok +1 alias2026-09-01
truncationwatsonx-49% max out · watsonx/mistralai/mistral-small-3-1-24b-instruct-2503: max_output_tokens cut 32,000 to 16,384 inferred2026-09-06
costdeepseek1.93x price · deepseek/deepseek-v4-pro-0813: cache_read_price_per_mtok $0.02/Mtok to $0.04/Mtok +2 aliases2026-09-07
costdeepseek1.93x price · deepseek/deepseek-v4-pro-0813: output_price_per_mtok $1.74/Mtok to $3.36/Mtok +2 aliases2026-09-07
costdeepseek1.93x price · deepseek/deepseek-v4-pro-0813: input_price_per_mtok $0.58/Mtok to $1.12/Mtok +2 aliases2026-09-07
costnebius1.92x price · nebius/Qwen/Qwen2.5-VL-72B-Instruct: input_price_per_mtok $0.13/Mtok to $0.25/Mtok2026-09-06
costdeepseek1.90x price · deepseek/deepseek-v4-pro-0813: cache_read_price_per_mtok $0.02/Mtok to $0.03/Mtok2026-09-10
costqwen1.90x price · qwen/qwen3-14b: input_price_per_mtok $0.12/Mtok to $0.23/Mtok +1 alias2026-09-08
costnebius1.88x price · nebius/Qwen/Qwen2.5-VL-72B-Instruct: output_price_per_mtok $0.40/Mtok to $0.75/Mtok2026-09-06
costnvidia1.88x price · nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.10/Mtok to $0.19/Mtok2026-09-02
costqwen1.87x price · qwen/qwen3-30b-a3b-instruct-2507: input_price_per_mtok $0.05/Mtok to $0.09/Mtok +1 alias2026-09-10
costz-ai1.86x price · z-ai/glm-5.3: cache_read_price_per_mtok $0.14/Mtok to $0.26/Mtok2026-09-07
costopenrouter1.85x price · openrouter/mistralai/mistral-small-3.1-24b-instruct: output_price_per_mtok $0.30/Mtok to $0.56/Mtok2026-09-06
costdeepseek1.81x price · deepseek/deepseek-v4-pro-0813: input_price_per_mtok $0.58/Mtok to $1.05/Mtok +1 alias2026-09-10
costdeepseek1.81x price · deepseek/deepseek-v4-pro-0813: output_price_per_mtok $1.74/Mtok to $3.15/Mtok +1 alias2026-09-10
cost~z-ai1.79x price · ~z-ai/glm-latest: cache_read_price_per_mtok $0.10/Mtok to $0.18/Mtok2026-09-03
costopenrouter1.79x price · openrouter/deepseek/deepseek-chat-v3-0324: input_price_per_mtok $0.14/Mtok to $0.25/Mtok2026-09-06
cost~deepseek1.78x price · ~deepseek/deepseek-v4-flash-latest: output_price_per_mtok $0.09/Mtok to $0.16/Mtok2026-09-07
costdeepseek1.74x price · deepseek/deepseek-chat-v3.1: output_price_per_mtok $0.95/Mtok to $1.65/Mtok +1 alias2026-09-03
costdeepseek1.69x price · deepseek/deepseek-v4-pro-0813: input_price_per_mtok $0.66/Mtok to $1.12/Mtok +3 aliases2026-09-04
costdeepseek1.69x price · deepseek/deepseek-v4-pro-0813: output_price_per_mtok $1.98/Mtok to $3.35/Mtok +3 aliases2026-09-04
costdeepseek1.69x price · deepseek/deepseek-v4-pro-0813: cache_read_price_per_mtok $0.02/Mtok to $0.04/Mtok +3 aliases2026-09-04
costibm-granite1.67x price · ibm-granite/granite-4.2-8b: output_price_per_mtok $0.15/Mtok to $0.25/Mtok2026-09-09
costnebius1.67x price · nebius/google/gemma-3-27b-it: input_price_per_mtok $0.06/Mtok to $0.10/Mtok2026-09-06
costqwen1.67x price · qwen/qwen3.5-35b-a3b: output_price_per_mtok $0.75/Mtok to $1.25/Mtok2026-09-05
costdeepseek1.65x price · deepseek/deepseek-v4-pro: input_price_per_mtok $0.63/Mtok to $1.04/Mtok2026-09-07
costdeepseek1.65x price · deepseek/deepseek-v4-pro: output_price_per_mtok $1.25/Mtok to $2.07/Mtok2026-09-07
costdeepseek1.65x price · deepseek/deepseek-v4-pro: cache_read_price_per_mtok $0.05/Mtok to $0.09/Mtok2026-09-07
cost~deepseek1.60x price · ~deepseek/deepseek-v4-flash-latest: output_price_per_mtok $0.10/Mtok to $0.16/Mtok2026-09-02
costtencent1.60x price · tencent/hy3: cache_read_price_per_mtok $0.02/Mtok to $0.03/Mtok +14 aliases2026-09-10
costtencent1.60x price · tencent/hy3: output_price_per_mtok $0.33/Mtok to $0.53/Mtok +14 aliases2026-09-10
costtencent1.60x price · tencent/hy3: input_price_per_mtok $0.08/Mtok to $0.13/Mtok +14 aliases2026-09-10
costqwen1.60x price · qwen/qwen3-235b-a22b-2507: output_price_per_mtok $0.55/Mtok to $0.88/Mtok2026-09-09
costopenrouter1.60x price · openrouter/nvidia/nemotron-3.5-lightning: input_price_per_mtok $0.05/Mtok to $0.08/Mtok2026-09-06
costdeepseek1.59x price · deepseek/deepseek-v4-pro-0813: input_price_per_mtok $0.66/Mtok to $1.05/Mtok2026-09-08
costdeepseek1.59x price · deepseek/deepseek-v4-pro-0813: output_price_per_mtok $1.98/Mtok to $3.15/Mtok2026-09-08
costdeepseek1.59x price · deepseek/deepseek-v4-pro-0813: cache_read_price_per_mtok $0.02/Mtok to $0.03/Mtok2026-09-08
costdeepseek1.57x price · deepseek/deepseek-v4-pro: cache_read_price_per_mtok $0.09/Mtok to $0.14/Mtok2026-09-01
costqwen1.57x price · qwen/qwen3-235b-a22b-2507: output_price_per_mtok $0.35/Mtok to $0.55/Mtok +1 alias2026-09-05
costfireworks_ai1.57x price · fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731: input_price_per_mtok $0.14/Mtok to $0.22/Mtok +1 alias2026-09-01
costnvidia1.56x price · nvidia/nemotron-3-ultra-550b-a55b: cache_read_price_per_mtok $0.12/Mtok to $0.19/Mtok2026-09-04
costqwen1.55x price · qwen/qwen3-30b-a3b-instruct-2507: output_price_per_mtok $0.19/Mtok to $0.30/Mtok +1 alias2026-09-10
costdeepseek1.55x price · deepseek/deepseek-v4-pro: output_price_per_mtok $2.06/Mtok to $3.20/Mtok2026-09-01
costdeepseek1.55x price · deepseek/deepseek-v4-pro: input_price_per_mtok $1.03/Mtok to $1.60/Mtok2026-09-01
costopenrouter1.50x price · openrouter/openai/gpt-oss-20b: input_price_per_mtok $0.02/Mtok to $0.03/Mtok2026-09-06
costmistral1.50x price · mistral/magistral-medium-latest: output_price_per_mtok $5.00/Mtok to $7.50/Mtok2026-09-03
costopenai1.50x price · gpt-realtime-2: output_price_per_mtok $16.00/Mtok to $24.00/Mtok2026-09-03
costnebius1.50x price · nebius/google/gemma-3-27b-it: output_price_per_mtok $0.20/Mtok to $0.30/Mtok2026-09-06
costqwen1.50x price · qwen/qwen3.5-397b-a17b: output_price_per_mtok $2.34/Mtok to $3.50/Mtok +1 alias2026-09-08
cost~deepseek1.44x price · ~deepseek/deepseek-v4-flash-latest: cache_read_price_per_mtok $0.0090/Mtok to $0.01/Mtok2026-09-07
costnvidia1.42x price · nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $2.20/Mtok to $3.12/Mtok2026-09-02
costqwen1.41x price · qwen/qwen3.5-397b-a17b: input_price_per_mtok $0.39/Mtok to $0.55/Mtok +1 alias2026-09-08
costminimax1.38x price · minimax/minimax-m1: input_price_per_mtok $0.40/Mtok to $0.55/Mtok +1 alias2026-09-09
costz-ai1.38x price · z-ai/glm-4.6: cache_read_price_per_mtok $0.08/Mtok to $0.11/Mtok +1 alias2026-09-08
costopenrouter1.38x price · openrouter/z-ai/glm-4.6: input_price_per_mtok $0.40/Mtok to $0.55/Mtok2026-09-06
costopenrouter1.36x price · openrouter/qwen/qwen3-coder: input_price_per_mtok $0.22/Mtok to $0.30/Mtok2026-09-06
costopenrouter1.35x price · openrouter/deepseek/deepseek-v3.2-exp: input_price_per_mtok $0.20/Mtok to $0.27/Mtok2026-09-06
costqwen1.33x price · qwen/qwen2.5-vl-72b-instruct: output_price_per_mtok $0.75/Mtok to $1.00/Mtok +1 alias2026-09-03
costnvidia1.30x price · nvidia/nemotron-3-ultra-550b-a55b: output_price_per_mtok $2.40/Mtok to $3.12/Mtok2026-09-04
cost~deepseek1.30x price · ~deepseek/deepseek-v4-flash-latest: cache_read_price_per_mtok $0.0100/Mtok to $0.01/Mtok2026-09-02
costopenrouter1.30x price · openrouter/openai/gpt-oss-20b: output_price_per_mtok $0.10/Mtok to $0.13/Mtok2026-09-06
costqwen1.29x price · qwen/qwen3.6-35b-a3b: output_price_per_mtok $0.70/Mtok to $0.90/Mtok2026-09-03
costz-ai1.28x price · z-ai/glm-4.6: input_price_per_mtok $0.43/Mtok to $0.55/Mtok +1 alias2026-09-08
costopenrouter1.27x price · openrouter/deepseek/deepseek-r1: input_price_per_mtok $0.55/Mtok to $0.70/Mtok2026-09-06
costdeepseek1.27x price · deepseek/deepseek-v4-flash: input_price_per_mtok $0.07/Mtok to $0.09/Mtok2026-09-10
costdeepseek1.27x price · deepseek/deepseek-v4-flash: output_price_per_mtok $0.14/Mtok to $0.18/Mtok2026-09-10
costdeepseek1.27x price · deepseek/deepseek-v4-flash: cache_read_price_per_mtok $0.01/Mtok to $0.02/Mtok2026-09-10
costz-ai1.26x price · z-ai/glm-4.6: output_price_per_mtok $1.75/Mtok to $2.20/Mtok +1 alias2026-09-08
costopenrouter1.26x price · openrouter/z-ai/glm-4.6: output_price_per_mtok $1.75/Mtok to $2.20/Mtok2026-09-06
truncationqwen-20% max out · qwen/qwen3.5-122b-a10b: max_output_tokens cut 81,920 to 65,5362026-09-10
truncation~z-ai-20% ctx · ~z-ai/glm-latest: context_tokens cut 1,310,720 to 1,048,576 inferred2026-09-09
truncationz-ai-20% ctx · z-ai/glm-5.3: context_tokens cut 1,310,720 to 1,048,5762026-09-09
truncationnebius-14% max out · nebius/google/gemma-3-27b-it: max_output_tokens cut 128,000 to 110,0002026-09-06
truncationnebius-14% ctx · nebius/google/gemma-3-27b-it: context_tokens cut 128,000 to 110,0002026-09-06
truncationz-ai-2% max out · z-ai/glm-5.1: max_output_tokens cut 131,072 to 128,000 +7 aliases2026-09-10
truncationdeepseek-2% max out · deepseek/deepseek-v4-flash-0731: max_output_tokens cut 393,216 to 384,000 +7 aliases2026-09-10
truncationdeepseek-2% max out · deepseek/deepseek-chat: max_output_tokens cut 16,384 to 16,0002026-09-10
truncationz-ai-1% ctx · z-ai/glm-4.7-flash: context_tokens cut 202,752 to 200,0002026-09-10
capabilityazurelost max_reasoning_effort · azure/gpt-6-astra: capabilities lost max_reasoning_effort +1 alias2026-09-09
capabilitynex-agilost frequency_penalty · nex-agi/nex-n2-pro: capabilities lost frequency_penalty inferred2026-09-07
capabilitynovitalost vision · novita/openai/gpt-oss-120b: capabilities lost vision +1 alias2026-09-06
capabilitybedrock_converselost native_structured_output · anthropic.claude-fable-5-1: capabilities lost native_structured_output +15 aliases2026-09-02
capability~anthropiclost tool_choice · ~anthropic/claude-fable-latest: capabilities lost tool_choice inferred2026-09-01
availabilitynex-aginex-agi/nex-n2-pro is no longer listed by this source — calls to it are expected to fail2026-09-08
availabilitynex-aginex-agi/nex-n2-mini is no longer listed by this source — calls to it are expected to fail2026-09-08
availabilitygooglegemini-flash-latest-high-res-exp is no longer listed by this source — calls to it are expected to fail2026-09-04
availabilitynvidianvidia/nemotron-3-ultra-550b-a55b:batch is no longer listed by this source — calls to it are expected to fail2026-09-03
availabilityanthropicclaude-2.0 is no longer listed by this source — calls to it are expected to fail inferred2026-09-01
availabilityanthropicclaude-2.1 is no longer listed by this source — calls to it are expected to fail inferred2026-09-01
availabilityanthropicanthropic/claude-opus-4.7-fast is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilityanthropicanthropic/claude-opus-4.8-fast is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilityanthropicanthropic/claude-opus-5-fast is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilitymistralaimistralai/codestral-2508:batch is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilitymistralaimistralai/mistral-large-2512:batch is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilitymistralaimistralai/mistral-small-2603:batch is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilitymistralaimistralai/ministral-8b-2512:batch is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilitymistralaimistralai/mistral-medium-3.1:batch is no longer listed by this source — calls to it are expected to fail2026-09-01
availabilityinceptioninception/mercury-2.5-preview vanished; inception/mercury-2.5 appeared with identical price and context — most likely a rename inferred2026-09-08
availabilityqwenqwen/qwen3.8-max vanished; qwen/qwen3.8-max-0902 appeared with identical price and context — most likely a rename inferred2026-09-05
availabilitygigachatgigachat/GigaChat-2-Lite vanished; gigachat/GigaChat-2 appeared with identical price and context — most likely a rename inferred2026-09-01
availabilitynousresearch[one catalog only — litellm still list it] nousresearch/hermes-4-70b is no longer listed by this source — calls to it are expected to fail inferred2026-09-09
availabilityminimax[one catalog only — litellm still list it] minimax/minimax-m3:free is no longer listed by this source — calls to it are expected to fail inferred2026-09-07
availabilityminimax[one catalog only — litellm still list it] minimax/minimax-m2.7:free is no longer listed by this source — calls to it are expected to fail inferred2026-09-07
availabilityz-ai[one catalog only — litellm still list it] z-ai/glm-5.2:free is no longer listed by this source — calls to it are expected to fail inferred2026-09-06
costopenrouteropenrouter/xiaomi/mimo-v2-flash: cache_read_price_per_mtok $0.0000/Mtok to $0.01/Mtok +1 alias2026-09-06
costopenrouteropenrouter/minimax/minimax-m2.1: cache_read_price_per_mtok $0.0000/Mtok to $0.03/Mtok2026-09-06
costopenrouteropenrouter/z-ai/glm-4.7: cache_read_price_per_mtok $0.0000/Mtok to $0.08/Mtok2026-09-06
availabilityibm-granite[one catalog only — litellm still list it] ibm-granite/granite-4.1-8b is no longer listed by this source — calls to it are expected to fail inferred2026-09-04
availabilityazure_ai[one catalog only — litellm, openrouter still list it] azure_ai/deepseek-v4-flash-0731 is no longer listed by this source — calls to it are expected to fail inferred2026-09-03
availabilityanthropic[one catalog only — litellm still list it] claude-3-sonnet-20240229 is no longer listed by this source — calls to it are expected to fail inferred2026-09-01
availabilitygoogle[one catalog only — litellm still list it] gemini-robotics-er-1.6-preview is no longer listed by this source — calls to it are expected to fail inferred2026-09-01

Announced this period

ImpactProvider What changedDetected
availabilityscalewayscaleway/mistralai/pixtral-12b-2409: retires 2026-10-01 (in 21 days) +1 alias2026-09-10
availabilityscalewayscaleway/mistralai/pixtral-12b-2409: deprecation announced for 2026-10-01 — in 21 days +1 alias2026-09-10
availabilitybedrock_converseus-gov.anthropic.claude-3-haiku-20240307-v1:0: retires 2026-09-10 (in 1 days) inferred2026-09-09
availabilityazureazure/gpt-realtime-2: retires 2026-08-31 (6 days ago) inferred2026-09-06
availabilitydatabricksdatabricks/databricks-gemini-2-5-flash: deprecation announced for 2026-10-02 — in 26 days inferred2026-09-06
availabilitydatabricksdatabricks/databricks-gemini-2-5-flash: retires 2026-10-02 (in 26 days) inferred2026-09-06
availabilityz-aiz-ai/glm-4.7-flash: retirement announced for 2026-09-10 — in 6 days2026-09-04
availabilityz-aiz-ai/glm-4.7-flash: retires 2026-09-10 (in 6 days)2026-09-04
availabilityazure_aiazure_ai/MAI-Image-2.5-Flash: retires 2026-10-01 (in 28 days) +1 alias inferred2026-09-03
availabilityazure_aiazure_ai/MAI-Image-2.5-Flash: deprecation announced for 2026-10-01 — in 28 days +1 alias inferred2026-09-03
availabilitycerebrascerebras/zai-glm-4.7: retires 2026-08-17 (15 days ago) inferred2026-09-01
availabilitybedrockamazon.nova-sonic-v1:0: retires 2026-09-14 (in 13 days) inferred2026-09-01
availabilitycerebrascerebras/zai-glm-4.7: deprecation announced for 2026-08-17 (date already passed) inferred2026-09-01
availabilitynex-aginex-agi/nex-n2-mini: retires 2026-09-08 (in 7 days) +1 alias inferred2026-09-01
availabilitynex-aginex-agi/nex-n2-mini: retirement announced for 2026-09-08 — in 7 days +1 alias inferred2026-09-01
availabilityazure_aiazure_ai/gpt-chat-latest: retires 2026-12-02 (in 83 days)2026-09-10
availabilityazure_aiazure_ai/codex-mini: retires 2026-11-15 (in 66 days) inferred2026-09-10
availabilitydatabricksdatabricks/databricks-claude-sonnet-4: retires 2026-10-09 (in 33 days) inferred2026-09-06
availabilitydatabricksdatabricks/databricks-claude-sonnet-4: deprecation announced for 2026-10-09 — in 33 days inferred2026-09-06
availabilityazure_aiazure_ai/kimi-k2.7-code: retires 2026-10-03 (in 30 days)2026-09-03
availabilityazure_aiazure_ai/claude-opus-4-7: retires 2027-04-06 (in 228 days) +2 aliases2026-09-10
availabilityazure_aiazure_ai/model_router: deprecation announced for 2027-05-20 — in 252 days2026-09-10
availabilityazureazure/eu/gpt-5.5-2026-04-23: retires 2027-10-26 (in 411 days) +5 aliases2026-09-10
availabilityazureazure/eu/gpt-5.5-2026-04-23: deprecation announced for 2027-10-26 — in 411 days +5 aliases2026-09-10
availabilityazure_aiazure_ai/model-router: retires 2027-05-20 (in 252 days) +1 alias2026-09-10
availabilityazure_aiazure_ai/Cohere-parse-v5: retires 2026-12-15 (in 100 days) +1 alias2026-09-10
availabilityz-aiz-ai/glm-5.3-flash: retirement announced for 2098-12-31 — in 26410 days2026-09-10
availabilityazure_aiazure_ai/claude-fable-5-1: retires 2027-12-05 (in 455 days) +1 alias2026-09-06
availabilityazureazure/gpt-4.1-nano-2025-04-14: deprecation announced for 2027-04-14 — in 229 days +2 aliases2026-09-06
availabilityanthropicclaude-fable-5-1: retires 2027-09-01 (in 365 days) +1 alias2026-09-06
availabilityvertex_ai-anthropic_modelsvertex_ai/claude-fable-5-1: retires 2027-03-01 (in 176 days) +1 alias2026-09-06
availabilityazure_aiazure_ai/claude-fable-5-1: deprecation announced for 2027-12-05 — in 455 days +1 alias2026-09-06
availabilityvertex_ai-anthropic_modelsvertex_ai/claude-fable-5-1: deprecation announced for 2027-03-01 — in 176 days +1 alias2026-09-06
availabilityazureazure/eu/gpt-4o-2024-08-06: retires 2027-04-14 (in 245 days) +23 aliases2026-09-06
availabilityazureazure/gpt-realtime-2.1-mini: retires 2027-06-25 (in 292 days) +1 alias2026-09-06
availabilityazure_aiazure_ai/DeepSeek-V4-Flash-0731: retires 2026-12-03 (in 91 days) +1 alias2026-09-03
availabilityz-aiz-ai/glm-4.5v: retirement announced for 2026-12-31 — in 120 days +3 aliases2026-09-02
availability~z-ai~z-ai/glm-flash-latest: retires 2098-12-31 (in 26418 days) +1 alias2026-09-02
availabilityopenaigpt-4o-mini-transcribe: deprecation announced for 2027-02-26 — in 178 days +3 aliases2026-09-01
availabilityazure_aiazure_ai/claude-opus-5: deprecation announced for 2027-07-08 — in 310 days2026-09-01
availabilityazure_aiazure_ai/claude-opus-4-8: retires 2027-09-01 (in 365 days)2026-09-01
availabilitybedrock_converseanthropic.claude-opus-4-1-20250805-v1:0: retires 2027-01-08 (in 149 days) +2 aliases2026-09-01
availabilityazure_aiazure_ai/claude-sonnet-5: deprecation announced for 2027-06-30 — in 302 days2026-09-01
availabilitybedrock_converseanthropic.claude-opus-4-1-20250805-v1:0: deprecation announced for 2027-01-08 — in 149 days +2 aliases2026-09-01
availabilityvertex_ai-language-modelsgemini-live-2.5-flash-native-audio: retires 2026-12-13 (in 103 days)2026-09-01
availabilityvertex_ai-embedding-modelstext-embedding-004: deprecation announced for 2027-04-01 — in 212 days2026-09-01
availabilityazure_aiazure_ai/claude-opus-5: retires 2027-07-08 (in 310 days)2026-09-01
availabilityvertex_ai-language-modelsgemini-live-2.5-flash-native-audio: deprecation announced for 2026-12-13 — in 103 days2026-09-01
availabilityazure_aiazure_ai/claude-sonnet-5: retires 2027-06-30 (in 302 days)2026-09-01
availabilityvertex_ai-embedding-modelsmultimodalembedding@001: retires 2027-04-01 (in 223 days) +3 aliases2026-09-01
availabilityazure_aiazure_ai/claude-opus-4-8: deprecation announced for 2027-09-01 — in 365 days2026-09-01

Who changed the most

ProviderUnannounced changes
deepseek35
openrouter29
qwen24
z-ai17
nvidia8
nebius8
mistralai7
~z-ai6
~deepseek6
anthropic6
google5
watsonx4

← August 2026  ·  All reports