Moondream: Moondream 3.1

1 provider live

moondream/moondream3.1-9b-a2b

1 live provider
100% uptime
0.28 s first token
334 tok/s output

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an optional reasoning mode.

Context: 32K; tokens
Max output: 4K; tokens
Input: $0.30; per million tokens
Output: $2.50; per million tokens

Providers

Ranked by price and speed. Requests go to the best healthy provider, then fail over down the list.

#	Provider	Input	Output	Cache read	Latency	Throughput	Uptime (3d)
1	Prime IntellectNon-EU Data policy not declared	$0.30	$2.50	n/a	0.28 s	334 tok/s	100%

Want to serve this model?Become a provider

Price history

No price changes since Oct 21, 2026.

Prime Intellect$0.30 in, $2.50 out

Performance

Last 24 hours, from llm.buzz's test requests

Throughput (tok/s)

Prime Intellect334 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
Prime Intellect	Oct 26, 08:00	334 tok/s	334 tok/s	334 tok/s
Prime Intellect	Oct 26, 13:00	334 tok/s	334 tok/s	334 tok/s
Prime Intellect	Oct 26, 17:00	401 tok/s	401 tok/s	401 tok/s
Prime Intellect	Oct 26, 22:00	334 tok/s	334 tok/s	334 tok/s
Prime Intellect	Oct 27, 02:00	232 tok/s	232 tok/s	232 tok/s
Prime Intellect	Last 24 hours	334 tok/s	232 tok/s	232 tok/s

Latency (time to first token)

Prime Intellect0.28 s

Data table

Provider	From (UTC)	p50	p90	p99
Prime Intellect	Oct 26, 08:00	0.33 s	0.33 s	0.33 s
Prime Intellect	Oct 26, 13:00	0.28 s	0.28 s	0.28 s
Prime Intellect	Oct 26, 17:00	0.28 s	0.28 s	0.28 s
Prime Intellect	Oct 26, 22:00	0.33 s	0.33 s	0.33 s
Prime Intellect	Oct 27, 02:00	0.28 s	0.28 s	0.28 s
Prime Intellect	Last 24 hours	0.28 s	0.33 s	0.33 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

Prime Intellect

Up: 95% or more served
Degraded: 85% to 95%
Down: below 85%
No data
From llm.buzz's test requests

Questions

How much does Moondream: Moondream 3.1 cost?

Moondream: Moondream 3.1 costs $0.30 per million input tokens and $2.50 per million output tokens at Prime Intellect, the provider requests go to first.

Do providers train on my prompts?

Each provider declares it, and the table above shows every declaration. You can limit a request to providers that keep nothing, or to providers in the EU.

Can I serve Moondream: Moondream 3.1 myself?

Yes. Apply as a provider, add your endpoint and list this model at your price. It goes live once the automated check passes.

Similar models

Moondream: Moondream 3 Previewmoondream/moondream3-preview

Open weights. 32K context, $0.30 input and $2.50 output. 1 provider.

DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp

Open weights. 1M context, $0.33 input and $0.99 output (25% off). 2 providers.

Qwen: Qwen3.8 27Bqwen/qwen3.8-27b

Open weights. 256K context, $0.20 input and $2.50 output. 4 providers.

Call it

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm.buzz/api/v1",
    api_key=os.environ["LLM_BUZZ_KEY"],
)
reply = client.chat.completions.create(
    model="moondream/moondream3.1-9b-a2b",
    messages=[{"role": "user", "content": "Hello"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llm.buzz/api/v1",
  apiKey: process.env.LLM_BUZZ_KEY,
});
const reply = await client.chat.completions.create({
  model: "moondream/moondream3.1-9b-a2b",
  messages: [{ role: "user", content: "Hello" }],
});

curl https://api.llm.buzz/api/v1/chat/completions \
  -H "Authorization: Bearer $LLM_BUZZ_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "moondream/moondream3.1-9b-a2b",
       "messages": [{"role": "user", "content": "Hello"}]}'

Endpoints

POST /api/v1/chat/completionsPOST /api/v1/responsesPOST /api/v1/messages

Authentication

Send your llm.buzz key as a Bearer token: Authorization: Bearer $LLM_BUZZ_KEY. Create keys in the console. The same key calls every model; each request pays the price of the provider that answered it.

More in Authentication and the API reference.

Call Moondream: Moondream 3.1 with one keyEach request pays the price of the provider that answered it.

Get API key