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 500
| Model | Provider | Input $/M | Output $/M | Context | Tools | Weights |
|---|---|---|---|---|---|---|
| falcon-7b | tiiuae | Self-host | — | — | — | Open |
| gpt-j-6b | EleutherAI | Self-host | — | — | — | Open |
| gpt2 | openai-community | Self-host | — | — | — | Open |
| gpt2-large | openai-community | Self-host | — | — | — | Open |
| gpt2-medium | openai-community | Self-host | — | — | — | Open |
| gpt2-mini | erwanf | Self-host | — | — | — | Open |
| granite-3.3-2b-instruct | ibm-granite | Self-host | — | — | — | Open |
| h2o-danube3-500m-chat | h2oai | Self-host | — | — | — | Open |
| Hermes-3-Llama-3.1-8B | NousResearch | Self-host | — | — | — | Open |
| japanese-gpt-neox-small | rinna | Self-host | — | — | — | Open |
| LLaDA-8B-Instruct | GSAI-ML | Self-host | — | — | — | Open |
| Llama-2-13b-chat-hf | Meta | Self-host | — | — | — | Open |
| Llama-2-7b-chat-hf | Meta | Self-host | — | — | — | Open |
| Llama-2-7b-hf | Meta | Self-host | — | — | — | Open |
| Llama-3_3-Nemotron-Super-49B-v1_5 | NVIDIA | Self-host | — | — | — | Open |
| Llama-3.1-8B | Meta | Self-host | — | — | — | Open |
| Llama-3.2-1B | Meta | Self-host | — | — | — | Open |
| Llama-3.2-3B | Meta | Self-host | — | — | — | Open |
| llama-7b | huggyllama | Self-host | — | — | — | Open |
| llm-jp-3-150m | llm-jp | Self-host | — | — | — | Open |
| Meta-Llama-3-8B | Meta | Self-host | — | — | — | Open |
| Meta-Llama-3-8B-Instruct | Meta | Self-host | — | — | — | Open |
| Meta-Llama-3-8B-Instruct-abliterated-v3 | failspy | Self-host | — | — | — | Open |
| Meta-Llama-3.1-8B-Instruct | NousResearch | Self-host | — | — | — | Open |
Prices are USD per million tokens from OpenRouter, read daily. Providers change prices often; check the model page before you rely on one.