API
Models & modalities
Every model runs on Arcen's own compute. The catalog is live - query it rather than hardcoding, and browse pricing on the models page.
The catalog
Each model carries a modality (text or text+vision), an endpoint_type (chat or embeddings), and its context_length (max context window in tokens).
curl
curl https://api.arcencompute.com/v1/models \
-H "Authorization: Bearer ar_sk_live_…"Vision (image input)
Models with modality: text+vision - currently minimax-m3 and qwen3.5-397b-a17b - accept image content blocks on chat completions, exactly like the OpenAI API. Pass a public URL or a base64 data: URI.
python
resp = client.chat.completions.create(
model="minimax-m3",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "What's in this image?"},
{"type": "image_url",
"image_url": {"url": "data:image/png;base64,iVBOR…"}},
],
}],
)Embeddings
OpenAI-compatible /v1/embeddings. Use an embeddings model such as text-embedding-3-small or qwen3-embedding-8b. input can be a string or an array of strings.
python
emb = client.embeddings.create(
model="text-embedding-3-small",
input="The quick brown fox",
)
print(emb.data[0].embedding[:5])