Skip to main content
​
2026-02-16
Deprecated qwen-3-32b and llama-3.3-70bWe recommend migrating to GPT OSS 120B.
Migration Notes:
  • Qwen 3 32B had reasoning enabled by default. GPT OSS supports configurable reasoning via the reasoning_effort parameter. Review the Reasoning documentation before migrating.
  • Legacy strict mode (constrained decoding) behavior on llama-3.3-70b differs slightly from current Production and Preview models. Review the Structured Outputs and Tool Use documentation before migrating requests using tools and/or response_format in strict mode.
​
2026-01-20
Deprecated zai-glm-4.6We recommend migrating to Z.ai GLM 4.7.
​
2025-11-14
Deprecated qwen-3-235b-a22b-thinking-2507We recommend migrating to GPT OSS 120B.
​
2025-11-05
Deprecated qwen-3-coder-480bWe recommend migrating to Z.ai GLM 4.7.
​
2025-11-03
Deprecated llama-4-scout-17b-16e-instructWe recommend migrating to GPT OSS 120B or Llama 3.3 70B.
​
2025-10-15
Deprecated llama-4-maverick-17b-128e-instructWe recommend migrating to GPT OSS 120B or Llama 3.3 70B.
​
2025-08-12
Deprecated deepseek-r1-distill-llama-70bWe recommend migrating to Qwen 3 32B.
​
2025-07-29
Deprecated qwen-3-235b-a22bWe recommend migrating to either Qwen 3 235B Instruct or Qwen 3 235B Thinking.
​
2025-01-17
The llama3.1-70b model has been deprecated. We recommend transitioning to llama-3.3-70b, a more powerful model released by Meta.