DeepInfra model deprecations
194 models DeepInfra deprecated or shut down, read from its own pages.
Shutting down soon 4
- bria/fibo Stops workingin 5 days
- bria/fibo-1.5 Stops workingin 5 days
- nousresearch/hermes-3-llama-3.1-405b Stops workingin 11 days
- nousresearch/hermes-3-llama-3.1-70b Stops workingin 11 days
Deprecated, no shutdown date yet 20
- No date deepseek-ai/deepseek-v3-0324 Deprecated, no date
- No date google/gemma-4-e4b-it Deprecated, no date
- No date meta-llama/llama-4-maverick-17b-128e-instruct-fp8 Deprecated, no date
- No date minimaxai/minimax-m2.5 Deprecated, no date
- No date minimaxai/minimax-m2.7 Deprecated, no date
- No date moonshotai/kimi-k2.5 Deprecated, no date
- No date moonshotai/kimi-k2.7-code Deprecated, no date
- No date nvidia/llama-3.3-nemotron-super-49b-v1.5 Deprecated, no date
- No date nvidia/nemotron-3-nano-30b-a3b Deprecated, no date
- No date nvidia/nemotron-3-nano-omni-30b-a3b-reasoning Deprecated, no date
- No date qwen/qwen3-max Deprecated, no date
- No date qwen/qwen3.5-122b-a10b Deprecated, no date
- No date qwen/qwen3.8-2.4t-a95b Deprecated, no date
- No date stepfun-ai/step-3.7-flash Deprecated, no date
- No date tencent/hy3 Deprecated, no date
- No date xiaomimimo/mimo-v2.5 Deprecated, no date
- No date xiaomimimo/mimo-v2.5-pro Deprecated, no date
- No date zai-org/glm-4.7-flash Deprecated, no date
- No date zai-org/glm-5 Deprecated, no date
- No date zai-org/glm-5.1 Deprecated, no date
Retired 170
- thinkingmachines/inkling Stopped working
- openai/gpt-oss-120b-turbo Stopped working
- ibm-granite/granite-4.2-30b Stopped working
- ibm-granite/granite-4.2-3b Stopped working
- qwen/qwen3.8-2.4t-a95b Stopped working
- qwen/qwen3-max Stopped working
- qwen/qwen3-max-thinking Stopped working
- inclusionai/ling-3.0-flash-fin Stopped working
- black-forest-labs/flux-1-redux-dev Stopped working
- black-forest-labs/flux.1-kontext-dev Stopped working
- deepseek-ai/janus-pro-1b Stopped working
- deepseek-ai/janus-pro-7b Stopped working
- nvidia/nemotron-3-nano-30b-a3b Stopped working
- nvidia/nvidia-nemotron-nano-9b-v2 Stopped working
- qwen/qwen-image-edit Stopped working
- tencent/hy3 Stopped working
- nvidia/cosmos3-nano Stopped working
- nvidia/cosmos3-super Stopped working
- google/gemma-4-e4b-it Stopped working
- meta-llama/llama-3.2-90b-vision-instruct Stopped working
- meta-llama/llama-4-maverick-17b-128e-instruct-fp8 Stopped working
- meta-llama/llama-4-maverick-17b-128e-instruct-turbo Stopped working
- qwen/qvq-72b-preview Stopped working
- qwen/qwen3.5-122b-a10b Stopped working
- stepfun-ai/step-3.5-flash Stopped working
- stepfun-ai/step-3.7-flash Stopped working
- zai-org/glm-5.1 Stopped working
- minimaxai/minimax-m2.7-turbo Stopped working
- deepseek-ai/deepseek-prover-v2-671b Stopped working
- deepseek-ai/deepseek-v3-0324 Stopped working
- deepseek-ai/deepseek-v3-0324-turbo Stopped working
- moonshotai/kimi-k2.7-code Stopped working
- xiaomimimo/mimo-v2.5 Stopped working
- xiaomimimo/mimo-v2.5-pro Stopped working
- nvidia/nemotron-3-diarization-preview Stopped working
- minimaxai/minimax-m2 Stopped working
- minimaxai/minimax-m2.1 Stopped working
- minimaxai/minimax-m2.5 Stopped working
- minimaxai/minimax-m2.7 Stopped working
- zai-org/glm-4.7-flash Stopped working
- zai-org/glm-5 Stopped working
- moonshotai/kimi-k2-instruct Stopped working
- moonshotai/kimi-k2-instruct-0905 Stopped working
- moonshotai/kimi-k2-thinking Stopped working
- moonshotai/kimi-k2.5 Stopped working
- moonshotai/kimi-k2.5-turbo Stopped working
- qwen/qwen3-235b-a22b-thinking-2507 Stopped working
- deepseek-ai/deepseek-v3.1-terminus Stopped working
- deepreinforce-ai/ornith-1.0-35b Stopped working
- meta-llama/llama-3.2-11b-vision-instruct Stopped working
- meta-llama/llama-3.2-1b-instruct Stopped working
- meta-llama/llama-3.2-3b-instruct Stopped working
- nvidia/llama-3.3-nemotron-super-49b-v1.5 Stopped working
- openbmb/minicpm-llama3-v-2_5 Stopped working
- meta-llama/meta-llama-3.1-8b-instruct Stopped working
- microsoft/phi-3-medium-4k-instruct Stopped working
- nvidia/llama-3.1-nemotron-70b-instruct Stopped working
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning Stopped working
- nvidia/nvidia-nemotron-nano-12b-v2-vl Stopped working
- openchat/openchat_3.5 Stopped working
- openchat/openchat-3.6-8b Stopped working
- qwen/qwen3-embedding-0.6b-batch Stopped working
- qwen/qwen3-embedding-4b-batch Stopped working
- qwen/qwen3-embedding-8b-batch Stopped working
- nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 Stopped working
- fastvideo/ltx2-distilled-diffusers Stopped working
- bigcode/starcoder2-15b-instruct-v0.1 Stopped working
- deepseek-ai/deepseek-r1-distill-llama-70b Stopped working
- deepseek-ai/deepseek-r1-distill-qwen-32b Stopped working
- mattshumer/reflection-llama-3.1-70b Stopped working
- meta-llama/meta-llama-3.1-70b-instruct Stopped working
- phind/phind-codellama-34b-v2 Stopped working
- qwen/qwen3.5-0.8b Stopped working
- qwen/qwen3.5-2b Stopped working
- qwen/qwen3.5-4b Stopped working
- qwen/qwq-32b-preview Stopped working
- deepseek-ai/deepseek-r1-0528-turbo Stopped working
- anthropic/claude-3-7-sonnet-latest Stopped working
- anthropic/claude-4-opus Stopped working
- anthropic/claude-4-sonnet Stopped working
- google/veo-3.0 Stopped working
- google/veo-3.0-fast Stopped working
- zyphra/zonos-v0.1-hybrid Stopped working
- zyphra/zonos-v0.1-transformer Stopped working
- allenai/olmo-3.1-32b-instruct Stopped working
- allenai/olmocr-2 Stopped working
- allenai/olmocr-2-7b-1025 Stopped working
- allenai/olmocr-7b-0725-fp8 Stopped working
- allenai/olmocr-7b-0825 Stopped working
- allenai/olmocr-7b-1025 Stopped working
- deepseek-ai/deepseek-ocr Stopped working
- meta-llama/llama-2-13b-chat-hf Stopped working
- meta-llama/meta-llama-3-8b-instruct Stopped working
- mistralai/mixtral-8x7b-instruct-v0.1 Stopped working
- paddlepaddle/paddleocr-vl-0.9b Stopped working
- sao10k/l3.3-70b-euryale-v2.3 Stopped working
- inworld-ai/inworld-tts-1.5-max Stopped working
- inworld-ai/inworld-tts-1.5-mini Stopped working
- qwen/qwen3-coder-480b-a35b-instruct Stopped working
- zai-org/glm-4.6v Stopped working
- qwen/qwen2.5-vl-32b-instruct Stopped working
- wan-ai/wan2.1-t2v-1.3b Stopped working
- wan-ai/wan2.1-t2v-14b Stopped working
- resembleai/chatterbox Stopped working
- microsoft/wizardlm-2-8x22b Stopped working
- mistralai/mixtral-8x22b-instruct-v0.1 Stopped working
- google/gemini-2.0-flash-001 Stopped working
- deepseek-ai/deepseek-r1 Stopped working
- deepseek-ai/deepseek-r1-turbo Stopped working
- deepseek-ai/deepseek-v3.2-exp Stopped working
- qwen/qwen3-coder-30b-a3b-instruct Stopped working
- meta-llama/llama-guard-3-8b Stopped working
- qwen/qwen3-vl-30b-a3b-thinking Stopped working
- qwen/qwen3-vl-4b-instruct Stopped working
- qwen/qwen3-vl-4b-thinking Stopped working
- qwen/qwen3-vl-8b-instruct Stopped working
- qwen/qwen3-vl-8b-thinking Stopped working
- deepinfra/airoboros-70b Stopped working
- lizpreciatior/lzlv_70b_fp16_hf Stopped working
- meta-llama/llama-3.3-70b-instruct Stopped working
- qwen/qwen2-7b-instruct Stopped working
- qwen/qwen2.5-7b-instruct Stopped working
- qwen/qwen2.5-coder-7b Stopped working
- qwen/qwen3-vl-235b-a22b-thinking Stopped working
- qwen/qwq-32b Stopped working
- zai-org/glm-4.5 Stopped working
- stabilityai/sd3.5 Stopped working
- stabilityai/sd3.5-medium Stopped working
- qwen/qwen3-235b-a22b Stopped working
- zai-org/glm-4.5-air Stopped working
- mistralai/mistral-7b-instruct-v0.1 Stopped working
- mistralai/mistral-7b-instruct-v0.2 Stopped working
- mistralai/mistral-7b-instruct-v0.3 Stopped working
- meta-llama/llama-2-70b-chat-hf Stopped working
- meta-llama/meta-llama-3-70b-instruct Stopped working
- mistralai/devstral-small-2505 Stopped working
- mistralai/devstral-small-2507 Stopped working
- mistralai/mistral-small-3.1-24b-instruct-2503 Stopped working
- qwen/qwen2.5-coder-32b-instruct Stopped working
- microsoft/phi-4-multimodal-instruct Stopped working
- microsoft/phi-4-reasoning-plus Stopped working
- novasky-ai/sky-t1-32b-preview Stopped working
- meta-llama/meta-llama-3.1-405b-instruct Stopped working
- nvidia/nemotron-4-340b-instruct Stopped working
- run-diffusion/juggernaut-flux Stopped working
- run-diffusion/juggernaut-lightning-flux Stopped working
- google/codegemma-7b-it Stopped working
- google/gemma-1.1-7b-it Stopped working
- google/gemma-2-27b-it Stopped working
- google/gemma-2-9b-it Stopped working
- sao10k/l3-70b-euryale-v2.1 Stopped working
- sao10k/l3-8b-lunaris-v1 Stopped working
- microsoft/wizardlm-2-7b Stopped working
- koboldai/llama2-13b-tiefighter Stopped working
- cognitivecomputations/dolphin-2.6-mixtral-8x7b Stopped working
- cognitivecomputations/dolphin-2.9.1-llama-3-70b Stopped working
- qwen/qwen2-72b-instruct Stopped working
- austism/chronos-hermes-13b-v2 Stopped working
- compvis/stable-diffusion-v1-4 Stopped working
- runwayml/stable-diffusion-v1-5 Stopped working
- stabilityai/stable-diffusion-2-1 Stopped working
- xpuct/deliberate Stopped working
- openai/whisper-base Stopped working
- openai/whisper-base.en Stopped working
- openai/whisper-medium.en Stopped working
- openai/whisper-small.en Stopped working
- openai/whisper-timestamped-medium Stopped working
- openai/whisper-timestamped-medium.en Stopped working
- openai/whisper-tiny.en Stopped working
- gryphe/mythomax-l2-13b-turbo Stopped working
Know before your API calls break.
Okapi finds the calls a breaking change hits in your code and opens the pull request that fixes them.
Add to GitHub