Moondream: Moondream 3.1
by MoondreamMoondream: Moondream 3.1 is a large language model from Moondream. It costs $0.300 per million input tokens and $2.50 per million output tokens. Its context window is 32K tokens.
- Input / 1M tokens
- $0.300
- Output / 1M tokens
- $2.50
- Cached input / 1M
- -
- Context window
- 32K
Not supported
tokens
Who serves it cheapest
1 hosts serve Moondream 3.1. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| PrimeIntellectCheapestfp8 | $0.300 | $2.50 | 32K | - | 97.9% |
About Moondream 3.1
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...
Specifications
| Model ID | moondream/moondream3.1-9b-a2b |
|---|---|
| Provider | Moondream |
| Context window | 32K tokens |
| Max output | 4K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - moondream/moondream3.1-9B-A2B |
| Released | October 15, 2026 |
Cheaper alternatives
Models that cost less than Moondream 3.1 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Moondream: Moondream 3.1 cost?
$0.300 per million input tokens and $2.50 per million output tokens.
What is the context window of Moondream: Moondream 3.1?
32K tokens, with up to 4K tokens of output per request.