AXON
MODEL FAMILY
Enterprise-grade AI models built for coding agents, tool calling, and advanced reasoning. Available via API and integrated directly in Orbital.
Axon Lumen 4
NEW · FLAGSHIPOur latest flagship model for frontier coding, agentic and visual workflows. State-of-the-art results across DeepSWE, FrontiersSWE, Terminal Bench 2.1 and BrowseComp — with a 1M-token context and native multimodal input.
axon-lumen-4Axon Eido 3 Pro
MOST INTELLIGENTOur flagship model for long-running agents, tool calling, coding and deep research. Frontier reasoning with a 1M-token context and native multimodal input.
axon-eido-3-proAxon Eido 3 Mini
WORKHORSEThe everyday general-purpose workhorse for day-to-day tasks — chat, extraction, RAG and agents — with the same 1M context, fast and cost-efficient.
axon-eido-3-miniAxon Eido 3 Flash
FASTFast, low-latency model suitable for low-complexity, day-to-day coding tasks and general use — with a 1M-token context and native multimodal input.
axon-eido-3-flashPROMPT
CACHING.
Cached input tokens are automatically discounted at 75% off the standard input price. Caching kicks in automatically for repeated prompt prefixes.
USE WITH
ANY SDK.
Fully OpenAI-compatible. Drop in your existing OpenAI client with just a base URL change.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_MATTERAI_KEY",
base_url="https://api.matterai.so/v1",
)
response = client.chat.completions.create(
model="axon-lumen-4",
messages=[{"role": "user", "content": "Hello"}],
)import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_MATTERAI_KEY",
baseURL: "https://api.matterai.so/v1",
});
const response = await client.chat.completions.create({
model: "axon-lumen-4",
messages: [{ role: "user", content: "Hello" }],
});