Public model catalog

Select one type tab. Search and pagination apply only to that type.

Language
text / multimodal

Language Models

Token-priced text and multimodal-capable language models.

ModelSlugCapabilityContext WindowInput PriceOutput PriceImage PriceWeb Search
Llama 3.2 90B Vision Instructmeta/llama-3.2-90bMultimodal input128,000 tokens$0.9360 / 1M$0.9360 / 1M
Llama 3.3 70B Instructmeta/llama-3.3-70bText-only128,000 tokens$0.9360 / 1M$0.9360 / 1M
Llama 4 Maverick 17B Instructmeta/llama-4-maverickMultimodal input131,072 tokens$0.1950 / 1M$0.7800 / 1M
Llama 4 Scout 17B Instructmeta/llama-4-scoutMultimodal input131,072 tokens$0.1040 / 1M$0.3900 / 1M
LongCat Flash Thinkingmeituan/longcat-flash-thinkingText-only128,000 tokens$0.1950 / 1M$1.95 / 1M
Magistral Medium 2509mistral/magistral-mediumMultimodal input128,000 tokens$2.60 / 1M$6.50 / 1M
Magistral Small 2509mistral/magistral-smallMultimodal input128,000 tokens$0.6500 / 1M$1.95 / 1M
Mercury 2inception/mercury-2Text-only128,000 tokens$0.3250 / 1M$0.9750 / 1M
Mercury Coder Small Betainception/mercury-coder-smallText-only32,000 tokens$0.3250 / 1M$1.30 / 1M
MiMo V2 Flashxiaomi/mimo-v2-flashText-only262,144 tokens$0.1170 / 1M$0.3770 / 1M
MiniMax M2minimax/minimax-m2Text-only205,000 tokens$0.4875 / 1M$1.56 / 1M
MiniMax M2.1minimax/minimax-m2.1Text-only204,800 tokens$0.3900 / 1M$1.56 / 1M

Note: listed costs are approximate upper-tier reference rates across providers. Final billing depends on the provider route used for each request and may be lower or higher. Routes are selected automatically to prioritize availability and lower cost.

Page 9 of 14 (168 LLM models)