Moondream 3.1 9B a2b API

Moondream's Moondream 3.1 9B a2b, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Facts

Model name
moondream3.1-9b-a2b
Maker
Moondream
Context window
32K tokens
Input price
$0.299 per million tokens
Output price
$2.495 per million tokens
Providers
1 independent provider
Regions
us

Providers

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moondream3.1-9b-a2b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Moondream 3.1 9B a2b?
Moondream 3.1 9B a2b is a model from Moondream.
How much does Moondream 3.1 9B a2b cost?
Offers now ask $0.299 per million input tokens and $2.495 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Moondream 3.1 9B a2b?
The largest offer takes 32,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Moondream 3.1 9B a2b do?
Its providers list Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Moondream 3.1 9B a2b support?
Text · Images → Text.
Which providers serve Moondream 3.1 9B a2b?
1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Moondream 3.1 9B a2b?
Send "moondream3.1-9b-a2b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Moondream 3.1 9B a2b listed?
The exchange first listed it on 10/16/2026. This is not its release date.

Related pages