LiteLLMModels

New AI models in June 2026

53 models were added to LiteLLM's price file in June 2026, newest first, with each one's headline price and context window.

AddedModelLabPriceContextProviders
Claude Sonnet 5Anthropic$2 / $10 per 1M tokens1M9
Gemini 3 Pro ImageGoogle$0.134 per image64K3
Gemini 3.1 Flash ImageGoogle$0.045 per image128K4
Mistral Ocr 4.0 deprecatedMistral AI$4.00 per 1K pages–2
Titan Embed G1 Text 02Amazon$0.10 per 1M tokens8K1
June 2026Arctic Embed L V2.0–$0.07 per 1M tokens8K1
June 2026Arctic Embed M V2.0–$0.07 per 1M tokens8K1
June 2026Claude Fable 5Anthropic$10 / $50 per 1M tokens1M9
June 2026Claude Opus 4.8Anthropic$5 / $25 per 1M tokens1M8
June 2026DeepSeek V4 FlashDeepSeek$0.30 / $1.20 per 1M tokens1M23
June 2026DeepSeek V4 Flash ThinkingDeepSeek$0.25 / $1.75 per 1M tokens200K1
June 2026DeepSeek V4 ProDeepSeek$1.32 / $3.96 per 1M tokens1M18
June 2026Gemini 25 Flash ImageGoogle$0.039 per image–1
June 2026Gemma 2B IT LoraGoogleFree8K1
June 2026Gemma 4 26BGoogle$0.03 / $0.165 per 1M tokens128K1
June 2026Gemma 4 26B A4BGoogle$0.13 / $0.40 per 1M tokens256K1
June 2026Gemma 4 26B A4B ITGoogleFree256K8
June 2026Gemma 4 31BGoogle$0.14 / $0.40 per 1M tokens256K2
June 2026Gemma 4 31B ITGoogleFree256K11
June 2026Gemma 4 31B IT ThinkingGoogle$0.15 / $0.40 per 1M tokens256K1
June 2026Gemma 4 E2BGoogle$0.04 / $0.08 per 1M tokens128K1
June 2026Gemma 7B IT LoraGoogleFree4K1
June 2026Gigachat 2–Free128K1
June 2026Gigaembeddings 3B 2025 09–Free4K1
June 2026GLM 5.1 Nvfp4 MtpZ.ai$1.40 / $4.40 per 1M tokens198K1
June 2026GLM 5.2Z.ai$1.40 / $4.40 per 1M tokens1M20
June 2026GLM 5p1 FastZ.ai$2.80 / $8.80 per 1M tokens203K1
June 2026GPT Realtime WhisperOpenAI$0.017 per minute32K2
June 2026Granite 4.0 H Micro–$0.017 / $0.112 per 1M tokens131K1
June 2026Hermes 3 8B Tee–$0.15 / $0.60 per 1M tokens16K1
June 2026Kimi K2.7 CodeMoonshot AI$0.95 / $4 per 1M tokens256K16
June 2026Kimi K2p6 Fast retiredMoonshot AI$2 / $8 per 1M tokens256K1
June 2026Kimi K2p7 Code Fast retiredMoonshot AI$1.90 / $8 per 1M tokens256K1
June 2026Llama 2 7B Chat HF LoraMetaFree8K1
June 2026Llama 3.3 70B Instruct FP8 FastMeta$0.293 / $2.253 per 1M tokens24K1
June 2026Mai Image 2.5 retired–$0.048 per image32K1
June 2026Mai Image 2.5 Flash retired–$0.02 per image32K1
June 2026Mercury 2Inception Labs$0.25 / $0.75 per 1M tokens128K1
June 2026Mercury Edit 2Inception Labs$0.25 / $0.75 per 1M tokens32K1
June 2026MiniMax M3MiniMax$0.30 / $1.20 per 1M tokens1M10
June 2026Mistral 7B Instruct V0.2 LoraMistral AIFree15K1
June 2026Mistral Medium 3.5Mistral AI$1.50 / $7.50 per 1M tokens256K2
June 2026Mistral Medium 3.5 128BMistral AI$1.50 / $7.50 per 1M tokens256K1
June 2026Nano BananaGoogle$0.039 per image–1
June 2026Nemotron 3 120B A12BNVIDIA$0.50 / $1.50 per 1M tokens256K1
June 2026Qwen3.5 122B A10B ThinkingAlibaba$0.25 / $1.75 per 1M tokens256K1
June 2026Qwen3.6 27BAlibaba$0.15 / $0.50 per 1M tokens256K6
June 2026Qwen3.6 27B ThinkingAlibaba$0.15 / $0.50 per 1M tokens256K1
June 2026Qwen3.6 35B A3BAlibaba$0.05 / $0.40 per 1M tokens256K8
June 2026Qwen3.6 35B A3B ThinkingAlibaba$0.15 / $0.50 per 1M tokens256K1
June 2026Qwen3.7 PlusAlibaba$0.282 / $1.128 per 1M tokens1M6
June 2026STT Async V4–$0.00002778 per second8K1
June 2026STT Async V5–$0.00002778 per second8K1