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 49–72 of 500

0.641score
Nanbeige4.2-3B
Nanbeige
Open-weights 4.17B-parameter text model from Nanbeige on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights
0.641score
NVIDIA-Nemotron-3-Super-120B-A12B-BF16
nvidia
Open-weights 123.61B-parameter text model from nvidia on Hugging Face (nvidia-nemotron-open-model-license).
ModelBFreshness: BOpen weights
0.641score
Ornith-1.5-35B-A3B
ornith-ai
Open-weights 35.95B-parameter text model from ornith-ai on Hugging Face (mit).
ModelBFreshness: BOpen weights
0.641score
Ornith-1.5-397B
ornith-ai
Open-weights 403.4B-parameter text model from ornith-ai on Hugging Face (mit).
ModelBFreshness: BOpen weights
0.641score
Ornith-1.5-9B
ornith-ai
Open-weights 9.65B-parameter text model from ornith-ai on Hugging Face (mit).
ModelBFreshness: BOpen weights
0.641score
Qwen3.8-27B-DFlash2
incoai
Open-weights 1.92B-parameter text model from incoai on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights
0.641score
Qwen3.8-27B-DSpark
RadixArk
Open-weights 1.86B-parameter text model from RadixArk on Hugging Face (other).
ModelBFreshness: BOpen weights
0.641score
Qwen3.8-4B-Distill
empero-ai
Open-weights 4.66B-parameter text model from empero-ai on Hugging Face (apache-2.0).
ModelBFreshness: BOpen weights
0.635score
Inkling-Small-DSpark-Preview
RadixArk
Open-weights 1.39B-parameter text model from RadixArk on Hugging Face.
ModelBFreshness: BOpen weights
0.629score
gpt-oss-120b
OpenAI
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose…
ModelAFreshness: A$0.15 / $0.6131K ctxOpen weights
0.629score
gpt-oss-20b
OpenAI
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
ModelAFreshness: A$0.018 / $0.09131K ctxOpen weights
0.600score
Nemotron 3 Nano 30B A3B
NVIDIA
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI…
ModelAFreshness: A$0.06 / $0.24262K ctxOpen weights
0.600score
Nemotron 3 Ultra
NVIDIA
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
ModelAFreshness: A$0.6 / $2.4262K ctxOpen weights
0.600score
Nemotron 3.5 Lightning
NVIDIA
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
ModelAFreshness: A$0.07 / $0.2262K ctxOpen weights
0.593score
K2-Horizon-3.7B
IFM
Open-weights 5.06B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.593score
K2-Horizon-375B-A23B
IFM
Open-weights 379.17B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.593score
K2-Horizon-MoVA-36B-A4B
IFM
Open-weights 37.44B-parameter text model from IFM on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.593score
MemT-1.0-Flash
MemTensor
Open-weights 287.94B-parameter text model from MemTensor on Hugging Face (mit).
ModelAFreshness: AOpen weights
0.593score
MemT-1.0-Nano
MemTensor
Open-weights 35.11B-parameter text model from MemTensor on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights
0.593score
Ornith-1.5-122B
ornith-ai
Open-weights 125.09B-parameter text model from ornith-ai on Hugging Face (mit).
ModelAFreshness: AOpen weights
0.592score
DeepSeek V3.2 Exp
DeepSeek
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.
ModelAFreshness: A$0.27 / $0.41164K ctxOpen weights
0.592score
GLM 4.6
Z.ai
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens…
ModelAFreshness: A$0.55 / $2.2205K ctxOpen weights
0.592score
GLM 4.7
Z.ai
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution.
ModelAFreshness: A$0.54 / $1.98205K ctxOpen weights
0.592score
Hunyuan A13B Instruct
Tencent
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for…
ModelAFreshness: A$0.14 / $0.57131K ctxOpen weights