28 new model IDs added to LiteLLM's catalog, including several gpt-5.6 and gpt-6 entries,

EXHIBIT 1338 · FLASH

Sep 13, 2026 02:29 UTC model_catalog litellm model catalog

28 new model IDs added to LiteLLM's catalog, including several gpt-5.6 and gpt-6 entries, new DeepSeek, Qwen, Mistral, and NVIDIA models, and a Meta voice transcribe model.

READY TO POST:

litellm just added a ton of new models, including multiple gpt-5.6 and gpt-6 entries on openrouter, plus new deepseek, qwen, and mistral variants. interesting to see those gpt IDs pop up.

new models are hitting litellm's catalog! notable additions include nvidia's nemotron nano, deepseek-v4p1-flash, and a meta muse-voice-transcribe model. always good to see more options.

Model catalog: 28 new model ids appeared across cloud providers [watched families / cloud] (21) + cerebras/qwen-3.8-27b + fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash + fireworks_ai/deepseek-v4p1-flash + gpt-live-1 + openrouter/deepseek/deepseek-v4.1-flash + openrouter/openai/gpt-5.6-luna-pro + openrouter/openai/gpt-5.6-sol-pro + openrouter/openai/gpt-5.6-terra-pro + openrouter/openai/gpt-6-astra-pro + openrouter/qwen/qwen3.8-max-0902 + together_ai/MiniMaxAI/MiniMax-M2.7 + together_ai/Qwen/Qwen3-Coder-Next-FP8 + together_ai/Qwen/Qwen3-VL-32B-Instruct + together_ai/Qwen/Qwen3-VL-8B-Instruct + together_ai/deepseek-ai/DeepSeek-R1-0528 + together_ai/mistralai/Mistral-7B-Instruct-v0.3 + together_ai/moonshotai/Kimi-K2.5-fp4 + together_ai/moonshotai/Kimi-K2.6 + together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2 + together_ai/zai-org/GLM-5 + together_ai/zai-org/GLM-5.1 [other providers] (7) + deepseek-flash + deepseek/deepseek-flash + inception/mercury-2.5 + meta/muse-voice-transcribe-1.0 + openrouter/openai/gpt-chat-latest + together_ai/Qwen/QwQ-32B + together_ai/mistralai/Ministral-3-14B-Instruct-2512