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 337–360 of 500

0.461score
Qwen3-8B
Qwen
Open-weights 8.19B-parameter text model from Qwen on Hugging Face (apache-2.0).
ModelFFreshness: FOpen weights
0.438score
ERNIE-4.5-21B-A3B-Thinking
baidu
Open-weights 21.83B-parameter text model from baidu on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.438score
granite-4.0-h-small
ibm-granite
Open-weights 32.21B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.438score
Solar-Open-100B
upstage
Open-weights 102.65B-parameter text model from upstage on Hugging Face (upstage-solar-license).
ModelDFreshness: DOpen weights
0.438score
The_GuageLLM_23M
Hai929
Open-weights 0.02B-parameter text model from Hai929 on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.433score
opt-125m
peft-internal-testing
Open-weights 0.13B-parameter text model from peft-internal-testing on Hugging Face.
ModelDFreshness: DOpen weights
0.432score
AgentCPM-Explore
openbmb
Open-weights 4.02B-parameter text model from openbmb on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.432score
c4ai-command-a-03-2025
CohereLabs
Open-weights 111.06B-parameter text model from CohereLabs on Hugging Face (cc-by-nc-4.0).
ModelDFreshness: DOpen weights
0.432score
c4ai-command-r7b-12-2024
CohereLabs
Open-weights 8.03B-parameter text model from CohereLabs on Hugging Face (cc-by-nc-4.0).
ModelDFreshness: DOpen weights
0.432score
DeepSeek-V3.2-Speciale
deepseek-ai
Open-weights 685.4B-parameter text model from deepseek-ai on Hugging Face (mit).
ModelDFreshness: DOpen weights
0.432score
Hermes-4.3-36B
NousResearch
Open-weights 36.15B-parameter text model from NousResearch on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.432score
TinyStories-1M
roneneldan
Open-weights text model from roneneldan on Hugging Face.
ModelDFreshness: DOpen weights
0.423score
phi-2
microsoft
Open-weights 2.78B-parameter text model from microsoft on Hugging Face (mit).
ModelDFreshness: DOpen weights
0.423score
Phi-3-mini-128k-instruct
microsoft
Open-weights 3.82B-parameter text model from microsoft on Hugging Face (mit).
ModelDFreshness: DOpen weights
0.423score
Phi-3-mini-4k-instruct
microsoft
Open-weights 3.82B-parameter text model from microsoft on Hugging Face (mit).
ModelDFreshness: DOpen weights
0.423score
Phi-3.5-mini-instruct
microsoft
Open-weights 3.82B-parameter text model from microsoft on Hugging Face (mit).
ModelDFreshness: DOpen weights
0.423score
Phi-4-mini-instruct
microsoft
Open-weights 3.84B-parameter text model from microsoft on Hugging Face (mit).
ModelDFreshness: DOpen weights
0.414score
UserLM-8b
microsoft
Open-weights 8.03B-parameter text model from microsoft on Hugging Face (mit).
ModelCFreshness: COpen weights
0.413score
aya-expanse-8b
CohereLabs
Open-weights 8.03B-parameter text model from CohereLabs on Hugging Face (cc-by-nc-4.0).
ModelDFreshness: DOpen weights
0.413score
Kimi-K2-Base
moonshotai
Open-weights 1026.41B-parameter text model from moonshotai on Hugging Face (modified-mit).
ModelDFreshness: DOpen weights
0.407score
WeDLM-8B-Instruct
tencent
Open-weights 8.19B-parameter text model from tencent on Hugging Face (apache-2.0).
ModelDFreshness: DOpen weights
0.402score
Nemotron-Orchestrator-8B
nvidia
Open-weights 8.19B-parameter text model from nvidia on Hugging Face.
ModelDFreshness: DOpen weights
0.401score
Llama-3.1-70B-Instruct
meta-llama
Open-weights 70.55B-parameter text model from meta-llama on Hugging Face (llama3.1).
ModelFFreshness: FOpen weights
0.401score
Llama-Guard-3-8B
meta-llama
Open-weights 8.03B-parameter text model from meta-llama on Hugging Face (llama3.1).
ModelFFreshness: FOpen weights