Conversation models, tools and agents
1542 in the catalogue today. Every one with what it costs, who sells it and where it stands. 1,542 in all, a hundred to a page; this is page 14 of 16.
Models that answer in prose across whatever subject you put to them. This is the largest category and the least differentiated: most of them are competent at most things, so the choice usually comes down to price, context length and how the maker behaves about availability. Look at what a model costs per million tokens in and out — the output rate is often four or five times the input rate, and it is the one that decides your bill.
- granite-4.1-30bIBM Granite227th of 260· 2 boards
- granite-docling-258MIBM Granite
- grok-1xAI
- grok-4.2-betaxAI$2→$6per Mtok in / out, xai lane1 selling
- h2o-lightning-4bH2O.ai
- halt-cotyass4
- helium-1-preview-2bKyutai
- huginn-0125tomg-group-umd
- humanizerjialinyyzz
- idefics-80b-instructHuggingFaceM4
- idefics2-8bHuggingFaceM4
- idefics2-8b-chattyHuggingFaceM4
- imp-v1-3bMILVLG
- inkling-256kThinking Machines Lab$1.87→$4.68per Mtok in / out, thinkingmachines lane1 selling
- instructblip-vicuna-13bSalesforce21st of 26
- instructblip-vicuna-7bSalesforce22nd of 26
- interfaze-1-liteinterfaze
- internlm-xcomposer2d5-7binternlm
- internlm2_5-7b-chatinternlm
- internlm3-8b-instructinternlm
- invoice-and-receipts_donut_v1mychen76
- jais-13binception42
- jais-13b-chatinception42
- jetmoe-8bJetMoE
- jina-vlmJina AI
- kanana-1.5-v-3b-instructkakaocorp
- keys-DeepSeek-V4.1-Flash-1017-Abliterateddrowzeys
- kosmos-2-patch14-224Microsoft
- kosmos-2.5Microsoft
- legal-bert-base-uncasednlpaueb
- llama-13bhuggyllama39th of 115· 13 boards$1.5→$2.1per Mtok in / out1 selling
- llama-2-ko-7bbeomi
- llama-3-70B-Instruct-abliteratedfailspy$3.5→$8.3per Mtok in / out1 selling
- llama-3-Korean-Bllossom-8BMLP-LAB$0.37→$0.38per Mtok in / out1 selling
- llama-3-vision-alpha-hfqresearch
- llama-3.1-Korean-Bllossom-Vision-8BBllossom
- llama-3.2-Korean-Bllossom-3BBllossom$0.2→$1.34per Mtok in / out1 selling
- llama-3.2-Korean-Bllossom-AICA-5BBllossom
- llama-7bhuggyllama32nd of 70· 12 boards$0.4→$0.8per Mtok in / out1 selling
- llama-joycaption-beta-one-hf-llavafancyfeast
- llama2_7b_chat_uncensoredgeorgesung$0.4→$0.8per Mtok in / out1 selling
- llama3-llava-next-8b-hfllava-hf
- llava-1.5-7b-hfLlava Hugging Face
- llava-gemma-2bIntel
- llava-llama-3-8b-v1_1xtuner$0.37→$0.38per Mtok in / out1 selling
- llava-llama-3-8b-v1_1-transformersxtuner
- llava-med-v1.5-mistral-7bMicrosoft
- llava-mini-llama-3.1-8bNatural Language Processing Group, Institute of Computing Technology, Chinese Academy of Science
- llava-onevision-qwen2-0.5b-ov-hfLlava Hugging Face
- llava-v1.5-13bliuhaotian
- llava-v1.5-7bliuhaotian19th of 26
- llava-v1.6-34bliuhaotian
- llava-v1.6-mistral-7bliuhaotian10th of 26
- llava-v1.6-vicuna-13bliuhaotian9th of 26
- llava-v1.6-vicuna-7bliuhaotian13th of 26
- lzlv_70b_fp16_hflizpreciatior$0.35→$0.4per Mtok in / out1 selling
- mPLUG-Owl3-7B-240728mPLUG
- mT5_multilingual_XLSumBUET CSE NLP Group
- magnum-v1-72banthracite-org$12→$20per Mtok in / out1 selling
- maple-previewdeepgrove
- mbart-large-50-many-to-many-mmtMeta
- mdeberta-v3-baseMicrosoft
- mdeberta-v3-base-squad2timpal0l
- med42-70bM42 Health
- medgemma-1.5-4b-itGoogle$0.2→$0.4per Mtok in / out1 selling
- medgemma-27b-itGoogle$0.4→$1.2per Mtok in / out1 selling
- medgemma-27b-text-itGoogle$0.27→$0.65per Mtok in / out1 selling
- medgemma-4b-itGoogle$0.2→$0.4per Mtok in / out1 selling
- medgemma-4b-ptGoogle$0.2→$0.4per Mtok in / out1 selling
- medical_summarizationFalcons.ai
- meditron-70bEPFL LLM Team
- meditron-7bEPFL LLM Team
- medsiglip-448Google
- miniGCausalLM
- miqu-1-70b-sf152334H
- mistral-8x7b-chatmattshumer
- mistral-ft-optimized-1218OpenPipe
- mixtral-7b-8expertDiscoResearch
- mmBERT-baseCenter for Language and Speech Processing @ JHU
- moondream1vikhyatk
- moondream2vikhyatk
- moondream3-previewmoondream$0.3→$2.5per Mtok in / out1 selling
- moondream3.1-9B-A2Bmoondream$0.3→$2.5per Mtok in / out1 selling
- morph-compactMorph$0.2→$0.5per Mtok in / out1 selling
- morph-reflex-v1Morph$0.001per call1 selling
- morph-routerMorph$0.005per call1 selling
- mythalion-13bPygmalionAI$1.5→$2.1per Mtok in / out1 selling
- nanoLLaVAqnguyen3
- nanoLLaVA-1.5qnguyen3
- nanoVLM-222Mlusxvr
- needle3Cactus Compute
- nemotron-3-nano-omniNVIDIA147th of 163$0.5→$0.9per Mtok in / out3 selling
- neural-chat-7b-v3-1Intel
- nllb-200-3.3BMeta
- nllb-200-distilled-1.3BMeta
- nllb-200-distilled-600MMeta
- notux-8x7b-v1argilla
- nougat-baseMeta
- nsfw_image_detectionFalcons.ai
- o3 (Fast)OpenAI$3.5→$14per Mtok in / out1 selling