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 265–288 of 695
- 0.583score
granite-4.1-3b
ibm-granite
Open-weights 3.4B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights - 0.583score
kimi-k2.6-eagle3-mla
lightseekorg
Open-weights 3.02B-parameter text model from lightseekorg on Hugging Face (other).
ModelCFreshness: COpen weights - 0.583score
Laguna-M.1
poolside
Open-weights 225.8B-parameter text model from poolside on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights - 0.583score
LFM2.5-230M-Base
LiquidAI
Open-weights 0.23B-parameter text model from LiquidAI on Hugging Face (lfm1.0).
ModelCFreshness: COpen weights - 0.583score
Olmo-3-7B-Instruct
allenai
Open-weights 7.3B-parameter text model from allenai on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights - 0.583score
Olmo-3-7B-Think
allenai
Open-weights 7.3B-parameter text model from allenai on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights - 0.583score
Ornith-1.0-35B
ornith-ai
Open-weights 35B-parameter text model from ornith-ai on Hugging Face (mit).
ModelCFreshness: COpen weights - 0.583score
Ornith-1.0-397B
ornith-ai
Open-weights 396.8B-parameter text model from ornith-ai on Hugging Face (mit).
ModelCFreshness: COpen weights - 0.583score
Ornith-1.0-9B
ornith-ai
Open-weights 9B-parameter text model from ornith-ai on Hugging Face (mit).
ModelCFreshness: COpen weights - 0.583score
Qwen3.6-35B-A3B-abliterated-v4
Bahushruth
Open-weights 34.66B-parameter text model from Bahushruth on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights - 0.583score
typhoon2.5-qwen3-4b
typhoon-ai
Open-weights 4.02B-parameter text model from typhoon-ai on Hugging Face (apache-2.0).
ModelCFreshness: COpen weights - 0.582score
Aion 3.5
AionLabs
Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
ModelAFreshness: A$3 / $6262K ctx - 0.582score
Aion 3.5 Mini
AionLabs
Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
ModelAFreshness: A$0.7 / $1.4262K ctx - 0.582score
Aion-2.0
AionLabs
Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling.
ModelAFreshness: A$0.8 / $1.6131K ctx - 0.582score
Aion-3.0
AionLabs
Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
ModelAFreshness: A$3 / $6131K ctx - 0.582score
Aion-3.0-Mini
AionLabs
Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.
ModelAFreshness: A$0.7 / $1.4131K ctx - 0.582score
Aion-RP 1.0 (8B)
AionLabs
Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto…
ModelAFreshness: A$0.8 / $1.633K ctx - 0.582score
Dots3-Note Preview
Dots Studio
Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total.
ModelAFreshness: AFree / Free512K ctx - 0.582score
Ember-1
Fireworks
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3).
ModelAFreshness: A$3 / $151M ctx - 0.582score
Extract
ScaleDown
Extract is a description-driven entity extraction model from ScaleDown.
ModelAFreshness: A$0.04 / Free1M ctx - 0.582score
Fugu Max
Sakana
Fugu Max is the cost-performance model in Sakana AI's Fugu family.
ModelAFreshness: A$2 / $61M ctx - 0.582score
Fugu Ultra
Sakana
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family.
ModelAFreshness: A$5 / $301M ctx - 0.582score
Fugu Ultra v2
Sakana
Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family.
ModelAFreshness: A$5 / $301M ctx - 0.582score
Glimpse
Elorian
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world.
ModelAFreshness: A$0.6 / $3262K ctx