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 97–120 of 500
- 0.587score
DeepSeek V4.1 Flash 1017
DeepSeek
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name.
ModelAFreshness: A$0.3 / $1.21M ctxOpen weights - 0.587score
Devstral 2 2512
Mistral AI
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding.
ModelAFreshness: A$0.4 / $2262K ctxOpen weights - 0.587score
GLM 4.5V
Z.ai
GLM-4.5V is a vision-language foundation model for multimodal agent applications.
ModelAFreshness: A$0.6 / $1.866K ctxOpen weights - 0.587score
GLM 4.6V
Z.ai
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media.
ModelAFreshness: A$0.3 / $0.9131K ctxOpen weights - 0.587score
GLM 5.3 Flash
Z.ai
GLM-5.3-Flash is a native multimodal model from Z.ai.
ModelAFreshness: A$0.15 / $0.51M ctxOpen weights - 0.587score
granite-switch-4.1-30b
ibm-granite
Open-weights 29.99B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights - 0.587score
granite-switch-4.1-8b
ibm-granite
Open-weights 8.78B-parameter text model from ibm-granite on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights - 0.587score
Hermes 3 405B Instruct
Nous Research
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning…
ModelAFreshness: A$1 / $1131K ctxOpen weights - 0.587score
Hermes 3 70B Instruct
Nous Research
Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic…
ModelAFreshness: A$0.7 / $0.7131K ctxOpen weights - 0.587score
Hermes 4 405B
Nous Research
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.
ModelAFreshness: A$1 / $3131K ctxOpen weights - 0.587score
Hy-Memory-30B-A3B
tencent
Open-weights 30.06B-parameter text model from tencent on Hugging Face (apache-2.0).
ModelAFreshness: AOpen weights - 0.587score
Hy-MT2-1.8B
Tencent
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.
ModelAFreshness: A$0.044 / $0.1778K ctxOpen weights - 0.587score
Hy-MT2-30B-A3B
Tencent
Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family.
ModelAFreshness: A$0.074 / $0.2958K ctxOpen weights - 0.587score
Hy-MT2-7B
Tencent
Hy-MT2-7B is a 7B-parameter translation model from Tencent.
ModelAFreshness: A$0.074 / $0.2958K ctxOpen weights - 0.587score
Kimi K2.5
Moonshot AI
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.
ModelAFreshness: A$0.5 / $2.5262K ctxOpen weights - 0.587score
Kimi K2.6
Moonshot AI
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.
ModelAFreshness: A$0.65 / $3.41262K ctxOpen weights - 0.587score
Kimi K2.7 Code
Moonshot AI
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long…
ModelAFreshness: A$0.671 / $3.35262K ctxOpen weights - 0.587score
Kimi K3
Moonshot AI
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
ModelAFreshness: A$0.214 / $201M ctxOpen weights - 0.587score
Ling-3.0-flash-Sante
inclusionAI
Open-weights 127.49B-parameter text model from inclusionAI on Hugging Face (mit).
ModelAFreshness: AOpen weights - 0.587score
Ling-3.0-flash-UBTree
inclusionAI
Open-weights 0.48B-parameter text model from inclusionAI on Hugging Face (mit).
ModelAFreshness: AOpen weights - 0.587score
Ling-3.1-flash
inclusionAI
Open-weights 572.12B-parameter text model from inclusionAI on Hugging Face (mit).
ModelAFreshness: AOpen weights - 0.587score
Llama 3.1 70B Instruct
Meta
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.
ModelAFreshness: A$0.4 / $0.4131K ctxOpen weights - 0.587score
Llama 3.1 8B Instruct
Meta
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.
ModelAFreshness: A$0.05 / $0.08131K ctxOpen weights - 0.587score
Llama 4 Maverick
Meta
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts…
ModelAFreshness: A$0.188 / $0.653524K ctxOpen weights