Okapi Okapi

DeepInfra

DeepInfra model deprecations

199 models DeepInfra deprecated or shut down, read from its own pages.

Deprecated, no shutdown date yet 22

  1. No date deepseek-ai/deepseek-v3-0324Model retirement Deprecated, no date
  2. No date google/gemma-4-e4b-itModel retirement Deprecated, no date
  3. No date meta-llama/llama-4-maverick-17b-128e-instruct-fp8Model retirement Deprecated, no date
  4. No date minimaxai/minimax-m2.5Model retirement Deprecated, no date
  5. No date minimaxai/minimax-m2.7Model retirement Deprecated, no date
  6. No date moonshotai/kimi-k2.5Model retirement Deprecated, no date
  7. No date moonshotai/kimi-k2.7-codeModel retirement Deprecated, no date
  8. No date nvidia/llama-3.3-nemotron-super-49b-v1.5Model retirement Deprecated, no date
  9. No date nvidia/nemotron-3-nano-30b-a3bModel retirement Deprecated, no date
  10. No date nvidia/nemotron-3-nano-omni-30b-a3b-reasoningModel retirement Deprecated, no date
  11. No date qwen/qwen3-maxModel retirement Deprecated, no date
  12. No date qwen/qwen3.5-122b-a10bModel retirement Deprecated, no date
  13. No date qwen/qwen3.8-2.4t-a95bModel retirement Deprecated, no date
  14. No date stepfun-ai/step-3.7-flashModel retirement Deprecated, no date
  15. No date stepfun-ai/step-5-previewModel retirement Deprecated, no date
  16. No date tencent/hy3Model retirement Deprecated, no date
  17. No date thinkingmachines/inklingModel retirement Deprecated, no date
  18. No date xiaomimimo/mimo-v2.5Model retirement Deprecated, no date
  19. No date xiaomimimo/mimo-v2.5-proModel retirement Deprecated, no date
  20. No date zai-org/glm-4.7-flashModel retirement Deprecated, no date
  21. No date zai-org/glm-5Model retirement Deprecated, no date
  22. No date zai-org/glm-5.1Model retirement Deprecated, no date

Retired 177

  1. bigcode/starcoder2-15b-instruct-v0.1Model retirement Stopped working
  2. mattshumer/reflection-llama-3.1-70bModel retirement Stopped working
  3. meta-llama/llama-2-70b-chat-hfModel retirement Stopped working
  4. meta-llama/meta-llama-3-70b-instructModel retirement Stopped working
  5. meta-llama/meta-llama-3.1-70b-instructModel retirement Stopped working
  6. meta-llama/meta-llama-3.1-70b-instruct-turboModel retirement Stopped working
  7. phind/phind-codellama-34b-v2Model retirement Stopped working
  8. meta-llama/meta-llama-3.1-405b-instructModel retirement Stopped working
  9. nousresearch/hermes-3-llama-3.1-405bModel retirement Stopped working
  10. nousresearch/hermes-3-llama-3.1-70bModel retirement Stopped working
  11. nvidia/nemotron-4-340b-instructModel retirement Stopped working
  12. austism/chronos-hermes-13b-v2Model retirement Stopped working
  13. gryphe/mythomax-l2-13bModel retirement Stopped working
  14. gryphe/mythomax-l2-13b-turboModel retirement Stopped working
  15. koboldai/llama2-13b-tiefighterModel retirement Stopped working
  16. stepfun-ai/step-5-previewModel retirement Stopped working
  17. bria/fiboModel retirement Stopped working
  18. bria/fibo-1.5Model retirement Stopped working
  19. black-forest-labs/flux-1-redux-devModel retirement Stopped working
  20. thinkingmachines/inklingModel retirement Stopped working
  21. openai/gpt-oss-120b-turboModel retirement Stopped working
  22. ibm-granite/granite-4.2-30bModel retirement Stopped working
  23. ibm-granite/granite-4.2-3bModel retirement Stopped working
  24. qwen/qwen3.8-2.4t-a95bModel retirement Stopped working
  25. qwen/qwen3-maxModel retirement Stopped working
  26. qwen/qwen3-max-thinkingModel retirement Stopped working
  27. inclusionai/ling-3.0-flash-finModel retirement Stopped working
  28. black-forest-labs/flux.1-kontext-devModel retirement Stopped working
  29. deepseek-ai/janus-pro-1bModel retirement Stopped working
  30. deepseek-ai/janus-pro-7bModel retirement Stopped working
  31. nvidia/nemotron-3-nano-30b-a3bModel retirement Stopped working
  32. nvidia/nvidia-nemotron-nano-9b-v2Model retirement Stopped working
  33. qwen/qwen-image-editModel retirement Stopped working
  34. tencent/hy3Model retirement Stopped working
  35. nvidia/cosmos3-nanoModel retirement Stopped working
  36. nvidia/cosmos3-superModel retirement Stopped working
  37. google/gemma-4-e4b-itModel retirement Stopped working
  38. meta-llama/llama-3.2-90b-vision-instructModel retirement Stopped working
  39. meta-llama/llama-4-maverick-17b-128e-instruct-fp8Model retirement Stopped working
  40. meta-llama/llama-4-maverick-17b-128e-instruct-turboModel retirement Stopped working
  41. qwen/qvq-72b-previewModel retirement Stopped working
  42. qwen/qwen3.5-122b-a10bModel retirement Stopped working
  43. stepfun-ai/step-3.5-flashModel retirement Stopped working
  44. stepfun-ai/step-3.7-flashModel retirement Stopped working
  45. zai-org/glm-5.1Model retirement Stopped working
  46. minimaxai/minimax-m2.7-turboModel retirement Stopped working
  47. deepseek-ai/deepseek-prover-v2-671bModel retirement Stopped working
  48. deepseek-ai/deepseek-v3-0324Model retirement Stopped working
  49. deepseek-ai/deepseek-v3-0324-turboModel retirement Stopped working
  50. moonshotai/kimi-k2.7-codeModel retirement Stopped working
  51. xiaomimimo/mimo-v2.5Model retirement Stopped working
  52. xiaomimimo/mimo-v2.5-proModel retirement Stopped working
  53. nvidia/nemotron-3-diarization-previewModel retirement Stopped working
  54. minimaxai/minimax-m2Model retirement Stopped working
  55. minimaxai/minimax-m2.1Model retirement Stopped working
  56. minimaxai/minimax-m2.5Model retirement Stopped working
  57. minimaxai/minimax-m2.7Model retirement Stopped working
  58. zai-org/glm-4.7-flashModel retirement Stopped working
  59. zai-org/glm-5Model retirement Stopped working
  60. moonshotai/kimi-k2-instructModel retirement Stopped working
  61. moonshotai/kimi-k2-instruct-0905Model retirement Stopped working
  62. moonshotai/kimi-k2-thinkingModel retirement Stopped working
  63. moonshotai/kimi-k2.5Model retirement Stopped working
  64. moonshotai/kimi-k2.5-turboModel retirement Stopped working
  65. qwen/qwen3-235b-a22b-thinking-2507Model retirement Stopped working
  66. deepseek-ai/deepseek-v3.1-terminusModel retirement Stopped working
  67. deepreinforce-ai/ornith-1.0-35bModel retirement Stopped working
  68. meta-llama/llama-3.2-11b-vision-instructModel retirement Stopped working
  69. meta-llama/llama-3.2-1b-instructModel retirement Stopped working
  70. meta-llama/llama-3.2-3b-instructModel retirement Stopped working
  71. nvidia/llama-3.3-nemotron-super-49b-v1.5Model retirement Stopped working
  72. openbmb/minicpm-llama3-v-2_5Model retirement Stopped working
  73. meta-llama/meta-llama-3.1-8b-instructModel retirement Stopped working
  74. microsoft/phi-3-medium-4k-instructModel retirement Stopped working
  75. nvidia/llama-3.1-nemotron-70b-instructModel retirement Stopped working
  76. nvidia/nemotron-3-nano-omni-30b-a3b-reasoningModel retirement Stopped working
  77. nvidia/nvidia-nemotron-nano-12b-v2-vlModel retirement Stopped working
  78. openchat/openchat_3.5Model retirement Stopped working
  79. openchat/openchat-3.6-8bModel retirement Stopped working
  80. qwen/qwen3-embedding-0.6b-batchModel retirement Stopped working
  81. qwen/qwen3-embedding-4b-batchModel retirement Stopped working
  82. qwen/qwen3-embedding-8b-batchModel retirement Stopped working
  83. nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16Model retirement Stopped working
  84. fastvideo/ltx2-distilled-diffusersModel retirement Stopped working
  85. deepseek-ai/deepseek-r1-distill-llama-70bModel retirement Stopped working
  86. deepseek-ai/deepseek-r1-distill-qwen-32bModel retirement Stopped working
  87. qwen/qwen3.5-0.8bModel retirement Stopped working
  88. qwen/qwen3.5-2bModel retirement Stopped working
  89. qwen/qwen3.5-4bModel retirement Stopped working
  90. qwen/qwq-32b-previewModel retirement Stopped working
  91. deepseek-ai/deepseek-r1-0528-turboModel retirement Stopped working
  92. anthropic/claude-3-7-sonnet-latestModel retirement Stopped working
  93. anthropic/claude-4-opusModel retirement Stopped working
  94. anthropic/claude-4-sonnetModel retirement Stopped working
  95. google/veo-3.0Model retirement Stopped working
  96. google/veo-3.0-fastModel retirement Stopped working
  97. zyphra/zonos-v0.1-hybridModel retirement Stopped working
  98. zyphra/zonos-v0.1-transformerModel retirement Stopped working
  99. allenai/olmo-3.1-32b-instructModel retirement Stopped working
  100. allenai/olmocr-2Model retirement Stopped working
  101. allenai/olmocr-2-7b-1025Model retirement Stopped working
  102. allenai/olmocr-7b-0725-fp8Model retirement Stopped working
  103. allenai/olmocr-7b-0825Model retirement Stopped working
  104. allenai/olmocr-7b-1025Model retirement Stopped working
  105. deepseek-ai/deepseek-ocrModel retirement Stopped working
  106. meta-llama/llama-2-13b-chat-hfModel retirement Stopped working
  107. meta-llama/meta-llama-3-8b-instructModel retirement Stopped working
  108. mistralai/mixtral-8x7b-instruct-v0.1Model retirement Stopped working
  109. paddlepaddle/paddleocr-vl-0.9bModel retirement Stopped working
  110. sao10k/l3.3-70b-euryale-v2.3Model retirement Stopped working
  111. inworld-ai/inworld-tts-1.5-maxModel retirement Stopped working
  112. inworld-ai/inworld-tts-1.5-miniModel retirement Stopped working
  113. qwen/qwen3-coder-480b-a35b-instructModel retirement Stopped working
  114. zai-org/glm-4.6vModel retirement Stopped working
  115. qwen/qwen2.5-vl-32b-instructModel retirement Stopped working
  116. wan-ai/wan2.1-t2v-1.3bModel retirement Stopped working
  117. wan-ai/wan2.1-t2v-14bModel retirement Stopped working
  118. resembleai/chatterboxModel retirement Stopped working
  119. microsoft/wizardlm-2-8x22bModel retirement Stopped working
  120. mistralai/mixtral-8x22b-instruct-v0.1Model retirement Stopped working
  121. google/gemini-2.0-flash-001Model retirement Stopped working
  122. deepseek-ai/deepseek-r1Model retirement Stopped working
  123. deepseek-ai/deepseek-r1-turboModel retirement Stopped working
  124. deepseek-ai/deepseek-v3.2-expModel retirement Stopped working
  125. qwen/qwen3-coder-30b-a3b-instructModel retirement Stopped working
  126. meta-llama/llama-guard-3-8bModel retirement Stopped working
  127. qwen/qwen3-vl-30b-a3b-thinkingModel retirement Stopped working
  128. qwen/qwen3-vl-4b-instructModel retirement Stopped working
  129. qwen/qwen3-vl-4b-thinkingModel retirement Stopped working
  130. qwen/qwen3-vl-8b-instructModel retirement Stopped working
  131. qwen/qwen3-vl-8b-thinkingModel retirement Stopped working
  132. deepinfra/airoboros-70bModel retirement Stopped working
  133. lizpreciatior/lzlv_70b_fp16_hfModel retirement Stopped working
  134. meta-llama/llama-3.3-70b-instructModel retirement Stopped working
  135. qwen/qwen2-7b-instructModel retirement Stopped working
  136. qwen/qwen2.5-7b-instructModel retirement Stopped working
  137. qwen/qwen2.5-coder-7bModel retirement Stopped working
  138. qwen/qwen3-vl-235b-a22b-thinkingModel retirement Stopped working
  139. qwen/qwq-32bModel retirement Stopped working
  140. zai-org/glm-4.5Model retirement Stopped working
  141. stabilityai/sd3.5Model retirement Stopped working
  142. stabilityai/sd3.5-mediumModel retirement Stopped working
  143. qwen/qwen3-235b-a22bModel retirement Stopped working
  144. zai-org/glm-4.5-airModel retirement Stopped working
  145. mistralai/mistral-7b-instruct-v0.1Model retirement Stopped working
  146. mistralai/mistral-7b-instruct-v0.2Model retirement Stopped working
  147. mistralai/mistral-7b-instruct-v0.3Model retirement Stopped working
  148. mistralai/devstral-small-2505Model retirement Stopped working
  149. mistralai/devstral-small-2507Model retirement Stopped working
  150. mistralai/mistral-small-3.1-24b-instruct-2503Model retirement Stopped working
  151. qwen/qwen2.5-coder-32b-instructModel retirement Stopped working
  152. microsoft/phi-4-multimodal-instructModel retirement Stopped working
  153. microsoft/phi-4-reasoning-plusModel retirement Stopped working
  154. novasky-ai/sky-t1-32b-previewModel retirement Stopped working
  155. run-diffusion/juggernaut-fluxModel retirement Stopped working
  156. run-diffusion/juggernaut-lightning-fluxModel retirement Stopped working
  157. google/codegemma-7b-itModel retirement Stopped working
  158. google/gemma-1.1-7b-itModel retirement Stopped working
  159. google/gemma-2-27b-itModel retirement Stopped working
  160. google/gemma-2-9b-itModel retirement Stopped working
  161. sao10k/l3-70b-euryale-v2.1Model retirement Stopped working
  162. sao10k/l3-8b-lunaris-v1Model retirement Stopped working
  163. microsoft/wizardlm-2-7bModel retirement Stopped working
  164. cognitivecomputations/dolphin-2.6-mixtral-8x7bModel retirement Stopped working
  165. cognitivecomputations/dolphin-2.9.1-llama-3-70bModel retirement Stopped working
  166. qwen/qwen2-72b-instructModel retirement Stopped working
  167. compvis/stable-diffusion-v1-4Model retirement Stopped working
  168. runwayml/stable-diffusion-v1-5Model retirement Stopped working
  169. stabilityai/stable-diffusion-2-1Model retirement Stopped working
  170. xpuct/deliberateModel retirement Stopped working
  171. openai/whisper-baseModel retirement Stopped working
  172. openai/whisper-base.enModel retirement Stopped working
  173. openai/whisper-medium.enModel retirement Stopped working
  174. openai/whisper-small.enModel retirement Stopped working
  175. openai/whisper-timestamped-mediumModel retirement Stopped working
  176. openai/whisper-timestamped-medium.enModel retirement Stopped working
  177. openai/whisper-tiny.enModel retirement 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