Moondream 3.1 API pricing
moondream · Mid-range price tier · Moondream Model License · released 2026-10. Prices in USD per 1 million tokens. Data snapshot: 2026-10-22.
Moondream 3.1 has held the same list price since 2026-10-17 and is the 17th cheapest of 113 models in the Mid-range price tier. Only one host, PrimeIntellect, sells it, so there is no second price to shop. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.30 per 1M tokens
- Output: $2.50 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: Not published
- Context window: 32K tokens
- Arena ELO: Not published
Market position
On blended price ($1.84 per 1M tokens at 30% input, 70% output) it is cheaper than 82% of models in the Mid-range price tier: 17th cheapest of 113, tied with 4 others. Across every price tier it is cheaper than 40% of priced text models in the catalogue: 181st cheapest of 308, tied with 4 others.
Licence, size and capabilities
Moondream 3.1 is open weights, which is not the same as open source: the weights are published, but under Moondream Model License, a licence that restricts some uses. Read it before self-hosting commercially. Its published size is 9B parameters. Listed capabilities: Text, Vision, Reasoning. Filling its 32K context window once costs $0.0096 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 1 host. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
PrimeIntellect is the only host with a published rate, $0.30 input / $2.50 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| PrimeIntellect (price we quote) | $0.30 | $2.50 | fp8 |
List prices as published on 2026-10-22, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where moondream publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $170 |
| Knowledge Q&A | 2,000 / 800 | $260 |
| Meeting Summary | 10,000 / 1,200 | $600 |
| Marketing Content | 2,500 / 1,800 | $525 |
| Coding Task | 3,000 / 2,000 | $590 |
| Invoice Processing | 1,500 / 600 | $195 |
| Call Summary | 2,000 / 700 | $235 |
| Agent Workflow | 6,000 / 3,000 | $930 |
Price history
Moondream 3.1 entered our daily price archive on 2026-10-17; tracking began on 2026-08-15. It listed at $0.30 input / $2.50 output per 1M tokens that day. No list price change since 2026-10-17. Last checked against the 2026-10-22 snapshot.
Alternatives to Moondream 3.1
- Next cheaper model in the Mid-range price tier: Kimi K2 0711 (Moonshot) at $1.781 blended, 3% less.
- Next more expensive: Nemotron 3 Ultra (Nvidia) at $1.86 blended, 1% more.
Other models from moondream
moondream has 1 other model in the catalogue. Prices per 1M tokens, input then output.
- Moondream 3 Preview: $0.30 / $2.50
Common questions about Moondream 3.1 pricing
- How much does Moondream 3.1 cost?
- Moondream 3.1 costs $0.30 per 1M input tokens and $2.50 per 1M output tokens at PrimeIntellect, the host whose rate we quote. PrimeIntellect serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-10-22.
- Which host is cheapest for Moondream 3.1?
- PrimeIntellect is the only host with a published rate, $0.30 input / $2.50 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model. Host rates as listed on 2026-10-22.
- Does Moondream 3.1 offer batch or cached pricing?
- No. Neither a batch rate nor a prompt-cache rate is published for Moondream 3.1 as of 2026-10-22.
- What would Moondream 3.1 cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $170 on Moondream 3.1 at the list price quoted on 2026-10-22.
- Can Moondream 3.1 be self-hosted?
- Yes, within the terms of its licence. Moondream 3.1 is open weights, which is not the same as open source: the weights are published, but under Moondream Model License, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of Moondream 3.1 changed?
- Moondream 3.1 entered our daily price archive on 2026-10-17; tracking began on 2026-08-15. It listed at $0.30 input / $2.50 output per 1M tokens that day. No list price change since 2026-10-17. Last checked against the 2026-10-22 snapshot.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server