110 new model IDs added to LiteLLM's catalog, including new Claude 3.5/3.7 Sonnet, NVIDIA

EXHIBIT 2483 · FLASH

Nov 4, 2026 22:12 UTC model_catalog litellm model catalog

110 new model IDs added to LiteLLM's catalog, including new Claude 3.5/3.7 Sonnet, NVIDIA Nemotron, Qwen3/3.5/3.6/3.7/3.8, DeepSeek, and models from MiniMaxAI, MoonshotAI, XiaomiMiMo, Stepfun-ai, and Tencent.

READY TO POST:

litellm just added 110 new model ids! 👀 including claude 3.5 sonnet, nvidia nemotron, and a ton of new qwen, minimaxai, and deepseek models. builder beware, time to update your config.

whoa, massive litellm model catalog update. spotted some new claude 3.7 sonnet models, plus a bunch of nvidia nemotron and qwen variants. looks like a lot more options for ai apps.

Model catalog: 110 new model ids appeared across cloud providers [watched families / cloud] (102) + bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0 + bedrock/us-gov-east-1/anthropic.claude-3-7-sonnet-20250219-v1:0 + bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0 + bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0 + bedrock_mantle/us-gov-east-1/moonshotai.kimi-k3 + bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-12b-v2 + bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-3-30b + bedrock_mantle/us-gov-east-1/nvidia.nemotron-nano-9b-v2 + bedrock_mantle/us-gov-east-1/nvidia.nemotron-super-3-120b + bedrock_mantle/us-gov-west-1/moonshotai.kimi-k3 + bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-12b-v2 + bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-3-30b + bedrock_mantle/us-gov-west-1/nvidia.nemotron-nano-9b-v2 + bedrock_mantle/us-gov-west-1/nvidia.nemotron-super-3-120b + gmi/MiniMaxAI/MiniMax-M2 + gmi/MiniMaxAI/MiniMax-M2.5 + gmi/MiniMaxAI/MiniMax-M2.7 + gmi/MiniMaxAI/MiniMax-M3 + gmi/MiniMaxAI/MiniMax-M3.1-Flash + gmi/Qwen/Qwen3-235B-A22B-FP8 + gmi/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 + gmi/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8 + gmi/Qwen/Qwen3-30B-A3B + gmi/Qwen/Qwen3-32B-FP8 + gmi/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 + gmi/Qwen/Qwen3-Next-80B-A3B-Instruct + gmi/Qwen/Qwen3-Next-80B-A3B-Thinking + gmi/Qwen/Qwen3.5-122B-A10B + gmi/Qwen/Qwen3.5-27B + gmi/Qwen/Qwen3.5-35B-A3B + gmi/Qwen/Qwen3.5-397B-A17B + gmi/Qwen/Qwen3.6-35B-A3B + gmi/Qwen/Qwen3.6-Plus + gmi/Qwen/Qwen3.6-Plus-2026-04-02 + gmi/Qwen/Qwen3.7-Max + gmi/Qwen/Qwen3.8-27B + gmi/Qwen/Qwen3.8-Flash + gmi/Qwen/Qwen3.8-Max + gmi/Qwen/Qwen3.8-Max-0902 + gmi/deepseek-ai/DeepSeek-Prover-V2-671B [other providers] (8) + gmi/XiaomiMiMo/MiMo-V2.5 + gmi/XiaomiMiMo/MiMo-V2.5-Pro + gmi/stepfun-ai/Step-3.7-Flash + gmi/stepfun-ai/Step-5-Preview + gmi/tencent/HunyuanOCR + gmi