AI API changes: August 2026
160 changes shipped without an announcement, and 95 that came with a published date. Compiled automatically from provider catalogs and endpoints; every figure below links to the model it came from.
65
capacity cuts
context or output shrank
0
price changes
same call, different bill
23
capabilities lost
95
announced
deprecations with a date
Unannounced, biggest first
| Impact | Provider | What changed | Detected |
|---|---|---|---|
| truncation | thedrummer | -97% max out · thedrummer/unslopnemo-12b: max_output_tokens cut 1,024,000 to 32,768 inferred | 2026-08-24 |
| truncation | openai | -97% max out · openai/gpt-4.1-nano: max_output_tokens cut 942,818 to 32,768 | 2026-08-30 |
| truncation | nvidia | -96% max out · nvidia/nemotron-3-ultra-550b-a55b: max_output_tokens cut 461,059 to 16,384 | 2026-08-28 |
| truncation | qwen | -94% max out · qwen/qwen3-next-80b-a3b-instruct: max_output_tokens cut 262,144 to 16,384 +1 alias | 2026-08-19 |
| truncation | novita | -91% ctx · novita/meta-llama/llama-3.3-70b-instruct: context_tokens cut 131,072 to 12,288 | 2026-08-28 |
| capability | arcee-ai | lost 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 inferred | 2026-08-31 |
| truncation | novita | -90% max out · novita/meta-llama/llama-3.3-70b-instruct: max_output_tokens cut 120,000 to 12,288 | 2026-08-28 |
| truncation | together_ai | -88% max out · together_ai/zai-org/GLM-5.2: max_output_tokens cut 1,048,575 to 128,000 +1 alias | 2026-08-30 |
| capability | lost frequency_penalty, logprobs, presence_penalty, repetition_penalty, stop, structured_outputs, top_k, top_logprobs · google/gemma-4-26b-a4b-it:free: capabilities lost frequency_penalty, logprobs, presence_penalty, repetition_penalty, stop, structured_outputs, top_k, top_logprobs inferred | 2026-08-20 | |
| truncation | qwen | -88% max out · qwen/qwen3-coder-30b-a3b-instruct: max_output_tokens cut 262,144 to 32,768 +2 aliases | 2026-08-13 |
| truncation | meta-llama | -87% max out · meta-llama/llama-3.3-70b-instruct: max_output_tokens cut 128,000 to 16,384 | 2026-08-04 |
| truncation | meta-llama | -84% ctx · meta-llama/llama-guard-4-12b: context_tokens cut 1,048,576 to 163,840 | 2026-08-26 |
| capability | tencent | lost frequency_penalty, presence_penalty, repetition_penalty, response_format, stop, structured_outputs · tencent/hy3-preview: capabilities lost frequency_penalty, presence_penalty, repetition_penalty, response_format, stop, structured_outputs inferred | 2026-08-03 |
| truncation | deepseek | -83% max out · deepseek/deepseek-v4-flash-0731: max_output_tokens cut 384,000 to 65,536 inferred | 2026-08-01 |
| truncation | deepseek | -80% max out · deepseek/deepseek-v3.1-terminus: max_output_tokens cut 163,840 to 32,768 | 2026-08-20 |
| truncation | qwen | -75% max out · qwen/qwen2.5-vl-72b-instruct: max_output_tokens cut 115,200 to 28,800 | 2026-08-26 |
| truncation | qwen | -75% max out · qwen/qwen3.5-122b-a10b: max_output_tokens cut 262,144 to 65,536 +8 aliases | 2026-08-23 |
| truncation | ~deepseek | -75% max out · ~deepseek/deepseek-v4-flash-latest: max_output_tokens cut 1,048,576 to 262,144 +1 alias inferred | 2026-08-23 |
| truncation | liquid | -75% max out · liquid/lfm-2.5-2.6b:free: max_output_tokens cut 32,768 to 8,192 inferred | 2026-08-14 |
| truncation | novita | -74% max out · novita/qwen/qwen2.5-7b-instruct: max_output_tokens cut 32,000 to 8,192 inferred | 2026-08-28 |
| truncation | qwen | -69% max out · qwen/qwen3.5-122b-a10b: max_output_tokens cut 262,144 to 81,920 +1 alias | 2026-08-24 |
| capability | x-ai | lost frequency_penalty, presence_penalty, stop · x-ai/grok-4.3: capabilities lost frequency_penalty, presence_penalty, stop +3 aliases | 2026-08-18 |
| capability | ~x-ai | lost frequency_penalty, presence_penalty, stop · ~x-ai/grok-latest: capabilities lost frequency_penalty, presence_penalty, stop inferred | 2026-08-18 |
| capability | anthropic | lost max_completion_tokens, response_format, structured_outputs · anthropic/claude-opus-4.1: capabilities lost max_completion_tokens, response_format, structured_outputs | 2026-08-06 |
| truncation | arcee-ai | -66% max out · arcee-ai/trinity-large-thinking: max_output_tokens cut 235,929 to 80,000 inferred | 2026-08-30 |
| truncation | novita | -62% max out · novita/moonshotai/kimi-k2-0905: max_output_tokens cut 262,144 to 100,352 +1 alias | 2026-08-28 |
| truncation | deepseek | -61% ctx · deepseek/deepseek-r1: context_tokens cut 163,840 to 64,000 | 2026-08-13 |
| truncation | novita | -60% max out · novita/deepseek/deepseek-v3-0324: max_output_tokens cut 163,840 to 65,536 inferred | 2026-08-28 |
| truncation | deepseek | -60% max out · deepseek/deepseek-v3.2: max_output_tokens cut 163,840 to 65,536 +1 alias | 2026-08-09 |
| truncation | deepseek | -59% max out · deepseek/deepseek-v4-pro-0813: max_output_tokens cut 943,717 to 384,000 | 2026-08-28 |
| truncation | novita | -59% max out · novita/qwen/qwen3-4b-fp8: max_output_tokens cut 20,000 to 8,192 inferred | 2026-08-28 |
| truncation | sao10k | -55% max out · sao10k/l3-lunaris-8b: max_output_tokens cut 16,384 to 7,372 inferred | 2026-08-25 |
| truncation | z-ai | -51% max out · z-ai/glm-5.2: max_output_tokens cut 262,144 to 128,000 | 2026-08-06 |
| capability | kwaipilot | lost logprobs, top_logprobs · kwaipilot/kat-coder-pro-v2.5: capabilities lost logprobs, top_logprobs +1 alias inferred | 2026-08-31 |
| capability | z-ai | lost logprobs, top_logprobs · z-ai/glm-4.7: capabilities lost logprobs, top_logprobs | 2026-08-31 |
| capability | xai | lost function_calling, tool_choice · xai/grok-4.20-multi-agent-0309: capabilities lost function_calling, tool_choice inferred | 2026-08-30 |
| truncation | -50% ctx · google/gemma-3-27b-it: context_tokens cut 262,144 to 131,072 | 2026-08-28 | |
| capability | qwen | lost logit_bias, min_p · qwen/qwen3-235b-a22b-thinking-2507: capabilities lost logit_bias, min_p | 2026-08-24 |
| truncation | qwen | -50% ctx · qwen/qwen3-235b-a22b-thinking-2507: context_tokens cut 262,144 to 131,072 | 2026-08-24 |
| truncation | mistral | -50% max out · mistral/codestral-2508: max_output_tokens cut 256,000 to 128,000 | 2026-08-21 |
| truncation | mistral | -50% ctx · mistral/codestral-2508: context_tokens cut 256,000 to 128,000 | 2026-08-21 |
| truncation | qwen | -50% max out · qwen/qwen3.6-27b: max_output_tokens cut 131,072 to 65,536 | 2026-08-19 |
| truncation | nvidia | -50% max out · nvidia/nemotron-3.5-lightning: max_output_tokens cut 262,144 to 131,072 | 2026-08-16 |
| truncation | xai | -50% max out · xai/grok-4.20-0309-reasoning: max_output_tokens cut 2,000,000 to 1,000,000 +3 aliases inferred | 2026-08-12 |
| truncation | xai | -50% ctx · xai/grok-4.20-0309-reasoning: context_tokens cut 2,000,000 to 1,000,000 +3 aliases inferred | 2026-08-12 |
| truncation | nvidia | -49% ctx · nvidia/nemotron-3-ultra-550b-a55b: context_tokens cut 512,288 to 262,144 | 2026-08-28 |
| truncation | mistralai | -49% ctx · mistralai/mistral-small-3.2-24b-instruct: context_tokens cut 256,000 to 131,072 | 2026-08-22 |
| truncation | liquid | -49% ctx · liquid/lfm-2.5-2.6b:free: context_tokens cut 128,000 to 65,536 inferred | 2026-08-21 |
| truncation | undi95 | -33% max out · undi95/remm-slerp-l2-13b: max_output_tokens cut 6,144 to 4,096 | 2026-08-24 |
| truncation | ~deepseek | -32% max out · ~deepseek/deepseek-v4-flash-latest: max_output_tokens cut 384,000 to 262,144 +3 aliases inferred | 2026-08-19 |
| truncation | z-ai | -30% max out · z-ai/glm-5.1: max_output_tokens cut 182,476 to 128,000 | 2026-08-30 |
| truncation | novita | -23% max out · novita/moonshotai/kimi-k2-instruct: max_output_tokens cut 131,072 to 100,352 inferred | 2026-08-28 |
| truncation | thedrummer | -20% max out · thedrummer/unslopnemo-12b: max_output_tokens cut 32,768 to 26,214 inferred | 2026-08-25 |
| truncation | mistralai | -20% max out · mistralai/mistral-small-3.1-24b-instruct: max_output_tokens cut 128,000 to 102,400 | 2026-08-25 |
| truncation | nvidia | -13% max out · nvidia/nemotron-3-nano-30b-a3b: max_output_tokens cut 262,144 to 228,000 inferred | 2026-08-10 |
| truncation | openai | -10% max out · openai/gpt-3.5-turbo-0613: max_output_tokens cut 4,096 to 3,685 +1 alias | 2026-08-25 |
| truncation | gryphe | -10% max out · gryphe/mythomax-l2-13b: max_output_tokens cut 4,096 to 3,686 | 2026-08-25 |
| truncation | deepseek | -10% max out · deepseek/deepseek-r1-distill-llama-70b: max_output_tokens cut 8,192 to 7,372 | 2026-08-25 |
| truncation | microsoft | -10% max out · microsoft/phi-4: max_output_tokens cut 16,384 to 14,745 | 2026-08-25 |
| truncation | rekaai | -10% max out · rekaai/reka-edge: max_output_tokens cut 16,384 to 14,745 inferred | 2026-08-25 |
| truncation | z-ai | -10% max out · z-ai/glm-5.1: max_output_tokens cut 202,752 to 182,476 | 2026-08-25 |
| truncation | minimax | -10% max out · minimax/minimax-01: max_output_tokens cut 1,000,192 to 900,172 inferred | 2026-08-25 |
| truncation | stepfun | -10% max out · stepfun/step-3.7-flash: max_output_tokens cut 256,000 to 230,400 inferred | 2026-08-25 |
| truncation | dots-studio | -10% max out · dots-studio/dots-3-note-preview:free: max_output_tokens cut 512,000 to 460,800 inferred | 2026-08-25 |
| truncation | z-ai | -10% max out · z-ai/glm-5.2:free: max_output_tokens cut 256,000 to 230,400 inferred | 2026-08-25 |
| truncation | ibm-granite | -10% max out · ibm-granite/granite-4.0-h-micro: max_output_tokens cut 131,000 to 117,900 | 2026-08-25 |
| truncation | deepseek | -10% max out · deepseek/deepseek-chat-v3-0324: max_output_tokens cut 163,840 to 147,456 +1 alias | 2026-08-25 |
| truncation | meta-llama | -10% max out · meta-llama/llama-3.2-1b-instruct: max_output_tokens cut 60,000 to 54,000 | 2026-08-25 |
| truncation | qwen | -10% max out · qwen/qwen2.5-vl-72b-instruct: max_output_tokens cut 128,000 to 115,200 | 2026-08-25 |
| truncation | deepseek | -10% max out · deepseek/deepseek-chat-v3.1: max_output_tokens cut 161,000 to 144,900 | 2026-08-25 |
| truncation | ~moonshotai | -7% max out · ~moonshotai/kimi-latest: max_output_tokens cut 943,718 to 877,357 | 2026-08-25 |
| truncation | ~moonshotai | -7% max out · ~moonshotai/kimi-latest: max_output_tokens cut 1,048,576 to 974,842 +1 alias | 2026-08-17 |
| truncation | nvidia | -5% ctx · nvidia/nemotron-3.5-lightning: context_tokens cut 1,048,576 to 1,000,000 | 2026-08-14 |
| truncation | nvidia | -3% max out · nvidia/nemotron-3-nano-30b-a3b: max_output_tokens cut 235,929 to 228,000 inferred | 2026-08-27 |
| truncation | -1% max out · google/gemini-3.1-flash-lite-image: max_output_tokens cut 66,000 to 65,536 | 2026-08-19 | |
| capability | bedrock_converse | lost prompt_caching · global.xai.grok-4.6: capabilities lost prompt_caching +1 alias | 2026-08-30 |
| capability | qwen | lost logit_bias · qwen/qwen-2.5-7b-instruct: capabilities lost logit_bias +1 alias | 2026-08-27 |
| capability | thinkingmachines | lost structured_outputs · thinkingmachines/inkling-small: capabilities lost structured_outputs inferred | 2026-08-23 |
| capability | gemini | lost reasoning · gemini/gemini-3.1-flash-lite-image: capabilities lost reasoning | 2026-08-23 |
| capability | vertex_ai-language-models | lost reasoning · gemini-3.1-flash-lite-image: capabilities lost reasoning; gained pdf_input, video_input +1 alias | 2026-08-23 |
| capability | minimax | lost parallel_tool_calls · minimax/minimax-m2.5: capabilities lost parallel_tool_calls | 2026-08-19 |
| capability | inclusionai | lost structured_outputs · inclusionai/ling-3.0-flash: capabilities lost structured_outputs inferred | 2026-08-19 |
| capability | openrouter | lost min_p · openrouter/free: capabilities lost min_p | 2026-08-18 |
| capability | openrouter | lost max_completion_tokens · openrouter/free: capabilities lost max_completion_tokens | 2026-08-18 |
| capability | lost top_a · google/gemma-4-31b-it: capabilities lost top_a | 2026-08-15 | |
| capability | deepseek | lost max_completion_tokens · deepseek/deepseek-r1: capabilities lost max_completion_tokens | 2026-08-13 |
| capability | kwaipilot | lost frequency_penalty · kwaipilot/kat-coder-air-v2.5: capabilities lost frequency_penalty +1 alias inferred | 2026-08-13 |
| capability | openai | lost max_completion_tokens · openai/gpt-5.3-chat: capabilities lost max_completion_tokens | 2026-08-08 |
| availability | kwaipilot | kwaipilot/kat-coder-air-v2.5 is no longer listed by this source — calls to it are expected to fail | 2026-08-31 |
| availability | arcee-ai | arcee-ai/virtuoso-large is no longer listed by this source — calls to it are expected to fail | 2026-08-29 |
| availability | openai | openai/gpt-5-mini:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.5-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.6-terra:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.6-luna:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | xai | xai/grok-2-1212 is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-4-turbo:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o3-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-4.1-mini:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.6-luna-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.6-terra-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-4.1:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-4.1-nano:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.4-nano:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o3:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.4:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.1:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | xai | xai/grok-vision-beta is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.6-sol-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-4o-mini:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.6-sol:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o1-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | xai | xai/grok-2-latest is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5-nano:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | xai | xai/grok-2-vision-1212 is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.4-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.2:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o4-mini-high:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o3-mini-high:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o4-mini:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.5:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o1:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5-codex:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-4o:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | xai | xai/grok-beta is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | xai | xai/grok-2-vision-latest is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/o3-mini:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.4-mini:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | openai | openai/gpt-5.2-pro:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | moonshotai | moonshotai/kimi-k2.7-code:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | thedrummer | thedrummer/rocinante-12b is no longer listed by this source — calls to it are expected to fail | 2026-08-28 |
| availability | z-ai | z-ai/glm-5.2:batch is no longer listed by this source — calls to it are expected to fail | 2026-08-26 |
| availability | stealth | stealth/ox-alpha is no longer listed by this source — calls to it are expected to fail | 2026-08-26 |
| availability | runwayml | runwayml/gen4_aleph is no longer listed by this source — calls to it are expected to fail | 2026-08-26 |
| availability | runwayml | runwayml/gen3a_turbo is no longer listed by this source — calls to it are expected to fail | 2026-08-26 |
| availability | google/gemma-3n-e4b-it is no longer listed by this source — calls to it are expected to fail | 2026-08-26 | |
| availability | qwen | qwen/qwen-plus-2025-07-28:thinking is no longer listed by this source — calls to it are expected to fail | 2026-08-25 |
| availability | inclusionai | inclusionai/ling-2.6-1t is no longer listed by this source — calls to it are expected to fail | 2026-08-24 |
| availability | inclusionai | inclusionai/ring-2.6-1t is no longer listed by this source — calls to it are expected to fail | 2026-08-24 |
| availability | nvidia | nvidia/nemotron-3-nano-30b-a3b:free is no longer listed by this source — calls to it are expected to fail | 2026-08-24 |
| availability | inclusionai | inclusionai/ling-2.6-flash is no longer listed by this source — calls to it are expected to fail | 2026-08-24 |
| availability | nvidia | nvidia/nemotron-nano-12b-v2-vl:free is no longer listed by this source — calls to it are expected to fail | 2026-08-24 |
| availability | nvidia | nvidia/nemotron-nano-9b-v2:free is no longer listed by this source — calls to it are expected to fail | 2026-08-24 |
| availability | openai | openai/gpt-oss-20b:free is no longer listed by this source — calls to it are expected to fail | 2026-08-22 |
| availability | deepcogito | deepcogito/cogito-v2.1-671b is no longer listed by this source — calls to it are expected to fail | 2026-08-22 |
| availability | z-ai | z-ai/glm-5.2:free is no longer listed by this source — calls to it are expected to fail | 2026-08-18 |
| availability | liquid | liquid/lfm-2.5-2.6b:free is no longer listed by this source — calls to it are expected to fail | 2026-08-18 |
| availability | gemini-3.7-flash-video-understanding-eap is no longer listed by this source — calls to it are expected to fail | 2026-08-13 | |
| availability | inclusionai | inclusionai/ling-3.0-tiny:free is no longer listed by this source — calls to it are expected to fail | 2026-08-13 |
| availability | anthropic | claude-instant-1.0 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | anthropic | claude-instant-1.2 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | anthropic | claude-1.0 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | anthropic | claude-instant-1.1 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | azure | gpt-4o version 2024-05-13 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | anthropic | claude-1.1 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | anthropic | claude-1.2 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | anthropic | claude-1.3 is no longer listed by this source — calls to it are expected to fail inferred | 2026-08-01 |
| availability | replicate | replicateopenai/gpt-oss-20b vanished; replicate/openai/gpt-oss-20b appeared with identical price and context — most likely a rename inferred | 2026-08-07 |
| availability | inclusionai | inclusionai/ling-3.0-flash:free vanished; inclusionai/ling-3.0-tiny:free appeared with identical price and context — most likely a rename inferred | 2026-08-06 |
Announced this period
| Impact | Provider | What changed | Detected |
|---|---|---|---|
| availability | together_ai | together_ai/google/gemma-3n-E4B-it: deprecation announced for 2026-08-25 (date already passed) +1 alias | 2026-08-28 |
| availability | together_ai | together_ai/deepseek-ai/DeepSeek-V4-Pro: retires 2026-08-27 (1 days ago) +3 aliases | 2026-08-28 |
| availability | together_ai | together_ai/google/gemma-3n-E4B-it: retires 2026-08-25 (3 days ago) +1 alias | 2026-08-28 |
| availability | moonshotai | moonshotai/kimi-k2.5: retirement announced for 2026-08-31 — in 4 days +1 alias | 2026-08-27 |
| availability | moonshotai | moonshotai/kimi-k2.5: retires 2026-08-31 (in 7 days) | 2026-08-24 |
| availability | azure_ai | azure_ai/deepseek-r1: deprecation announced for 2026-08-13 (date already passed) | 2026-08-21 |
| availability | azure_ai | azure_ai/claude-opus-4-1: deprecation announced for 2026-08-05 (date already passed) inferred | 2026-08-21 |
| availability | gemini | gemini/gemini-robotics-er-1.6-preview: retires 2026-08-31 (in 10 days) | 2026-08-21 |
| availability | azure_ai | azure_ai/deepseek-r1: retires 2026-08-13 (8 days ago) | 2026-08-21 |
| availability | azure_ai | azure_ai/MAI-Image-2e: deprecation announced for 2026-08-15 (date already passed) inferred | 2026-08-21 |
| availability | gemini | gemini/gemini-robotics-er-1.6-preview: deprecation announced for 2026-08-31 — in 10 days | 2026-08-21 |
| availability | azure_ai | azure_ai/MAI-Image-2e: retires 2026-08-15 (6 days ago) inferred | 2026-08-21 |
| availability | azure_ai | azure_ai/claude-opus-4-1: retires 2026-08-05 (16 days ago) inferred | 2026-08-21 |
| availability | vertex_ai-anthropic_models | vertex_ai/claude-opus-4-1: deprecation announced for 2026-08-05 (date already passed) +1 alias inferred | 2026-08-21 |
| availability | vertex_ai-anthropic_models | vertex_ai/claude-opus-4-1: retires 2026-08-05 (16 days ago) +1 alias inferred | 2026-08-21 |
| availability | nvidia | nvidia/nemotron-3-nano-30b-a3b:free: retires 2026-08-24 (in 4 days) +2 aliases inferred | 2026-08-20 |
| availability | nvidia | nvidia/nemotron-3-nano-30b-a3b:free: retirement announced for 2026-08-24 — in 4 days +2 aliases inferred | 2026-08-20 |
| availability | inclusionai | inclusionai/ling-2.6-1t: retires 2026-08-24 (in 5 days) +2 aliases inferred | 2026-08-19 |
| availability | inclusionai | inclusionai/ling-2.6-1t: retirement announced for 2026-08-24 — in 5 days +2 aliases inferred | 2026-08-19 |
| availability | deepseek | deepseek/deepseek-v3.1-terminus: retires 2026-08-17 (in 2 days) | 2026-08-15 |
| availability | deepseek | deepseek/deepseek-v3.1-terminus: retirement announced for 2026-08-17 — in 2 days | 2026-08-15 |
| availability | groq | groq/llama-3.1-8b-instant: deprecation announced for 2026-08-16 — in 3 days +1 alias inferred | 2026-08-13 |
| availability | groq | groq/meta-llama/llama-4-scout-17b-16e-instruct: deprecation announced for 2026-07-17 (date already passed) +1 alias | 2026-08-13 |
| availability | groq | groq/meta-llama/llama-4-scout-17b-16e-instruct: retires 2026-07-17 (27 days ago) +1 alias | 2026-08-13 |
| availability | groq | groq/llama-3.1-8b-instant: retires 2026-08-16 (in 3 days) +1 alias inferred | 2026-08-13 |
| availability | inclusionai | inclusionai/ling-3.0-tiny:free: retirement announced for 2026-08-13 — in 1 days inferred | 2026-08-12 |
| availability | inclusionai | inclusionai/ling-3.0-tiny:free: retires 2026-08-13 (in 1 days) inferred | 2026-08-12 |
| availability | mistral | mistral/devstral-2512: retires 2026-07-31 (12 days ago) +5 aliases inferred | 2026-08-12 |
| availability | anthropic | claude-opus-4-1: deprecation announced for 2026-08-05 (date already passed) inferred | 2026-08-12 |
| availability | bedrock | anthropic.claude-3-sonnet-20240229-v1:0: retires 2026-07-30 (13 days ago) +8 aliases | 2026-08-12 |
| availability | gemini | gemini/imagen-4.0-fast-generate-001: retires 2026-08-17 (in 5 days) +2 aliases | 2026-08-12 |
| availability | bedrock | cohere.command-r-plus-v1:0: retires 2026-08-19 (in 7 days) +1 alias inferred | 2026-08-12 |
| availability | bedrock | anthropic.claude-3-haiku-20240307-v1:0: deprecation announced for 2026-09-10 — in 29 days +5 aliases | 2026-08-12 |
| availability | mistral | mistral/mistral-medium-2505: deprecation announced for 2026-08-31 — in 19 days +2 aliases inferred | 2026-08-12 |
| availability | bedrock | anthropic.claude-3-haiku-20240307-v1:0: retires 2026-09-10 (in 29 days) +5 aliases | 2026-08-12 |
| availability | gemini | gemini/imagen-4.0-fast-generate-001: deprecation announced for 2026-08-17 — in 5 days +2 aliases | 2026-08-12 |
| availability | bedrock | anthropic.claude-3-sonnet-20240229-v1:0: deprecation announced for 2026-07-30 (date already passed) +8 aliases | 2026-08-12 |
| availability | mistral | mistral/mistral-medium-2505: retires 2026-08-31 (in 19 days) +2 aliases inferred | 2026-08-12 |
| availability | bedrock | cohere.command-r-plus-v1:0: deprecation announced for 2026-08-19 — in 7 days +1 alias inferred | 2026-08-12 |
| availability | anthropic | claude-opus-4-1-20250805: retires 2026-08-05 (in 4 days) +1 alias inferred | 2026-08-12 |
| availability | mistral | mistral/devstral-2512: deprecation announced for 2026-07-31 (date already passed) +5 aliases inferred | 2026-08-12 |
| availability | gemini | gemini/gemini-embedding-2-preview: retires 2026-08-10 (2 days ago) | 2026-08-12 |
| availability | gemini | gemini/gemini-embedding-2-preview: deprecation announced for 2026-08-10 (date already passed) | 2026-08-12 |
| availability | openai | gpt-5.2-chat-latest: deprecation announced for 2026-08-10 (date already passed) +1 alias | 2026-08-12 |
| availability | openai | gpt-4o-mini-search-preview-2025-03-11: deprecation announced for 2026-07-23 (date already passed) +15 aliases | 2026-08-12 |
| availability | openai | gpt-4o-audio: deprecation announced for 2026-07-20 (date already passed) +8 aliases inferred | 2026-08-05 |
| availability | openai | computer-use-preview-2025-03-11: retires 2026-07-23 (9 days ago) +17 aliases inferred | 2026-08-01 |
| availability | openai | gpt-5.2-chat-latest: retires 2026-08-10 (in 9 days) +3 aliases | 2026-08-01 |
| availability | gemini | gemini/gemini-omni-flash-preview: deprecation announced for 2026-09-30 — in 31 days | 2026-08-30 |
| availability | gemini | gemini/gemini-omni-flash-preview: retires 2026-09-30 (in 31 days) | 2026-08-30 |
| availability | azure | azure/gpt-4o-transcribe: retires 2026-10-15 (in 64 days) +1 alias inferred | 2026-08-28 |
| availability | azure | azure/gpt-4o-transcribe: deprecation announced for 2026-10-15 — in 64 days +1 alias inferred | 2026-08-28 |
| availability | anthropic | claude-sonnet-4-5-20250929: retires 2026-09-29 (in 39 days) +1 alias | 2026-08-21 |
| availability | vertex_ai-language-models | gemini-2.5-flash-lite: retires 2026-10-20 (in 60 days) +2 aliases | 2026-08-21 |
| availability | azure_ai | azure_ai/claude-haiku-4-5: retires 2026-10-19 (in 59 days) +2 aliases inferred | 2026-08-21 |
| availability | text-completion-openai | babbage-002: retires 2026-09-28 (in 38 days) +2 aliases | 2026-08-21 |
| availability | azure | azure/o4-mini-2025-04-16: deprecation announced for 2026-10-16 — in 65 days +2 aliases | 2026-08-21 |
| availability | vertex_ai-language-models | gemini-2.5-flash-lite: deprecation announced for 2026-10-20 — in 60 days +2 aliases | 2026-08-21 |
| availability | vertex_ai-video-models | vertex_ai/veo-3.1-fast-generate-001: deprecation announced for 2026-11-17 — in 88 days +1 alias inferred | 2026-08-21 |
| availability | anthropic | claude-haiku-4-5-20251001: deprecation announced for 2026-10-15 — in 55 days +1 alias | 2026-08-21 |
| availability | openai | ft-babbage-002: retires 2026-10-23 (in 83 days) +45 aliases | 2026-08-21 |
| availability | azure | azure/o4-mini-2025-04-16: retires 2026-10-16 (in 65 days) +2 aliases | 2026-08-21 |
| availability | azure | azure/gpt-image-1: retires 2026-10-23 (in 72 days) +9 aliases | 2026-08-21 |
| availability | azure | azure/eu/o1-2024-12-17: retires 2026-10-21 (in 70 days) +6 aliases | 2026-08-21 |
| availability | openai | ft:gpt-3.5-turbo-0125: deprecation announced for 2026-10-23 — in 72 days +33 aliases | 2026-08-21 |
| availability | vertex_ai-anthropic_models | vertex_ai/claude-sonnet-4-5: deprecation announced for 2026-09-29 — in 39 days +1 alias inferred | 2026-08-21 |
| availability | anthropic | claude-sonnet-4-5-20250929: deprecation announced for 2026-09-29 — in 39 days +1 alias | 2026-08-21 |
| availability | vertex_ai-video-models | vertex_ai/veo-3.1-fast-generate-001: retires 2026-11-17 (in 88 days) +1 alias inferred | 2026-08-21 |
| availability | vertex_ai-language-models | gemini-2.5-flash-image: deprecation announced for 2026-10-02 — in 42 days +1 alias | 2026-08-21 |
| availability | azure | azure/eu/o1-2024-12-17: deprecation announced for 2026-10-21 — in 70 days +4 aliases | 2026-08-21 |
| availability | vertex_ai-language-models | gemini-2.5-flash-image: retires 2026-10-02 (in 42 days) +1 alias | 2026-08-21 |
| availability | azure_ai | azure_ai/claude-haiku-4-5: deprecation announced for 2026-10-19 — in 59 days +2 aliases inferred | 2026-08-21 |
| availability | vertex_ai-anthropic_models | vertex_ai/claude-haiku-4-5: deprecation announced for 2026-10-15 — in 55 days +1 alias inferred | 2026-08-21 |
| availability | text-completion-openai | babbage-002: deprecation announced for 2026-09-28 — in 38 days +2 aliases | 2026-08-21 |
| availability | vertex_ai-anthropic_models | vertex_ai/claude-haiku-4-5: retires 2026-10-15 (in 55 days) +1 alias inferred | 2026-08-21 |
| availability | azure | azure/gpt-image-1: deprecation announced for 2026-10-23 — in 72 days +9 aliases | 2026-08-21 |
| availability | vertex_ai-anthropic_models | vertex_ai/claude-sonnet-4-5: retires 2026-09-29 (in 39 days) +1 alias inferred | 2026-08-21 |
| availability | dots-studio | dots-studio/dots-3-note-preview:free: retires 2026-09-30 (in 41 days) inferred | 2026-08-20 |
| availability | azure | azure/gpt-4.1-nano-2025-04-14: deprecation announced for 2026-10-14 — in 63 days +1 alias | 2026-08-12 |
| availability | text-completion-openai | ft:babbage-002: retires 2026-10-23 (in 72 days) +1 alias inferred | 2026-08-12 |
Who changed the most
| Provider | Unannounced changes |
|---|---|
| openai | 38 |
| qwen | 11 |
| nvidia | 9 |
| deepseek | 9 |
| xai | 9 |
| anthropic | 8 |
| novita | 7 |
| z-ai | 7 |
| 6 | |
| inclusionai | 6 |
| thedrummer | 3 |
| arcee-ai | 3 |