Model FatigueLLMs under $1, measured — and who holds your data
Providers

DeepInfra

DeepInfra model retirements

Model retirements DeepInfra has published since 2026, with the model id exactly as DeepInfra writes it. Each date comes from DeepInfra's own published pages.

Upcoming (5)

Model idShuts downDeprecatedReplacementSource
Bria/fibo-1.52026-10-27Bria/fibo-2.0provider page
Bria/fibo2026-10-27Bria/fibo-2.0provider page
Gryphe/MythoMax-L2-13b2026-10-29Sao10K/L3-8B-Lunaris-v1-Turboprovider page
NousResearch/Hermes-3-Llama-3.1-70B2026-11-02deepseek-ai/DeepSeek-V4.1-Flash-1017provider page
NousResearch/Hermes-3-Llama-3.1-405B2026-11-02deepseek-ai/DeepSeek-V4.1-Flash-1017provider page

Already retired (103)

Model idShuts downDeprecatedReplacementSource
black-forest-labs/FLUX-1-Redux-dev2026-10-23black-forest-labs/FLUX-2-devprovider page
thinkingmachines/Inkling2026-10-22thinkingmachines/Inkling-Smallprovider page
openai/gpt-oss-120b-Turbo2026-10-20openai/gpt-oss-120bprovider page
ibm-granite/granite-4.2-30b2026-10-18ibm-granite/granite-4.2-8bprovider page
ibm-granite/granite-4.2-3b2026-10-18ibm-granite/granite-4.2-8bprovider page
Qwen/Qwen3.8-2.4T-A95B2026-10-12zai-org/GLM-5.3provider page
Qwen/Qwen3-Max2026-10-10Qwen/Qwen3.8-Maxprovider page
Qwen/Qwen3-Max-Thinking2026-10-10Qwen/Qwen3.8-Maxprovider page
inclusionAI/Ling-3.0-flash-Fin2026-10-09inclusionAI/Ling-3.0-flash-VLprovider page
black-forest-labs/FLUX.1-Kontext-dev2026-10-08black-forest-labs/FLUX-2-devprovider page
nvidia/Nemotron-3-Nano-30B-A3B2026-10-08nvidia/NVIDIA-Nemotron-3.5-Lightningprovider page
nvidia/NVIDIA-Nemotron-Nano-9B-v22026-10-08nvidia/NVIDIA-Nemotron-3.5-Lightningprovider page
Qwen/Qwen-Image-Edit2026-10-08Qwen/Qwen-Image-Edit-Maxprovider page
tencent/Hy32026-10-08tencent/Hy4-previewprovider page
nvidia/Cosmos3-Nano2026-10-02Wan-AI/Wan3.0-Videoprovider page
nvidia/Cosmos3-Super2026-10-02Wan-AI/Wan3.0-Videoprovider page
google/gemma-4-E4B-it2026-10-01google/gemma-4-31B-it-turboprovider page
meta-llama/Llama-3.2-90B-Vision-Instruct2026-10-01google/gemma-4-31B-it-turboprovider page
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP82026-10-01google/gemma-4-31B-it-turboprovider page
meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo2026-10-01google/gemma-4-31B-it-turboprovider page
Qwen/QVQ-72B-Preview2026-10-01google/gemma-4-31B-it-turboprovider page
Qwen/Qwen3.5-122B-A10B2026-10-01Qwen/Qwen3.5-397B-A17Bprovider page
stepfun-ai/Step-3.5-Flash2026-10-01XiaomiMiMo/MiMo-V2.6-Flashprovider page
stepfun-ai/Step-3.7-Flash2026-10-01XiaomiMiMo/MiMo-V2.6-Flashprovider page
zai-org/GLM-5.12026-10-01zai-org/GLM-5.3provider page
MiniMaxAI/MiniMax-M2.7-Turbo2026-09-30MiniMaxAI/MiniMax-M3provider page
deepseek-ai/DeepSeek-Prover-V2-671B2026-09-29deepseek-ai/DeepSeek-V4.1-Flashprovider page
deepseek-ai/DeepSeek-V3-03242026-09-29deepseek-ai/DeepSeek-V4.1-Flashprovider page
deepseek-ai/DeepSeek-V3-0324-Turbo2026-09-29deepseek-ai/DeepSeek-V4.1-Flashprovider page
moonshotai/Kimi-K2.7-Code2026-09-29moonshotai/Kimi-K3provider page
XiaomiMiMo/MiMo-V2.52026-09-29XiaomiMiMo/MiMo-V2.6-Flashprovider page
XiaomiMiMo/MiMo-V2.5-Pro2026-09-29XiaomiMiMo/MiMo-V2.6-Proprovider page
nvidia/Nemotron-3-Diarization-preview2026-09-25nvidia/Nemotron-3-Diarizationprovider page
MiniMaxAI/MiniMax-M22026-09-10MiniMaxAI/MiniMax-M3provider page
MiniMaxAI/MiniMax-M2.12026-09-10MiniMaxAI/MiniMax-M3provider page
MiniMaxAI/MiniMax-M2.52026-09-10MiniMaxAI/MiniMax-M3provider page
MiniMaxAI/MiniMax-M2.72026-09-10MiniMaxAI/MiniMax-M3provider page
zai-org/GLM-4.7-Flash2026-09-10zai-org/GLM-5.3-Flashprovider page
zai-org/GLM-52026-09-10zai-org/GLM-5.2provider page
moonshotai/Kimi-K2-Instruct2026-09-07moonshotai/Kimi-K2.6provider page
moonshotai/Kimi-K2-Instruct-09052026-09-07moonshotai/Kimi-K2.6provider page
moonshotai/Kimi-K2-Thinking2026-09-07moonshotai/Kimi-K2.6provider page
moonshotai/Kimi-K2.52026-09-07moonshotai/Kimi-K2.6provider page
moonshotai/Kimi-K2.5-Turbo2026-09-07moonshotai/Kimi-K2.6provider page
Qwen/Qwen3-235B-A22B-Thinking-25072026-08-24Qwen/Qwen3.6-35B-A3Bprovider page
deepseek-ai/DeepSeek-V3.1-Terminus2026-08-17deepseek-ai/DeepSeek-V4-Flash-0731provider page
deepreinforce-ai/Ornith-1.0-35B2026-07-19Qwen/Qwen3.6-35B-A3Bprovider page
meta-llama/Llama-3.2-11B-Vision-Instruct2026-07-17google/gemma-4-31B-itprovider page
meta-llama/Llama-3.2-1B-Instruct2026-07-17google/gemma-4-31B-itprovider page
meta-llama/Llama-3.2-3B-Instruct2026-07-17google/gemma-4-31B-itprovider page
nvidia/Llama-3.3-Nemotron-Super-49B-v1.52026-07-17nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bprovider page
openbmb/MiniCPM-Llama3-V-2_52026-07-17google/gemma-4-31B-itprovider page
meta-llama/Meta-Llama-3.1-8B-Instruct2026-07-16meta-llama/Meta-Llama-3.1-8B-Instruct-Turboprovider page
microsoft/Phi-3-medium-4k-instruct2026-07-16meta-llama/Meta-Llama-3.1-8B-Instruct-Turboprovider page
nvidia/Llama-3.1-Nemotron-70B-Instruct2026-07-16nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bprovider page
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning2026-07-16nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bprovider page
nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL2026-07-16nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bprovider page
openchat/openchat_3.52026-07-16meta-llama/Meta-Llama-3.1-8B-Instruct-Turboprovider page
openchat/openchat-3.6-8b2026-07-16meta-llama/Meta-Llama-3.1-8B-Instruct-Turboprovider page
Qwen/Qwen3-Embedding-0.6B-batch2026-07-06Qwen/Qwen3-Embedding-0.6Bprovider page
Qwen/Qwen3-Embedding-4B-batch2026-07-06Qwen/Qwen3-Embedding-4Bprovider page
Qwen/Qwen3-Embedding-8B-batch2026-07-06Qwen/Qwen3-Embedding-8Bprovider page
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF162026-06-26nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bprovider page
FastVideo/LTX2-Distilled-Diffusers2026-06-24FastVideo/LTX-2.3-Distilled-Diffusersprovider page
bigcode/starcoder2-15b-instruct-v0.12026-06-11meta-llama/Meta-Llama-3.1-70B-Instruct-Turboprovider page
deepseek-ai/DeepSeek-R1-Distill-Llama-70B2026-06-11deepseek-ai/DeepSeek-R1-0528provider page
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B2026-06-11deepseek-ai/DeepSeek-R1-0528provider page
mattshumer/Reflection-Llama-3.1-70B2026-06-11meta-llama/Meta-Llama-3.1-70B-Instruct-Turboprovider page
meta-llama/Meta-Llama-3.1-70B-Instruct2026-06-11meta-llama/Meta-Llama-3.1-70B-Instruct-Turboprovider page
Phind/Phind-CodeLlama-34B-v22026-06-11meta-llama/Meta-Llama-3.1-70B-Instruct-Turboprovider page
Qwen/Qwen3.5-0.8B2026-06-11Qwen/Qwen3.5-9Bprovider page
Qwen/Qwen3.5-2B2026-06-11Qwen/Qwen3.5-9Bprovider page
Qwen/Qwen3.5-4B2026-06-11Qwen/Qwen3.5-9Bprovider page
Qwen/QwQ-32B-Preview2026-06-11deepseek-ai/DeepSeek-R1-0528provider page
deepseek-ai/DeepSeek-R1-0528-Turbo2026-05-21deepseek-ai/DeepSeek-R1-0528provider page
anthropic/claude-3-7-sonnet-latest2026-05-20anthropic/claude-sonnet-4-6provider page
anthropic/claude-4-opus2026-05-20anthropic/claude-opus-4-7provider page
anthropic/claude-4-sonnet2026-05-20anthropic/claude-sonnet-4-6provider page
google/veo-3.02026-05-20google/veo-3.1provider page
google/veo-3.0-fast2026-05-20google/veo-3.1-fastprovider page
allenai/Olmo-3.1-32B-Instruct2026-05-07google/gemma-4-31B-itprovider page
allenai/olmOCR-22026-05-07google/gemma-4-31B-itprovider page
allenai/olmOCR-2-7B-10252026-05-07google/gemma-4-31B-itprovider page
allenai/olmOCR-7B-0725-FP82026-05-07google/gemma-4-31B-itprovider page
allenai/olmOCR-7B-08252026-05-07google/gemma-4-31B-itprovider page
allenai/olmOCR-7B-10252026-05-07google/gemma-4-31B-itprovider page
deepseek-ai/DeepSeek-OCR2026-05-07google/gemma-4-31B-itprovider page
meta-llama/Llama-2-13b-chat-hf2026-05-07meta-llama/Llama-4-Scout-17B-16E-Instructprovider page
meta-llama/Meta-Llama-3-8B-Instruct2026-05-07meta-llama/Llama-4-Scout-17B-16E-Instructprovider page
mistralai/Mixtral-8x7B-Instruct-v0.12026-05-07mistralai/Mistral-Small-24B-Instruct-2501provider page
PaddlePaddle/PaddleOCR-VL-0.9B2026-05-07google/gemma-4-31B-itprovider page
Sao10K/L3.3-70B-Euryale-v2.32026-05-07Sao10K/L3.1-70B-Euryale-v2.2provider page
inworld-ai/inworld-tts-1.5-max2026-05-05inworld-ai/realtime-tts-1.5-maxprovider page
inworld-ai/inworld-tts-1.5-mini2026-05-05inworld-ai/realtime-tts-1.5-miniprovider page
Qwen/Qwen3-Coder-480B-A35B-Instruct2026-04-30Qwen/Qwen3-Coder-480B-A35B-Instruct-Turboprovider page
zai-org/GLM-4.6V2026-04-30google/gemma-4-26B-A4B-itprovider page
Qwen/Qwen2.5-VL-32B-Instruct2026-04-25Qwen/Qwen3-VL-30B-A3B-Instructprovider page
Wan-AI/Wan2.1-T2V-1.3B2026-04-09Wan-AI/Wan2.2-T2V-A14Bprovider page
Wan-AI/Wan2.1-T2V-14B2026-04-09Wan-AI/Wan2.2-T2V-A14Bprovider page
ResembleAI/chatterbox2026-03-10ResembleAI/chatterbox-turboprovider page
microsoft/WizardLM-2-8x22B2026-02-18deepseek-ai/DeepSeek-V3.2provider page
mistralai/Mixtral-8x22B-Instruct-v0.12026-02-18deepseek-ai/DeepSeek-V3.2provider page
google/gemini-2.0-flash-0012026-02-06google/gemini-2.5-flashprovider page