Okapi Okapi

DeepInfra

DeepInfra model deprecations

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

Shutting down soon 4

  1. bria/fibo Stops workingin 5 days
  2. bria/fibo-1.5 Stops workingin 5 days
  3. nousresearch/hermes-3-llama-3.1-405b Stops workingin 11 days
  4. nousresearch/hermes-3-llama-3.1-70b Stops workingin 11 days

Deprecated, no shutdown date yet 20

  1. No date deepseek-ai/deepseek-v3-0324 Deprecated, no date
  2. No date google/gemma-4-e4b-it Deprecated, no date
  3. No date meta-llama/llama-4-maverick-17b-128e-instruct-fp8 Deprecated, no date
  4. No date minimaxai/minimax-m2.5 Deprecated, no date
  5. No date minimaxai/minimax-m2.7 Deprecated, no date
  6. No date moonshotai/kimi-k2.5 Deprecated, no date
  7. No date moonshotai/kimi-k2.7-code Deprecated, no date
  8. No date nvidia/llama-3.3-nemotron-super-49b-v1.5 Deprecated, no date
  9. No date nvidia/nemotron-3-nano-30b-a3b Deprecated, no date
  10. No date nvidia/nemotron-3-nano-omni-30b-a3b-reasoning Deprecated, no date
  11. No date qwen/qwen3-max Deprecated, no date
  12. No date qwen/qwen3.5-122b-a10b Deprecated, no date
  13. No date qwen/qwen3.8-2.4t-a95b Deprecated, no date
  14. No date stepfun-ai/step-3.7-flash Deprecated, no date
  15. No date tencent/hy3 Deprecated, no date
  16. No date xiaomimimo/mimo-v2.5 Deprecated, no date
  17. No date xiaomimimo/mimo-v2.5-pro Deprecated, no date
  18. No date zai-org/glm-4.7-flash Deprecated, no date
  19. No date zai-org/glm-5 Deprecated, no date
  20. No date zai-org/glm-5.1 Deprecated, no date

Retired 170

  1. thinkingmachines/inkling Stopped working
  2. openai/gpt-oss-120b-turbo Stopped working
  3. ibm-granite/granite-4.2-30b Stopped working
  4. ibm-granite/granite-4.2-3b Stopped working
  5. qwen/qwen3.8-2.4t-a95b Stopped working
  6. qwen/qwen3-max Stopped working
  7. qwen/qwen3-max-thinking Stopped working
  8. inclusionai/ling-3.0-flash-fin Stopped working
  9. black-forest-labs/flux-1-redux-dev Stopped working
  10. black-forest-labs/flux.1-kontext-dev Stopped working
  11. deepseek-ai/janus-pro-1b Stopped working
  12. deepseek-ai/janus-pro-7b Stopped working
  13. nvidia/nemotron-3-nano-30b-a3b Stopped working
  14. nvidia/nvidia-nemotron-nano-9b-v2 Stopped working
  15. qwen/qwen-image-edit Stopped working
  16. tencent/hy3 Stopped working
  17. nvidia/cosmos3-nano Stopped working
  18. nvidia/cosmos3-super Stopped working
  19. google/gemma-4-e4b-it Stopped working
  20. meta-llama/llama-3.2-90b-vision-instruct Stopped working
  21. meta-llama/llama-4-maverick-17b-128e-instruct-fp8 Stopped working
  22. meta-llama/llama-4-maverick-17b-128e-instruct-turbo Stopped working
  23. qwen/qvq-72b-preview Stopped working
  24. qwen/qwen3.5-122b-a10b Stopped working
  25. stepfun-ai/step-3.5-flash Stopped working
  26. stepfun-ai/step-3.7-flash Stopped working
  27. zai-org/glm-5.1 Stopped working
  28. minimaxai/minimax-m2.7-turbo Stopped working
  29. deepseek-ai/deepseek-prover-v2-671b Stopped working
  30. deepseek-ai/deepseek-v3-0324 Stopped working
  31. deepseek-ai/deepseek-v3-0324-turbo Stopped working
  32. moonshotai/kimi-k2.7-code Stopped working
  33. xiaomimimo/mimo-v2.5 Stopped working
  34. xiaomimimo/mimo-v2.5-pro Stopped working
  35. nvidia/nemotron-3-diarization-preview Stopped working
  36. minimaxai/minimax-m2 Stopped working
  37. minimaxai/minimax-m2.1 Stopped working
  38. minimaxai/minimax-m2.5 Stopped working
  39. minimaxai/minimax-m2.7 Stopped working
  40. zai-org/glm-4.7-flash Stopped working
  41. zai-org/glm-5 Stopped working
  42. moonshotai/kimi-k2-instruct Stopped working
  43. moonshotai/kimi-k2-instruct-0905 Stopped working
  44. moonshotai/kimi-k2-thinking Stopped working
  45. moonshotai/kimi-k2.5 Stopped working
  46. moonshotai/kimi-k2.5-turbo Stopped working
  47. qwen/qwen3-235b-a22b-thinking-2507 Stopped working
  48. deepseek-ai/deepseek-v3.1-terminus Stopped working
  49. deepreinforce-ai/ornith-1.0-35b Stopped working
  50. meta-llama/llama-3.2-11b-vision-instruct Stopped working
  51. meta-llama/llama-3.2-1b-instruct Stopped working
  52. meta-llama/llama-3.2-3b-instruct Stopped working
  53. nvidia/llama-3.3-nemotron-super-49b-v1.5 Stopped working
  54. openbmb/minicpm-llama3-v-2_5 Stopped working
  55. meta-llama/meta-llama-3.1-8b-instruct Stopped working
  56. microsoft/phi-3-medium-4k-instruct Stopped working
  57. nvidia/llama-3.1-nemotron-70b-instruct Stopped working
  58. nvidia/nemotron-3-nano-omni-30b-a3b-reasoning Stopped working
  59. nvidia/nvidia-nemotron-nano-12b-v2-vl Stopped working
  60. openchat/openchat_3.5 Stopped working
  61. openchat/openchat-3.6-8b Stopped working
  62. qwen/qwen3-embedding-0.6b-batch Stopped working
  63. qwen/qwen3-embedding-4b-batch Stopped working
  64. qwen/qwen3-embedding-8b-batch Stopped working
  65. nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16 Stopped working
  66. fastvideo/ltx2-distilled-diffusers Stopped working
  67. bigcode/starcoder2-15b-instruct-v0.1 Stopped working
  68. deepseek-ai/deepseek-r1-distill-llama-70b Stopped working
  69. deepseek-ai/deepseek-r1-distill-qwen-32b Stopped working
  70. mattshumer/reflection-llama-3.1-70b Stopped working
  71. meta-llama/meta-llama-3.1-70b-instruct Stopped working
  72. phind/phind-codellama-34b-v2 Stopped working
  73. qwen/qwen3.5-0.8b Stopped working
  74. qwen/qwen3.5-2b Stopped working
  75. qwen/qwen3.5-4b Stopped working
  76. qwen/qwq-32b-preview Stopped working
  77. deepseek-ai/deepseek-r1-0528-turbo Stopped working
  78. anthropic/claude-3-7-sonnet-latest Stopped working
  79. anthropic/claude-4-opus Stopped working
  80. anthropic/claude-4-sonnet Stopped working
  81. google/veo-3.0 Stopped working
  82. google/veo-3.0-fast Stopped working
  83. zyphra/zonos-v0.1-hybrid Stopped working
  84. zyphra/zonos-v0.1-transformer Stopped working
  85. allenai/olmo-3.1-32b-instruct Stopped working
  86. allenai/olmocr-2 Stopped working
  87. allenai/olmocr-2-7b-1025 Stopped working
  88. allenai/olmocr-7b-0725-fp8 Stopped working
  89. allenai/olmocr-7b-0825 Stopped working
  90. allenai/olmocr-7b-1025 Stopped working
  91. deepseek-ai/deepseek-ocr Stopped working
  92. meta-llama/llama-2-13b-chat-hf Stopped working
  93. meta-llama/meta-llama-3-8b-instruct Stopped working
  94. mistralai/mixtral-8x7b-instruct-v0.1 Stopped working
  95. paddlepaddle/paddleocr-vl-0.9b Stopped working
  96. sao10k/l3.3-70b-euryale-v2.3 Stopped working
  97. inworld-ai/inworld-tts-1.5-max Stopped working
  98. inworld-ai/inworld-tts-1.5-mini Stopped working
  99. qwen/qwen3-coder-480b-a35b-instruct Stopped working
  100. zai-org/glm-4.6v Stopped working
  101. qwen/qwen2.5-vl-32b-instruct Stopped working
  102. wan-ai/wan2.1-t2v-1.3b Stopped working
  103. wan-ai/wan2.1-t2v-14b Stopped working
  104. resembleai/chatterbox Stopped working
  105. microsoft/wizardlm-2-8x22b Stopped working
  106. mistralai/mixtral-8x22b-instruct-v0.1 Stopped working
  107. google/gemini-2.0-flash-001 Stopped working
  108. deepseek-ai/deepseek-r1 Stopped working
  109. deepseek-ai/deepseek-r1-turbo Stopped working
  110. deepseek-ai/deepseek-v3.2-exp Stopped working
  111. qwen/qwen3-coder-30b-a3b-instruct Stopped working
  112. meta-llama/llama-guard-3-8b Stopped working
  113. qwen/qwen3-vl-30b-a3b-thinking Stopped working
  114. qwen/qwen3-vl-4b-instruct Stopped working
  115. qwen/qwen3-vl-4b-thinking Stopped working
  116. qwen/qwen3-vl-8b-instruct Stopped working
  117. qwen/qwen3-vl-8b-thinking Stopped working
  118. deepinfra/airoboros-70b Stopped working
  119. lizpreciatior/lzlv_70b_fp16_hf Stopped working
  120. meta-llama/llama-3.3-70b-instruct Stopped working
  121. qwen/qwen2-7b-instruct Stopped working
  122. qwen/qwen2.5-7b-instruct Stopped working
  123. qwen/qwen2.5-coder-7b Stopped working
  124. qwen/qwen3-vl-235b-a22b-thinking Stopped working
  125. qwen/qwq-32b Stopped working
  126. zai-org/glm-4.5 Stopped working
  127. stabilityai/sd3.5 Stopped working
  128. stabilityai/sd3.5-medium Stopped working
  129. qwen/qwen3-235b-a22b Stopped working
  130. zai-org/glm-4.5-air Stopped working
  131. mistralai/mistral-7b-instruct-v0.1 Stopped working
  132. mistralai/mistral-7b-instruct-v0.2 Stopped working
  133. mistralai/mistral-7b-instruct-v0.3 Stopped working
  134. meta-llama/llama-2-70b-chat-hf Stopped working
  135. meta-llama/meta-llama-3-70b-instruct Stopped working
  136. mistralai/devstral-small-2505 Stopped working
  137. mistralai/devstral-small-2507 Stopped working
  138. mistralai/mistral-small-3.1-24b-instruct-2503 Stopped working
  139. qwen/qwen2.5-coder-32b-instruct Stopped working
  140. microsoft/phi-4-multimodal-instruct Stopped working
  141. microsoft/phi-4-reasoning-plus Stopped working
  142. novasky-ai/sky-t1-32b-preview Stopped working
  143. meta-llama/meta-llama-3.1-405b-instruct Stopped working
  144. nvidia/nemotron-4-340b-instruct Stopped working
  145. run-diffusion/juggernaut-flux Stopped working
  146. run-diffusion/juggernaut-lightning-flux Stopped working
  147. google/codegemma-7b-it Stopped working
  148. google/gemma-1.1-7b-it Stopped working
  149. google/gemma-2-27b-it Stopped working
  150. google/gemma-2-9b-it Stopped working
  151. sao10k/l3-70b-euryale-v2.1 Stopped working
  152. sao10k/l3-8b-lunaris-v1 Stopped working
  153. microsoft/wizardlm-2-7b Stopped working
  154. koboldai/llama2-13b-tiefighter Stopped working
  155. cognitivecomputations/dolphin-2.6-mixtral-8x7b Stopped working
  156. cognitivecomputations/dolphin-2.9.1-llama-3-70b Stopped working
  157. qwen/qwen2-72b-instruct Stopped working
  158. austism/chronos-hermes-13b-v2 Stopped working
  159. compvis/stable-diffusion-v1-4 Stopped working
  160. runwayml/stable-diffusion-v1-5 Stopped working
  161. stabilityai/stable-diffusion-2-1 Stopped working
  162. xpuct/deliberate Stopped working
  163. openai/whisper-base Stopped working
  164. openai/whisper-base.en Stopped working
  165. openai/whisper-medium.en Stopped working
  166. openai/whisper-small.en Stopped working
  167. openai/whisper-timestamped-medium Stopped working
  168. openai/whisper-timestamped-medium.en Stopped working
  169. openai/whisper-tiny.en Stopped working
  170. 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