DigitalOcean Gradient models & pricing
DigitalOcean Gradient hosts 13 models (10 with public pricing) covering 1 modalities. DigitalOcean Gradient AI Platform — managed inference for open-source models. Cheapest input starts at $0.200/M tokens; the most premium goes up to $15.00/M. Use Future AGI's Agent Command Center to route any DigitalOcean Gradient model with cost-optimized fallback and unified observability.
chat 13
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| Llama3.8b Instruct | $0.200/M | $0.200/M | 8,192 | |
| Mistral Nemo Instruct 2407 | $0.300/M | $0.300/M | 128,000 | |
| Llama3.3 70B Instruct | $0.650/M | $0.650/M | 128,000 | |
| Anthropic Claude 3.5 Haiku | $0.800/M | $4.00/M | 200,000 | |
| DeepSeek R1 Distill Llama 70B | $0.990/M | $0.990/M | 32,768 | |
| OpenAI o3 mini | $1.10/M | $4.40/M | 200,000 | |
| OpenAI o3 | $2.00/M | $8.00/M | 200,000 | |
| Anthropic Claude 3.5 Sonnet | $3.00/M | $15.00/M | 200,000 | |
| Anthropic Claude 3.7 Sonnet | $3.00/M | $15.00/M | 200,000 | |
| Anthropic Claude 3 Opus | $15.00/M | $75.00/M | 200,000 | |
| Alibaba Qwen3.32b | — | — | 131,072 | |
| OpenAI GPT 4o | — | — | 128,000 | |
| OpenAI GPT 4o mini | — | — | 128,000 |
FAQ
How many DigitalOcean Gradient models are there?
13 DigitalOcean Gradient models are listed across 1 modality on this page. 10 have public per-token pricing.
How is DigitalOcean Gradient pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which DigitalOcean Gradient model is cheapest?
Input pricing on DigitalOcean Gradient starts at $0.200 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to DigitalOcean Gradient via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a DigitalOcean Gradient target, and call DigitalOcean Gradient models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.