DigitalOcean Gradient API pricing
Updated
DigitalOcean Gradient lists standard per-token prices for 59 models. The cheapest is GPT-5 Nano at USD 0.05 input and USD 0.40 output per 1M tokens; the dearest is GPT-5.4 Pro at USD 30 / USD 180. It publishes cached-input prices for 56 of them, plus flex / spot and fast tiers (no batch or priority). Checked 2026-11-14.
- Models with a standard price
- 59
- Median input / output
- USD 1.75 / USD 8
- Cached-input prices
- 56 of 59
- Cheapest host for
- 0 of 57 shared models
Which models is DigitalOcean Gradient the cheapest provider for?
None outright. Of the 57 models that DigitalOcean Gradient shares with other providers, 16 are cheaper elsewhere at the standard tier, and DigitalOcean Gradient ties the lowest price for the other 41, where another provider charges the same. It is the dearest provider for 6.
How does DigitalOcean Gradient price the most widely hosted models?
The 6 models DigitalOcean Gradient sells that the most other providers also sell, with DigitalOcean Gradient's rank among them on the 3:1 blend.
| Model | DigitalOcean Gradient | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 1.40 / USD 4.40 | 6 of 24 | DeepInfra USD 0.5625 / USD 2.50 |
| OpenAI GPT OSS 120B | USD 0.10 / USD 0.70 | 10 of 21 | CoreWeave Forge USD 0.03 / USD 0.17 |
| GLM 5.3 Flash | USD 0.15 / USD 0.50 | 3 of 20 | GMI Cloud USD 0.075 / USD 0.25 |
| GLM 5.2 | USD 1.40 / USD 4.40 | 5 of 19 | DeepInfra USD 0.5625 / USD 1.80 |
| Kimi K3 | USD 3 / USD 15 | 5 of 18 | Chutes USD 1.85 / USD 9.50 |
| DeepSeek V4.1 Flash | USD 0.30 / USD 1.20 | 5 of 16 | DeepInfra USD 0.14 / USD 0.42 |
Which model makers does DigitalOcean Gradient sell?
DigitalOcean Gradient prices models from 12 makers. OpenAI leads with 24 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| OpenAI | 24 | GPT-5 Nano USD 0.05 / USD 0.40 | USD 1.875 / USD 10 |
| Anthropic | 15 | Claude Haiku 5.5 USD 0.10 / USD 0.50 | USD 5 / USD 25 |
| DeepSeek | 6 | DeepSeek V4 Flash 0731 USD 0.14 / USD 0.28 | USD 0.40 / USD 1.40 |
| Moonshot AI | 3 | Kimi K2.6 USD 0.95 / USD 4 | USD 2 / USD 10 |
| Z.ai | 3 | GLM 5.3 Flash USD 0.15 / USD 0.50 | USD 1.40 / USD 4.40 |
| MiniMax | 2 | MiniMax M3.1 Flash USD 0.15 / USD 0.60 | USD 0.225 / USD 0.90 |
| Arcee AI | 1 | Trinity Large USD 0.25 / USD 0.90 | — |
| Mistral AI | 1 | Ministral 3 14B USD 0.20 / USD 0.20 | — |
| NVIDIA | 1 | NVIDIA Nemotron 3.5 Super VL USD 0.30 / USD 0.65 | — |
| Qwen | 1 | Qwen3.8 Max USD 2 / USD 6 | — |
| Reflection AI | 1 | Beam 1.0 501B A23B USD 0.40 / USD 1.20 | — |
| Xiaomi | 1 | MiMo V2.5 Pro USD 0.80 / USD 3 | — |
DigitalOcean Gradient price list
USD per 1M tokens: 95 prices for 59 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means DigitalOcean Gradient is cheaper. Of 51 hosted model prices with a maker price to compare, 0 are below the maker's and 1 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| Beam 1.0 501B A23B | standard | USD 0.40 | USD 0.04 | USD 1.20 | not stated | — | source |
| Claude Fable 5 | standard | USD 10 | USD 1 | USD 50 | not stated | same | source |
| Claude Fable 5.1 | standard | USD 10 | USD 0.25 | USD 50 | not stated | same | source |
| Claude Fable 5.2 | standard fast | USD 8 USD 16 | USD 0.20 USD 0.40 | USD 40 USD 80 | not stated | same | source |
| Claude Haiku 4.5 | standard | USD 1 | USD 0.10 | USD 5 | not stated | same | source |
| Claude Haiku 5.5 | standard | USD 0.10 | USD 0.01 | USD 0.50 | not stated | same | source |
| Claude Opus 4.5 | standard | USD 5 | USD 0.50 | USD 25 | not stated | same | source |
| Claude Opus 4.6 | standard | USD 5 | USD 0.50 | USD 25 | not stated | same | source |
| Claude Opus 4.7 | standard | USD 5 | USD 0.50 | USD 25 | not stated | same | source |
| Claude Opus 4.8 | standard fast | USD 5 USD 10 | USD 0.50 USD 1 | USD 25 USD 50 | not stated | same | source |
| Claude Opus 5 | standard fast | USD 5 USD 10 | USD 0.50 USD 1 | USD 25 USD 50 | not stated | same | source |
| Claude Opus 5.5 | standard fast | USD 4 USD 8 | USD 0.20 USD 0.40 | USD 20 USD 40 | not stated | same | source |
| Claude Sonnet 4.5 | standard | USD 3 | USD 0.30 | USD 15 | not stated | same | source |
| Claude Sonnet 4.6 | standard | USD 3 | USD 0.30 | USD 15 | not stated | same | source |
| Claude Sonnet 5 | standard | USD 2 | USD 0.20 | USD 10 | not stated | same | source |
| Claude Sonnet 5.5 | standard | USD 2 | USD 0.20 | USD 10 | not stated | same | source |
| DeepSeek V3.2 | standard | USD 0.50 | USD 0.15 | USD 1.60 | not stated | — | source |
| DeepSeek V4 Flash 0731 | standard | USD 0.14 | USD 0.028 | USD 0.28 | not stated | — | source |
| DeepSeek V4 Pro | standard | USD 1.74 | USD 0.348 | USD 3.48 | not stated | +10% | source |
| DeepSeek V4 Pro 0813 | standard | USD 1.32 | USD 0.044 | USD 3.96 | not stated | same | source |
| DeepSeek V4.1 Flash | standard | USD 0.30 | USD 0.006 | USD 1.20 | not stated | same | source |
| DeepSeek V4.1 Flash 1017 | standard | USD 0.30 | USD 0.006 | USD 1.20 | not stated | same | source |
| GLM 5.2 | standard | USD 1.40 | USD 0.21 | USD 4.40 | not stated | same | source |
| GLM 5.3 | standard | USD 1.40 | USD 0.26 | USD 4.40 | not stated | same | source |
| GLM 5.3 Flash | standard | USD 0.15 | USD 0.03 | USD 0.50 | not stated | same | source |
| GPT-4.1 (2025-04-14) | standard fast | USD 2 USD 3.50 | USD 0.50 USD 0.875 | USD 8 USD 14 | not stated | same | source |
| GPT-4o | standard fast | USD 2.50 USD 4.25 | USD 1.25 USD 2.125 | USD 10 USD 17 | not stated | same | source |
| GPT-4o mini | standard fast | USD 0.15 USD 0.25 | USD 0.075 USD 0.125 | USD 0.60 USD 1 | not stated | same | source |
| GPT-5 (2025-08-07) | standard flex / spot fast | USD 1.25 USD 0.625 USD 2.50 | USD 0.125 USD 0.0625 USD 0.25 | USD 10 USD 5 USD 20 | not stated | same | source |
| GPT-5 Mini | standard flex / spot fast | USD 0.25 USD 0.125 USD 0.45 | USD 0.025 USD 0.0125 USD 0.045 | USD 2 USD 1 USD 3.60 | not stated | same | source |
| GPT-5 Nano | standard flex / spot | USD 0.05 USD 0.025 | USD 0.005 USD 0.0025 | USD 0.40 USD 0.20 | not stated | same | source |
| GPT-5.2 | standard flex / spot fast | USD 1.75 USD 0.875 USD 3.50 | USD 0.175 USD 0.0875 USD 0.35 | USD 14 USD 7 USD 28 | not stated | same | source |
| GPT-5.2 Pro | standard | USD 21 | — | USD 168 | not stated | same | source |
| GPT-5.3 Codex | standard fast | USD 1.75 USD 3.50 | USD 0.175 USD 0.35 | USD 14 USD 28 | not stated | same | source |
| GPT-5.4 | standard flex / spot fast | USD 2.50 USD 1.25 USD 5 | USD 0.25 USD 0.13 USD 0.50 | USD 15 USD 7.50 USD 30 | not stated | same | source |
| GPT-5.4 Mini | standard flex / spot fast | USD 0.75 USD 0.375 USD 1.50 | USD 0.075 USD 0.0375 USD 0.15 | USD 4.50 USD 2.25 USD 9 | not stated | same | source |
| GPT-5.4 Nano | standard flex / spot | USD 0.20 USD 0.10 | USD 0.02 USD 0.01 | USD 1.25 USD 0.625 | not stated | same | source |
| GPT-5.4 Pro | standard flex / spot | USD 30 USD 15 | — — | USD 180 USD 90 | not stated | same | source |
| GPT-5.5 | standard flex / spot fast | USD 5 USD 2.50 USD 12.50 | USD 0.50 USD 0.25 USD 1.25 | USD 30 USD 15 USD 75 | not stated | same | source |
| GPT-5.6 Luna | standard flex / spot fast | USD 0.20 USD 0.10 USD 0.40 | USD 0.02 USD 0.01 USD 0.04 | USD 1.20 USD 0.60 USD 2.40 | not stated | same | source |
| GPT-5.6 Sol | standard flex / spot fast | USD 4 USD 2 USD 8 | USD 0.40 USD 0.20 USD 0.80 | USD 20 USD 10 USD 40 | not stated | same | source |
| GPT-5.6 Terra | standard flex / spot fast | USD 2 USD 1 USD 4 | USD 0.20 USD 0.10 USD 0.40 | USD 12 USD 6 USD 24 | not stated | same | source |
| GPT-6 Astra | standard flex / spot fast | USD 10 USD 5 USD 20 | USD 1 USD 0.50 USD 2 | USD 50 USD 25 USD 100 | not stated | same | source |
| GPT-6 Luna | standard | USD 0.10 | USD 0.01 | USD 0.50 | not stated | same | source |
| GPT-6 Sol | standard | USD 2 | USD 0.20 | USD 10 | not stated | same | source |
| GPT-6.1 Sol | standard flex / spot fast | USD 2 USD 1 USD 4 | USD 0.10 USD 0.05 USD 0.20 | USD 10 USD 5 USD 20 | not stated | same | source |
| GPT-6.1 Terra | standard fast | USD 1 USD 2 | USD 0.05 USD 0.10 | USD 5 USD 10 | not stated | same | source |
| Kimi K2.6 | standard | USD 0.95 | USD 0.19 | USD 4 | not stated | same | source |
| Kimi K3 | standard | USD 3 | USD 0.30 | USD 15 | not stated | same | source |
| Kimi K3.1 Pro | standard | USD 2 | USD 0.20 | USD 10 | not stated | same | source |
| MiMo V2.5 Pro | standard | USD 0.80 | USD 0.16 | USD 3 | not stated | — | source |
| MiniMax M2.5 | standard | USD 0.30 | USD 0.06 | USD 1.20 | not stated | — | source |
| MiniMax M3.1 Flash | standard | USD 0.15 | USD 0.015 | USD 0.60 | not stated | same | source |
| Ministral 3 14B | standard | USD 0.20 | USD 0.04 | USD 0.20 | not stated | same | source |
| NVIDIA Nemotron 3.5 Super VL | standard | USD 0.30 | USD 0.06 | USD 0.65 | not stated | — | source |
| o3 (2025-04-16) | standard flex / spot fast | USD 2 USD 1 USD 3.50 | USD 0.50 USD 0.25 USD 0.875 | USD 8 USD 4 USD 14 | not stated | same | source |
| OpenAI GPT OSS 120B | standard | USD 0.10 | — | USD 0.70 | not stated | — | source |
| Qwen3.8 Max | standard | USD 2 | USD 0.20 | USD 6 | not stated | same | source |
| Trinity Large | standard | USD 0.25 | USD 0.06 | USD 0.90 | not stated | — | source |
- Cached "—" means DigitalOcean Gradient's page shows no cache price for that row; budget cached tokens at the input price.
- Context "not stated": DigitalOcean Gradient's pricing page does not give context windows.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does DigitalOcean Gradient publish?
- flex / spot (15 rows). Across 15 models with both prices, the median flex / spot price is 50% below standard.
- fast (21 rows). Across 21 models with both prices, the median fast price is 2× standard (range 1.67× standard to 2.5× standard).
Cached input: 56 of 59 standard prices include a cache-read price, a median 10% of the input price. What cached input means.
What we recorded about DigitalOcean Gradient's pricing page: Serverless inference table in DigitalOcean docs (Inference pricing). Cache-write prices are published but not stored here (no field). Batch is described only as "up to a 50% discount" on OpenAI and Anthropic models, so no batch rows. Non-text models (fal, TTS, image, video) and the TypeSafe "Jev" model (input-only price) left out. Model ids and context windows are not on the pricing page.
Is DigitalOcean Gradient cheaper than the model makers' own APIs?
Mostly it charges the same as the maker. Of 51 standard prices for models whose maker sells its own API, 0 are below the maker's price, 1 above and 50 the same, on the 3:1 blend. The median difference is zero. The biggest markup is DeepSeek V4 Pro, 10% above DeepSeek.
BroadNet Inference and DigitalOcean Gradient
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that DigitalOcean Gradient prices: DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against DigitalOcean Gradient's USD 0.30 / USD 1.20 (BroadNet is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against DigitalOcean Gradient's USD 1.40 / USD 4.40 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on DigitalOcean Gradient
- DigitalOcean Gradient's own pricing page (the source; checked 2026-11-14)
- All 41 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Questions
How much does the DigitalOcean Gradient API cost per token?
DigitalOcean Gradient's standard prices run from USD 0.05 input and USD 0.40 output per 1M tokens (GPT-5 Nano) to USD 30 / USD 180 (GPT-5.4 Pro). The median across 59 standard prices is USD 1.75 input and USD 8 output per 1M, which is USD 0.00000175 per input token. Input, cached input and output are billed separately.
What is the cheapest model on DigitalOcean Gradient?
GPT-5 Nano, at USD 0.05 input and USD 0.40 output per 1M tokens (USD 0.1375 on a 3:1 input-to-output blend). The cheapest from other makers: Claude Haiku 5.5 (Anthropic) at USD 0.10 / USD 0.50; DeepSeek V4 Flash 0731 (DeepSeek) at USD 0.14 / USD 0.28; Kimi K2.6 (Moonshot AI) at USD 0.95 / USD 4.
Is DigitalOcean Gradient cheaper than other providers?
It depends on the model. Of 57 models that other providers also price, DigitalOcean Gradient is the cheapest standard price for none; it ties the lowest price, without beating it, for 41; another provider is cheaper for 16; and it is the dearest for 6. Its median rank is 1 of a median 5 providers, on a 3:1 input-to-output blend.
Does DigitalOcean Gradient have batch, cached or priority pricing?
Cached input: yes, for 56 of 59 standard prices, at a median 10% of the input price. Other tiers: flex / spot on 15 rows (median input 50% below standard); fast on 21 rows (median input 2× standard).
How much does a chatbot cost per month on DigitalOcean Gradient?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 9.27 on GPT-5 Nano, USD 231.75 on GPT-5 (2025-08-07) (the middle of DigitalOcean Gradient's list) and USD 5,940 on GPT-5.4 Pro. Try your own numbers.