LiteLLMModels

New AI models in September 2025

28 models were added to LiteLLM's price file in September 2025, newest first, with each one's headline price and context window.

AddedModelLabPriceContextProviders
September 2025Codestral EmbedMistral AI$0.15 per 1M tokens8K2
September 2025Doubao EmbeddingByteDanceFree4K1
September 2025Doubao Embedding LargeByteDanceFree4K1
September 2025Doubao Embedding Large Text 240915ByteDanceFree4K1
September 2025Doubao Embedding Large Text 250515ByteDanceFree4K1
September 2025Doubao Embedding Text 240715ByteDanceFree4K1
September 2025GPT Realtime deprecatedOpenAI$4 / $16 per 1M tokens32K2
September 2025GPT-5 Codex deprecatedOpenAI$1.25 / $10 per 1M tokens272K2
September 2025Grok 4 FastxAI$5 / $25 per 1M tokens128K1
September 2025Grok 4 Fast Non Reasoning retiredxAI$0.20 / $0.50 per 1M tokens–1
September 2025Grok 4 Fast Reasoning retiredxAI$0.20 / $0.50 per 1M tokens–1
September 2025Grok Code FastxAI$1 / $2 per 1M tokens256K1
September 2025Grok Code Fast 1xAI$1 / $2 per 1M tokens256K3
September 2025Llava V1.6 Mistral 7B HF–$0.29 / $0.29 per 1M tokens32K1
September 2025Mamba Codestral 7B V0.1–$0.19 / $0.19 per 1M tokens256K1
September 2025Marengo Embed 2.7 deprecated––771
September 2025Pegasus 1.2 deprecated–––1
September 2025Qwen CoderAlibaba$0.30 / $1.50 per 1M tokens1M3
September 2025Qwen FlashAlibaba–998K3
September 2025Qwen3 Coder 30B A3B deprecatedAlibaba$0.15 / $0.60 per 1M tokens256K2
September 2025Qwen3 Coder 480B A35B deprecatedAlibaba$0.45 / $1.80 per 1M tokens256K1
September 2025Qwen3 Coder FlashAlibaba–998K3
September 2025Qwen3 Coder PlusAlibaba–998K3
September 2025Qwen3 Max PreviewAlibaba–252K3
September 2025Qwen3 Next 80B A3B InstructAlibaba$0.15 / $1.20 per 1M tokens256K10
September 2025Qwen3 Next 80B A3B ThinkingAlibaba$0.15 / $1.20 per 1M tokens256K9
September 2025QwQ PlusAlibaba$0.80 / $2.40 per 1M tokens96K3
September 2025Veo 2.0 Generate 001Google$0.50 per second1K1