Agnes 2.0 Flash is a fast, efficient language model built for high-frequency agentic workloads: tool calling, coding, multi-turn chat, reasoning and image understanding. It speaks an OpenAI-compatible Chat Completions dialect and is offered free on MeshTok, making it an easy default for prototyping pipelines before graduating to paid frontier models.
可直接取代 OpenAI。只需變更 base_url 和 model。
# Python - pip install openai from openai import OpenAI client = OpenAI( base_url="https://meshtok.com/v1", api_key="sk-your-MeshTok-key", ) resp = client.chat.completions.create( model="agnes/agnes-2.0-flash", messages=[{"role":"user","content":"Hello!"}], ) print(resp.choices[0].message.content)
# cURL curl https://meshtok.com/v1/chat/completions \ -H "Authorization: Bearer sk-your-MeshTok-key" \ -H "Content-Type: application/json" \ -d '{"model":"agnes/agnes-2.0-flash","messages":[{"role":"user","content":"Hello!"}]}'
其他您可能考慮的模型。
Free upgrade of the Agnes flash line for agents and coding.
Latest Agnes generation, tuned for agent coding and tools.
Cheap and fast 1536-dim embeddings at scale.
DeepSeek’s flagship reasoning model.