プロバイダー · 2026-11-12
digitalocean
| モデル | 入力 / 1M | 出力 / 1M | コンテキスト | プロバイダー | タグ |
|---|---|---|---|---|---|
| Multi-QA-mpnet-base-dot-v1 | $0.009 | Unknown | 512 | 1 | open-weights |
| All-MiniLM-L6-v2 | $0.009 | Unknown | 256 | 1 | open-weights |
| BGE Reranker v2 M3 | $0.010 | Unknown | 8K | 1 | open-weights |
| E5 Large v2 | $0.020 | Unknown | 512 | 1 | open-weights |
| BGE M3 | $0.020 | Unknown | 8K | 1 | open-weights |
| GTE Large (v1.5) | $0.090 | Unknown | 8K | 1 | open-weights |
| Arcee Trinity Large Thinking (Public Preview) | $0.250 | $0.900 | 128K | 1 | tools · reasoning · open-weights |
| Beam | $0.400 | $1.20 | 1.05M | 1 | tools · reasoning |
| MiMo V2.5 Pro | $0.800 | $3.00 | 262K | 1 | tools · reasoning · open-weights |
| Stable Diffusion 3.5 Large | 不明 | 不明 | 256 | 1 | open-weights |
| Wan2.2-T2V-A14B | 不明 | 不明 | 100 | 1 | open-weights |
| Ministral 3 14B派生 | $0.200 | $0.200 | 262K | 1 | tools · json · open-weights |
| Deepseek V4 Flash派生 | $0.140 | $0.280 | 1.05M | 1 | tools · open-weights |
| Anthropic Claude 5.5 Haiku派生 | $0.100 | $0.500 | 1M | 1 | tools · json · reasoning · vision |
| Nemotron-nano 12b v2-vl派生 | $0.200 | $0.600 | 128K | 1 | tools · reasoning · vision · open-weights |
| Nemotron 3 Nano Omni派生 | $0.500 | $0.900 | 66K | 1 | tools · json · reasoning · vision · open-weights |
| Deepseek 3.2派生 | $0.500 | $1.60 | 164K | 1 | tools · reasoning · open-weights |
| Anthropic Claude Sonnet 5派生 | $2.00 | $10.00 | 1M | 1 | tools · reasoning |
| Qwen3 TTS VoiceDesign派生 | 不明 | 不明 | 33K | 1 | open-weights |
Frequently asked questions
How many AI models does digitalocean offer?
We track 11 canonical digitalocean models plus 8 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.
Which digitalocean model is the cheapest?
Multi-QA-mpnet-base-dot-v1 is currently the lowest-priced digitalocean model, at $0.009 per 1M input tokens and Unknown per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which digitalocean model has the largest context window?
Beam leads at 1.05M tokens. This is the total of prompt + completion.
Which digitalocean models support tool calling?
Multiple digitalocean models support tool calling, with Arcee Trinity Large Thinking (Public Preview) being a popular pick. The capability column in the table above marks every model with digitalocean tool-calling support.
What are the best alternatives to digitalocean?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this digitalocean pricing data?
Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top digitalocean models
- Multi-QA-mpnet-base-dot-v1$0.01 in / $0.00 out
- All-MiniLM-L6-v2$0.01 in / $0.00 out
- BGE Reranker v2 M3$0.01 in / $0.00 out
- E5 Large v2$0.02 in / $0.00 out
- BGE M3$0.02 in / $0.00 out
Browse by use case
Browse by capability
最終更新：
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.