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.
Showing 217–240 of 500
- 0.547score
Ling-2.6-1T
inclusionAI
Open-weights 1025.41B-parameter text model from inclusionAI on Hugging Face (mit).
ModelBFreshness: BOpen weights - 0.547score
Ling-2.6-flash
inclusionAI
Open-weights 107.49B-parameter text model from inclusionAI on Hugging Face (mit).
ModelBFreshness: BOpen weights - 0.542score
gpt-oss-safeguard-20b
OpenAI
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.
ModelAFreshness: A$0.075 / $0.3131K ctxOpen weights - 0.532score
MiniCPM5-2B-DSpark
openbmb
Open-weights 0.32B-parameter text model from openbmb on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights - 0.528score
LFM2-8B-A1B
LiquidAI
Open-weights 8.34B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.527score
Kimi-K3-DSpark
RadixArk
Open-weights 2.25B-parameter text model from RadixArk on Hugging Face.
ModelBFreshness: BOpen weights - 0.522score
LFM2-24B-A2B
LiquidAI
Open-weights 23.84B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelBFreshness: BOpen weights - 0.522score
Solar-Open2-250B
upstage
Open-weights 250.29B-parameter text model from upstage on Hugging Face (upstage-solar-license).
ModelBFreshness: BOpen weights - 0.519score
Phi 4
Microsoft
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or…
ModelAFreshness: A$0.07 / $0.1416K ctxOpen weights - 0.517score
Nemotron 3 Nano Omni
NVIDIA
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems.
ModelAFreshness: AFree / Free256K ctxOpen weights - 0.517score
Nemotron 3 Super
NVIDIA
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex…
ModelAFreshness: A$0.3 / $2.4262K ctxOpen weights - 0.517score
Nemotron 3.5 Content Safety
NVIDIA
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
ModelAFreshness: A$0.2 / $0.2131K ctxOpen weights - 0.517score
Nemotron 3.5 Super VL
NVIDIA
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
ModelAFreshness: A$0.15 / $0.51M ctxOpen weights - 0.508score
EXAONE-3.5-7.8B-Instruct
LGAI-EXAONE
Open-weights 7.82B-parameter text model from LGAI-EXAONE on Hugging Face (exaone).
ModelDFreshness: DOpen weights - 0.508score
gpt-oss-120b-Eagle3-short-context
nvidia
Open-weights 0.79B-parameter text model from nvidia on Hugging Face (nvidia-open-model-license).
ModelDFreshness: DOpen weights - 0.508score
Kimi-Linear-48B-A3B-Instruct
moonshotai
Open-weights 49.12B-parameter text model from moonshotai on Hugging Face (mit).
ModelDFreshness: DOpen weights - 0.508score
LLaDA2.0-mini
inclusionAI
Open-weights 16.26B-parameter text model from inclusionAI on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights - 0.508score
NVIDIA-Nemotron-3-Nano-4B-BF16
nvidia
Open-weights 3.97B-parameter text model from nvidia on Hugging Face (nvidia-nemotron-open-model-license).
ModelDFreshness: DOpen weights - 0.508score
NVIDIA-Nemotron-Nano-9B-v2
nvidia
Open-weights 8.89B-parameter text model from nvidia on Hugging Face (nvidia-open-model-license).
ModelDFreshness: DOpen weights - 0.508score
Olmo-3-1025-7B
allenai
Open-weights 7.3B-parameter text model from allenai on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights - 0.508score
pythia-14m
EleutherAI
Open-weights 0.01B-parameter text model from EleutherAI on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights - 0.508score
Qwen3.6-27B-DFlash
z-lab
Open-weights 1.73B-parameter text model from z-lab on Hugging Face (mit).
ModelDFreshness: DOpen weights - 0.507score
Qwen3Guard-Gen-0.6B
Qwen
Open-weights 0.75B-parameter text model from Qwen on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights - 0.503score
granite-4.1-8b
ibm-granite
Open-weights 8.79B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights