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 25–30 of 30
- 0.587score
Qwen3.8 Flash
Qwen (Alibaba)
Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
ModelAFreshness: A$0.15 / $0.471M ctxOpen weights - 0.577score
Beam 1.0 501B A23B
Reflection
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.
ModelAFreshness: A$0.25 / $11M ctxOpen weights - 0.577score
LongCat 2.0
Meituan
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.
ModelAFreshness: A$0.3 / $1.21M ctxOpen weights - 0.577score
Step 5 Preview
StepFun
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).
ModelAFreshness: A$1 / $2.71M ctxOpen weights - 0.577score
UnslopNemo 12B
TheDrummer
UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.
ModelAFreshness: A$0.4 / $0.41M 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