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 577–600 of 695
| Model | Provider | Input $/M | Output $/M | Context | Tools | Weights |
|---|---|---|---|---|---|---|
| Llama3-ChatQA-1.5-8B | NVIDIA | Self-host | — | — | — | Open |
| LongCat-Flash-Chat | meituan-longcat | Self-host | — | — | — | Open |
| Meta-Llama-3-70B | Meta | Self-host | — | — | — | Open |
| Meta-Llama-3.1-8B | NousResearch | Self-host | — | — | — | Open |
| MiniCPM3-4B | openbmb | Self-host | — | — | — | Open |
| Nous-Hermes-2-Mixtral-8x7B-DPO | NousResearch | Self-host | — | — | — | Open |
| openai-gpt | openai-community | Self-host | — | — | — | Open |
| openchat-3.5-0106 | openchat | Self-host | — | — | — | Open |
| Seed-OSS-36B-Instruct | ByteDance-Seed | Self-host | — | — | — | Open |
| SOLAR-10.7B-Instruct-v1.0 | upstage | Self-host | — | — | — | Open |
| SOLAR-10.7B-v1.0 | upstage | Self-host | — | — | — | Open |
| starcoder2-15b | bigcode | Self-host | — | — | — | Open |
| Tongyi-DeepResearch-30B-A3B | Alibaba-NLP | Self-host | — | — | — | Open |
| vicuna-7b-v1.5 | lmsys | Self-host | — | — | — | Open |
| WizardLM-2-8x22B | alpindale | Self-host | — | — | — | Open |
| Yi-34B | 01-ai | Self-host | — | — | — | Open |
| Yi-34B-Chat | 01-ai | Self-host | — | — | — | Open |
| Yi-6B | 01-ai | Self-host | — | — | — | Open |
| mamba-130m-hf | state-spaces | Self-host | — | — | — | Open |
| opt-125m | Self-host | — | — | — | Open | |
| opt-350m | Self-host | — | — | — | Open | |
| Qwen3-8B-64k-Context-2X-Josiefied-Uncensored | DavidAU | Self-host | — | — | — | Open |
| SmolLM-135M-Instruct-FP32 | modularai | Self-host | — | — | — | Open |
| Qwen-7B | Qwen | 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.