695 listed

Models

Language models for agents: hosted models with input and output prices per million tokens from OpenRouter (read daily; prices change often), and open-weights models from Hugging Face with license and downloads. Filter by tool calling, context window and price, or switch to the table to compare.

Cards Table

Showing 433–456 of 500

0.392score
Nous-Hermes-Llama2-13b
NousResearch
Open-weights 13.02B-parameter text model from NousResearch on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.392score
OLMo-7B
allenai
Open-weights 6.89B-parameter text model from allenai on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.392score
solar-pro-preview-instruct
upstage
Open-weights 22.14B-parameter text model from upstage on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.392score
starcoder
bigcode
Open-weights 15.82B-parameter text model from bigcode on Hugging Face (bigcode-openrail-m).
ModelFFreshness: FOpen weights
0.392score
xgen-7b-8k-base
Salesforce
Open-weights 7B-parameter text model from Salesforce on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.392score
Yarn-Mistral-7b-128k
NousResearch
Open-weights 7B-parameter text model from NousResearch on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.392score
Yi-34B-200K
01-ai
Open-weights 34.39B-parameter text model from 01-ai on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.391score
CodeQwen1.5-7B-Chat
Qwen
Open-weights 7.25B-parameter text model from Qwen on Hugging Face (tongyi-qianwen).
ModelFFreshness: FOpen weights
0.391score
Qwen-72B
Qwen
Open-weights 72.29B-parameter text model from Qwen on Hugging Face (tongyi-qianwen-license-agreement).
ModelFFreshness: FOpen weights
0.391score
Qwen2.5-14B-Instruct-1M
Qwen
Open-weights 14.77B-parameter text model from Qwen on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.387score
DeepSeek-Prover-V2-671B
deepseek-ai
Open-weights 684.49B-parameter text model from deepseek-ai on Hugging Face.
ModelFFreshness: FOpen weights
0.387score
Hunyuan-1.8B-Instruct
tencent
Open-weights 1.79B-parameter text model from tencent on Hugging Face.
ModelFFreshness: FOpen weights
0.387score
MistralLite
amazon
Open-weights text model from amazon on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.387score
santacoder
bigcode
Open-weights text model from bigcode on Hugging Face (bigcode-openrail-m).
ModelFFreshness: FOpen weights
0.387score
starcoderbase
bigcode
Open-weights text model from bigcode on Hugging Face (bigcode-openrail-m).
ModelFFreshness: FOpen weights
0.377score
CodeLlama-7b-hf
codellama
Open-weights 6.74B-parameter text model from codellama on Hugging Face (llama2).
ModelFFreshness: FOpen weights
0.377score
gpt-neo-125m
EleutherAI
Open-weights 0.15B-parameter text model from EleutherAI on Hugging Face (mit).
ModelFFreshness: FOpen weights
0.377score
gpt-neox-20b
EleutherAI
Open-weights 20.74B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.377score
macbert4csc-base-chinese
shibing624
Open-weights 0.1B-parameter text model from shibing624 on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.377score
pythia-160m-deduped
EleutherAI
Open-weights 0.21B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.377score
pythia-70m-deduped
EleutherAI
Open-weights 0.1B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.377score
vlt5-base-keywords
Voicelab
Open-weights 0.28B-parameter text model from Voicelab on Hugging Face (cc-by-4.0).
ModelFFreshness: FOpen weights
0.376score
Qwen2-7B-Instruct
Qwen
Open-weights 7.62B-parameter text model from Qwen on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.376score
Qwen3-14B-Base
Qwen
Open-weights 14.77B-parameter text model from Qwen on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights