Sunsetsby GlyphTogether AI model and API retirement dates
0 scheduled · 247 recorded · Together AI
Retirements
Recently retired
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 (fine-tuning)
Stopped answering on Together AI.
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-R1-0528 (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-R1-Distill-Llama-70B (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-R1-Distill-Llama-70B-131k (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-R1-Distill-Llama-70B-32k (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-V3-0324 (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-V3-Base (fine-tuning)
Stopped answering on Together AI.
deepseek-ai/DeepSeek-V3.1-Base (fine-tuning)
Stopped answering on Together AI.
meta-llama/Llama-3.2-1B-Instruct (fine-tuning)
Stopped answering on Together AI.
meta-llama/Llama-3.2-3B-Instruct (fine-tuning)
Stopped answering on Together AI.
meta-llama/Llama-3.3-70B-131k-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Llama-3.3-70B-32k-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Llama-4-Maverick-17B-128E (fine-tuning)
Stopped answering on Together AI.
meta-llama/Llama-4-Scout-17B-16E (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3-70B-Instruct (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3-8B-Instruct (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-405B-10k-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-405B-10k-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-405B-8k-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-405B-8k-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-405B-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-405B-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-70B-131k-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-70B-131k-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-70B-32k-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-70B-32k-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-70B-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-70B-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-8B-131k-Instruct-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-8B-131k-Reference (fine-tuning)
Stopped answering on Together AI.
meta-llama/Meta-Llama-3.1-8B-Reference (fine-tuning)
Stopped answering on Together AI.
mistralai/Mistral-7B-Instruct-v0.2 (fine-tuning)
Stopped answering on Together AI.
mistralai/Mixtral-8x7B-v0.1 (fine-tuning)
Stopped answering on Together AI.
moonshotai/Kimi-K2-Instruct (fine-tuning)
Stopped answering on Together AI.
moonshotai/Kimi-K2-Instruct-0905 (fine-tuning)
Stopped answering on Together AI.
moonshotai/Kimi-K2-Thinking (fine-tuning)
Stopped answering on Together AI.
nvidia/NVIDIA-Nemotron-Nano-9B-v2 (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-235B-A22B-Instruct-2507 (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-30B-A3B-Instruct-2507 (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-Coder-30B-A3B-Instruct (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-Coder-480B-A35B-Instruct (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-Next-80B-A3B-Instruct (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-Next-80B-A3B-Thinking (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-VL-235B-A22B-Instruct (fine-tuning)
Stopped answering on Together AI.
Qwen/Qwen3-VL-30B-A3B-Instruct (fine-tuning)
Stopped answering on Together AI.
togethercomputer/llama-2-7b-chat (fine-tuning)
Stopped answering on Together AI.
Nothing scheduled right now.
Changes
Sat, Oct 31
Qwen/Qwen3.8-2.4T-A95B
Together AI lists Qwen/Qwen3.8-2.4T-A95B to retire on Nov 4, 2026.
Mon, Oct 26
thinkingmachines/Inkling
Together AI lists thinkingmachines/Inkling to retire on Nov 6, 2026.
MiniMaxAI/MiniMax-M3
Together AI lists MiniMaxAI/MiniMax-M3 to retire on Nov 6, 2026.
Sun, Oct 11
deepseek-ai/DeepSeek-V4-Flash-0731
Together AI lists deepseek-ai/DeepSeek-V4-Flash-0731 to retire on Oct 22, 2026.
meta-llama/Llama-3.3-70B-Instruct-Turbo
Together AI lists meta-llama/Llama-3.3-70B-Instruct-Turbo to retire on Oct 22, 2026.
Fri, Sep 25
togethercomputer/llama-2-7b-chat (fine-tuning)
Together AI lists togethercomputer/llama-2-7b-chat (fine-tuning) to retire on Jul 29, 2026.
mistralai/Mistral-7B-v0.1 (fine-tuning)
Together AI lists mistralai/Mistral-7B-v0.1 (fine-tuning) to retire on Jul 29, 2026.
mistralai/Mistral-7B-Instruct-v0.2 (fine-tuning)
Together AI lists mistralai/Mistral-7B-Instruct-v0.2 (fine-tuning) to retire on Jul 29, 2026.
mistralai/Mixtral-8x7B-v0.1 (fine-tuning)
Together AI lists mistralai/Mixtral-8x7B-v0.1 (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-27b-pt (fine-tuning)
Together AI lists google/gemma-3-27b-pt (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-27b-it-VLM (fine-tuning)
Together AI lists google/gemma-3-27b-it-VLM (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-27b-it (fine-tuning)
Together AI lists google/gemma-3-27b-it (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-12b-pt (fine-tuning)
Together AI lists google/gemma-3-12b-pt (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-12b-it-VLM (fine-tuning)
Together AI lists google/gemma-3-12b-it-VLM (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-12b-it (fine-tuning)
Together AI lists google/gemma-3-12b-it (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-4b-pt (fine-tuning)
Together AI lists google/gemma-3-4b-pt (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-4b-it-VLM (fine-tuning)
Together AI lists google/gemma-3-4b-it-VLM (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-4b-it (fine-tuning)
Together AI lists google/gemma-3-4b-it (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-1b-pt (fine-tuning)
Together AI lists google/gemma-3-1b-pt (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-1b-it (fine-tuning)
Together AI lists google/gemma-3-1b-it (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-270m-it (fine-tuning)
Together AI lists google/gemma-3-270m-it (fine-tuning) to retire on Jul 29, 2026.
google/gemma-3-270m (fine-tuning)
Together AI lists google/gemma-3-270m (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3-70B-Instruct (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3-70B-Instruct (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3-8B (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3-8B (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3-8B-Instruct (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3-8B-Instruct (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-405B-8k-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-405B-8k-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-405B-8k-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-405B-8k-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-405B-10k-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-405B-10k-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-405B-10k-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-405B-10k-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-405B-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-405B-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-405B-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-405B-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-70B-131k-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-70B-131k-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-70B-32k-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-70B-32k-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-70B-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-70B-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-70B-131k-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-70B-131k-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-70B-32k-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-70B-32k-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-70B-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-70B-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-8B-131k-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-8B-131k-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-8B-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-8B-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Meta-Llama-3.1-8B-131k-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Meta-Llama-3.1-8B-131k-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-3.2-1B (fine-tuning)
Together AI lists meta-llama/Llama-3.2-1B (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-3.2-1B-Instruct (fine-tuning)
Together AI lists meta-llama/Llama-3.2-1B-Instruct (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-3.2-3B (fine-tuning)
Together AI lists meta-llama/Llama-3.2-3B (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-3.2-3B-Instruct (fine-tuning)
Together AI lists meta-llama/Llama-3.2-3B-Instruct (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-3.3-70B-131k-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Llama-3.3-70B-131k-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-3.3-70B-32k-Instruct-Reference (fine-tuning)
Together AI lists meta-llama/Llama-3.3-70B-32k-Instruct-Reference (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-4-Maverick-17B-128E (fine-tuning)
Together AI lists meta-llama/Llama-4-Maverick-17B-128E (fine-tuning) to retire on Jul 29, 2026.
meta-llama/Llama-4-Scout-17B-16E (fine-tuning)
Together AI lists meta-llama/Llama-4-Scout-17B-16E (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-R1-Distill-Qwen-14B (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-R1-Distill-Llama-70B-131k (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-R1-Distill-Llama-70B-131k (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-R1-Distill-Llama-70B-32k (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-R1-Distill-Llama-70B-32k (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-R1-Distill-Llama-70B (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-R1-Distill-Llama-70B (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-V3-Base (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-V3-Base (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-V3.1-Base (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-V3.1-Base (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-V3 (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-V3 (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-V3-0324 (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-V3-0324 (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-R1 (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-R1 (fine-tuning) to retire on Jul 29, 2026.
deepseek-ai/DeepSeek-R1-0528 (fine-tuning)
Together AI lists deepseek-ai/DeepSeek-R1-0528 (fine-tuning) to retire on Jul 29, 2026.
About Together AI's dates
Read from docs.together.ai/docs/deprecations. Calendar feed: sunsets.fru.dev/vendors/together-ai.ics.
Companies: Company profile · Awards · Blogs · calendar: 247 dated events · Compliance: 2 certifications · compute · Free: 1 free offer · Funding: Funding rounds · labs · lawsuits · Leaders: 9 leaders · Paydays: Pay schedule · Pricing: Inference host · 13 models · problems · Releases: 48 releases · salaries · socials · standards: AI models · 2 standards supported · terms: Data terms: 3 answers, 2 pages watched · Titles: 29 open roles