AI Model Catalog

Name: ANT
Author: Antbase

11,981 AI models across 92 providers. Every model available through a single API endpoint.

👁️ Vision 🧠 Thinking 🔧 Tools ⚡ Streaming 🎨 Image Gen 🎬 Video Gen ✦ Free

All (11,981)Featherless (10218)Vercel (351)AskCodi (311)DeepInfra (126)Hugging Face (126)OpenAI (86)Phala (66)SiliconFlow (58)

Showing 1–100 of 648 models

Page 1 of 7

Model	Quality	Input /1K	Output /1K	Context	Capabilities
Thinking Machines: Inkling (free) thinkingmachines/inkling:free	40	Free	Free	1.0M	👁🧠🔧⚡
Thinking Machines: Inkling Small (free) thinkingmachines/inkling-small:free	40	Free	Free	1.0M	👁🧠🔧⚡
DeepSeek R1 Distill Qwen 7B huggingface/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B	45	$0.000150	$0.000150	0	🧠🔧⚡
Inkling Small huggingface/thinkingmachines/Inkling-Small	45	$0.000450	$0.0012	0	🧠⚡
DeepSeek R1 Distill Llama 8B huggingface/deepseek-ai/DeepSeek-R1-Distill-Llama-8B	45	$0.000050	$0.000050	0	🧠⚡
Qwen3 4B Thinking 2507 huggingface/Qwen/Qwen3-4B-Thinking-2507	45	$0.0014	$0.0050	0	🧠🔧⚡
Qwen3 235B A22B Thinking 2507 huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507	45	$0.000230	$0.0023	0	🧠🔧⚡
DeepSeek R1 Distill Qwen 14B huggingface/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	45	$0.000200	$0.000200	0	🧠🔧⚡
Inkling huggingface/thinkingmachines/Inkling	45	$0.000950	$0.0040	0	🧠⚡
DeepSeek R1 0528 huggingface/deepseek-ai/DeepSeek-R1-0528	45	$0.000500	$0.0022	0	🧠⚡
Deepseek R1 14b Cot Math Reasoning Full featherless/Jianyuan1/deepseek-r1-14b-cot-math-reasoning-full	50	—	—	33K	🧠⚡
Claude Opus 5.5 vercel/anthropic/claude-opus-5.5	50	$0.0040	$0.020	1M	👁🧠🔧⚡
SearchR1 Nq Hotpotqa Train Qwen2.5 7b Em Grpo V0.2 featherless/PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-7b-em-grpo-v0.2	50	—	—	33K	🧠⚡
Qwen2.5 7B Vietnamese Medical NER GRPO featherless/PeterPaker123/Qwen2.5-7B-Vietnamese-Medical-NER-GRPO	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Llama 8B featherless/unsloth/DeepSeek-R1-Distill-Llama-8B	50	—	—	33K	🧠⚡
Llama 2 13b Chat Hf FINETUNE9 4.4w R16 Gate Up Down featherless/CHIH-HUNG/Llama-2-13b-chat-hf-FINETUNE9_4.4w-r16-gate_up_down	50	—	—	4K	🧠🔧⚡
DeepSeek R1 Distill Alpaca FineTuned featherless/krishanwalia30/DeepSeek-R1-Distill-Alpaca-FineTuned	50	—	—	33K	🧠⚡
Llama 3 DeepSeek R1 Distill 8B LewdPlay Uncensored featherless/mergekit-community/Llama-3-DeepSeek-R1-Distill-8B-LewdPlay-Uncensored	50	—	—	8K	🧠⚡
Qwen2.5 Coder 14B Instruct Reason featherless/dbands/Qwen2.5-Coder-14B-Instruct-reason	50	—	—	33K	🧠🔧⚡
Think1 featherless/HenriCastro/think1	50	—	—	4K	🧠⚡
Qwen3.5 9B Deckard Claude DIMOE Uncensored Heretic Thinking featherless/DavidAU/Qwen3.5-9B-Deckard-Claude-DIMOE-Uncensored-Heretic-Thinking	50	—	—	33K	🧠⚡
TableGPT R1 featherless/tablegpt/TableGPT-R1	50	—	—	33K	🧠⚡
Gpt 5.1 Thinking vercel/openai/gpt-5.1-thinking	50	$0.013	$0.032	400K	👁🧠🔧⚡
Qwen3.8 27B Thinkingcap Abliterated featherless/hotdogs/Qwen3.8-27B-thinkingcap-abliterated	50	—	—	33K	🧠⚡
Qwen3.8 27B Opus Abliterix Reasoning BF16 featherless/timteh673/Qwen3.8-27B-Opus-Abliterix-Reasoning-BF16	50	—	—	33K	🧠⚡
Gemini 3.8 Live Extended Thinking vercel/google/gemini-3.8-live-extended-thinking	50	$0.0040	$0.013	0	👁🧠🔧⚡
Verl Grpo Numina Qwen3 8b AdamWLR1e 6 Beta0p9 Bs256 In1024 Out1024 featherless/Sinestro38/verl_grpo_numina_qwen3_8b_adamWLR1e-6_beta0p9_bs256_in1024_out1024	50	—	—	33K	🧠⚡
Foundation Sec 8B Reasoning featherless/fdtn-ai/Foundation-Sec-8B-Reasoning	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Qwen 14B Abliterated V2 featherless/Greytechai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2	50	—	—	33K	🧠⚡
OpenThinker3 7B featherless/open-thoughts/OpenThinker3-7B	50	—	—	33K	🧠⚡
Llama3 Diverce Ver1.0 featherless/sel303/llama3-diverce-ver1.0	50	—	—	8K	🧠⚡
Grok 4.1 Fast Non Reasoning vercel/spacexai/grok-4.1-fast-non-reasoning	50	$0.013	$0.032	1M	🧠🔧⚡
Nsfw W Deepseek R1 Retry featherless/mergekit-community/nsfw-w-deepseek-r1-retry	50	—	—	33K	🧠⚡
Claude Opus 5.5 Fast vercel/anthropic/claude-opus-5.5-fast	50	$0.013	$0.032	1M	👁🧠🔧⚡
Qwen3 VL 32B Gemini Heretic Uncensored Thinking featherless/slowface/Qwen3-VL-32B-Gemini-Heretic-Uncensored-Thinking	50	—	—	33K	👁🧠⚡
Qwen3 8B Drama Thinking featherless/FutureMa/Qwen3-8B-Drama-Thinking	50	—	—	33K	🧠⚡
Mistral Nemo Inst 2407 12B Thinking Uncensored HERETIC HI Claude Opus featherless/Babsie/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus	50	—	—	33K	🧠⚡
AceReason Nemotron 7B featherless/nvidia/AceReason-Nemotron-7B	50	—	—	33K	🧠⚡
M2 Llama featherless/Shishir1807/M2_llama	50	—	—	4K	🧠⚡
Claude Sonnet 4 vercel/anthropic/claude-sonnet-4	50	$0.0030	$0.015	1M	👁🧠🔧⚡
Guns And Roses R1 featherless/inflatebot/guns-and-roses-r1	50	—	—	33K	🧠⚡
Llama 3.1 8b Instruct Armorm Iter1 featherless/simonycl/llama-3.1-8b-instruct-armorm-iter1	50	—	—	33K	🧠🔧⚡
Llama3.1 8B Base Gsm8k Ft Freeze Rsn Lr1e 5 featherless/kmseong/llama3.1-8B_base_gsm8k_ft_freeze_rsn_lr1e-5	50	—	—	33K	🧠⚡
TelecomGPT R1 featherless/KU-DFI/TelecomGPT-R1	50	—	—	33K	🧠⚡
Qwen2.5 0.5B Open R1 GRPO featherless/Cys621/Qwen2.5-0.5B-Open-R1-GRPO	50	—	—	33K	🧠⚡
Writing Model Qwen 32B Thinking featherless/AQuarterMile/Writing-Model-Qwen-32B-thinking	50	—	—	33K	🧠⚡
Deepseek R1 Distill NSFW RPv1 featherless/mergekit-community/Deepseek-R1-Distill-NSFW-RPv1	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Qwen 32B featherless/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Llama 70B Abliterated featherless/nguyenthilaitrieulong/DeepSeek-R1-Distill-Llama-70B-abliterated	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Qwen 7B Uncensored Personality BR featherless/Phanzor/DeepSeek-R1-Distill-Qwen-7B-Uncensored-Personality-BR	50	—	—	33K	🧠⚡
L3.1 Dark Reasoning LewdPlay Evo Hermes R1 Uncensored 8B Heretic featherless/Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic	50	—	—	8K	🧠⚡
DeepSeek R1 Distill Qwen 14B Blunt Uncensored Blunt featherless/braindao/DeepSeek-R1-Distill-Qwen-14B-Blunt-Uncensored-Blunt	50	—	—	33K	🧠⚡
Open R1 Math 7B Instruct featherless/prithivMLmods/Open-R1-Math-7B-Instruct	50	—	—	33K	🧠🔧⚡
Llama 2 13b Bdcheck R1 featherless/tschmmm/llama-2-13b-bdcheck_r1	50	—	—	4K	🧠⚡
Claude Opus 5 vercel/anthropic/claude-opus-5	50	$0.0050	$0.025	1M	👁🧠🔧⚡
MistralThinker V1.1 featherless/Undi95/MistralThinker-v1.1	50	—	—	33K	🧠⚡
Trinity Large Thinking vercel/arcee-ai/trinity-large-thinking	50	$0.000250	$0.000800	262K	🧠🔧⚡
Cosmos Reason2 32B featherless/nvidia/Cosmos-Reason2-32B	50	—	—	33K	🧠⚡
Llama 2 13b Hf FINETUNE12 4.6w R16 Gate Up Down featherless/CHIH-HUNG/Llama-2-13b-hf-FINETUNE12_4.6w-r16-gate_up_down	50	—	—	4K	🧠⚡
Qwen2.5 1.5B Open R1 Distill featherless/ZMC2019/Qwen2.5-1.5B-Open-R1-Distill	50	—	—	33K	🧠⚡
Llama 3.1 8B R1 V0.1 featherless/CreitinGameplays/Llama-3.1-8B-R1-v0.1	50	—	—	33K	🧠⚡
Skywork OR1 32B featherless/Skywork/Skywork-OR1-32B	50	—	—	33K	🧠⚡
Deepseek R1 Distill Qwen 32b Uncensored featherless/Wlc7758/Deepseek-R1-Distill-Qwen-32b-uncensored	50	—	—	33K	🧠⚡
Skywork OR1 7B featherless/Skywork/Skywork-OR1-7B	50	—	—	33K	🧠⚡
Qwen3.5 2B Claude 4.6 OS Auto Variable HERETIC UNCENSORED THINKING featherless/DavidAU/Qwen3.5-2B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING	50	—	—	33K	🧠⚡
Claude Opus 4.8 Fast vercel/anthropic/claude-opus-4.8-fast	50	$0.013	$0.032	1M	👁🧠🔧⚡
Claude Opus 5 Fast vercel/anthropic/claude-opus-5-fast	50	$0.013	$0.032	1M	👁🧠🔧⚡
Gemma 3 12b It Ko Reasoning featherless/DimensionSTP/gemma-3-12b-it-Ko-Reasoning	50	—	—	33K	🧠⚡
7b Min Perprompt Iter1 Eta 1e3 Step 332 Final featherless/zjhhhh/7b_min_perprompt_iter1_eta_1e3_step_332_final	50	—	—	33K	🧠⚡
Deepseek R1 Distill NSFW RPv1 Mlx Fp16 featherless/hsefz-ChenJunJie/Deepseek-R1-Distill-NSFW-RPv1-mlx-fp16	50	—	—	33K	🧠⚡
Deepthink Reasoning 7B featherless/prithivMLmods/Deepthink-Reasoning-7B	50	—	—	33K	🧠⚡
Trinity Large Thinking askcodi/arcee-ai/trinity-large-thinking	50	$0.000250	$0.000800	0	🧠⚡
Deepseek R1 askcodi/deepseek/deepseek-r1	50	$0.0070	$0.025	0	🧠⚡
Llama3.3 8B Instruct Thinking Heretic Uncensored Claude 4.5 Opus High Reasoning Mlx Fp16 featherless/alexgusevski/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-fp16	50	—	—	8K	🧠🔧⚡
Llama2 Finetuned Chatbot featherless/simlamkr1/llama2_finetuned_chatbot	50	—	—	4K	🧠🔧⚡
Llama 3.3 70B Vulpecula R1 featherless/Sao10K/Llama-3.3-70B-Vulpecula-r1	50	—	—	33K	🧠⚡
StrikeGPT R1 Zero 8B featherless/Bouquets/StrikeGPT-R1-Zero-8B	50	—	—	33K	🧠⚡
Tempesthenno Reasoning Exp 1216 featherless/sthenno/tempesthenno-reasoning-exp-1216	50	—	—	33K	🧠⚡
Llama 3.1 8B R1 Experimental featherless/CreitinGameplays/Llama-3.1-8B-R1-experimental	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Llama 8B Abliterated featherless/huihui-ai/DeepSeek-R1-Distill-Llama-8B-abliterated	50	—	—	33K	🧠⚡
DLER R1 7B Research featherless/nvidia/DLER-R1-7B-Research	50	—	—	33K	🧠⚡
Short Paper Llama Llama3.1 8b Train Sft All Train No Think featherless/koutch/short_paper_llama_llama3.1-8b_train_sft_all_train_no_think	50	—	—	33K	🧠⚡
DeepSeek R1 Qwen Lorablated 32B featherless/nbeerbower/DeepSeek-R1-Qwen-lorablated-32B	50	—	—	33K	🧠⚡
ThinkPRM 14B featherless/launch/ThinkPRM-14B	50	—	—	33K	🧠⚡
Reasoning Llama 3.1 CoT RE1 NMT V2 ORPO featherless/EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO	50	—	—	33K	🧠⚡
Inkling Small askcodi/thinkingmachines/inkling-small	50	$0.000450	$0.0012	0	🧠⚡
OpenCodeReasoning Nemotron 32B featherless/nvidia/OpenCodeReasoning-Nemotron-32B	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Qwen 7B Uncensored featherless/thirdeyeai/DeepSeek-R1-Distill-Qwen-7B-uncensored	50	—	—	33K	🧠⚡
Stockmark DocReasoner Qwen2.5 VL 32B featherless/stockmark/Stockmark-DocReasoner-Qwen2.5-VL-32B	50	—	—	33K	👁🧠⚡
DeepSeek R1 Distill Qwen 32B Japanese featherless/cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese	50	—	—	33K	🧠⚡
DeepSeek R1 Distill Llama 8B Merged 16bit featherless/samlucky/DeepSeek-R1-Distill-Llama-8B_merged_16bit	50	—	—	33K	🧠⚡
QqWen 14B RL Reasoning featherless/morganstanley/qqWen-14B-RL-Reasoning	50	—	—	33K	🧠⚡
Qwen2.5 7B Think KTO V0.2 featherless/ericflo/Qwen2.5-7B-Think-KTO-v0.2	50	—	—	33K	🧠⚡
M3 Llama featherless/Shishir1807/M3_llama	50	—	—	4K	🧠⚡
Claude Haiku 5.5 vercel/anthropic/claude-haiku-5.5	50	$0.000100	$0.000500	1M	👁🧠🔧⚡
Claude Opus 4.5 vercel/anthropic/claude-opus-4.5	50	$0.0050	$0.025	200K	👁🧠🔧⚡
DeepSeek R1 Distill Qwen 14B featherless/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B	50	—	—	33K	🧠⚡
AceReason Nemotron 14B featherless/nvidia/AceReason-Nemotron-14B	50	—	—	33K	🧠⚡
Llama 3.1 8b Reasoning Test featherless/CreitinGameplays/Llama-3.1-8b-reasoning-test	50	—	—	33K	🧠⚡
OpenR1 Qwen 7B Turkish featherless/WiroAI/OpenR1-Qwen-7B-Turkish	50	—	—	33K	🧠⚡

Compare AI Models Across Every Provider

Antbase aggregates 11,981 AI models from 92 providers into a single catalog. Every model is accessible through one OpenAI-compatible API endpoint — no separate accounts, no provider-specific SDKs. Compare quality scores, token pricing, context windows, and capabilities like vision, reasoning, function calling, and streaming.

Models are scored by quality based on benchmark performance, real-world routing success rates, and community rankings. The default sort shows the highest-quality models first — from frontier reasoning models like GPT-5, Claude Opus, and Gemini Ultra to efficient open-source options like Llama, Gemma, Qwen, Mistral, and DeepSeek.

Use the filters above to narrow by provider, capability, or pricing tier. Click any model to see detailed specifications, pricing breakdowns, and a direct link to try it in the Playground.