DigitalOcean: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by DigitalOcean for your use-case.
Most Intelligent
Updated
GLM-5.3 (max)
Kimi K3 (max)GLM-5.3-Flash
Qwen3.8 2.4T A95B
DeepSeek V4.1 Flash (max)Intelligence index
Total 12 models
Fastest
DeepSeek V4 Pro 0813 (max)DeepSeek V3.2
MiniMax-M2.5DeepSeek V3.2 (Non-reasoning)Qwen3.8 2.4T A95BOutput speed
Total 12 models
Lowest Price
DeepSeek V4 Flash 0731 (max)GLM-5.3-FlashDeepSeek V4.1 Flash (max)MiniMax-M2.5DeepSeek V3.2Blended price (per 1M tokens)
Total 12 models
DigitalOcean offers 12 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on DigitalOcean are GLM-5.3 (max) (45), Kimi K3 (max) (44), and GLM-5.3-Flash (42).
- For output speed, the fastest models are DeepSeek V4 Pro 0813 (max) (90 t/s), DeepSeek V3.2 (86 t/s), and MiniMax-M2.5 (83 t/s). Speed varies significantly across models, with a 52% difference between the fastest and slowest.
- For latency, DeepSeek V3.2 (Non-reasoning) (1.11s), Qwen3.5 397B A17B (Non-reasoning) (1.97s), and DeepSeek V4 Pro 0813 (max) (23.20s) offer the lowest time to first answer token.
- For pricing, DeepSeek V4 Flash 0731 (max) ($0.08), GLM-5.3-Flash ($0.10), and DeepSeek V4.1 Flash (max) ($0.18) offer the lowest blended prices per 1M tokens. Prices vary up to 4.8x across models.
- For context window size, GLM-5.3 (max) (1M), Kimi K3 (max) (1M), and GLM-5.3-Flash (1M) support the largest context windows on DigitalOcean.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic knowledge work, (Elo-500)/2000
Agentic real-world work tasks, (Elo-500)/2000
Agentic SaaS workflows
Agentic coding & terminal use
Coding
Reasoning & knowledge
Professional document reasoning, All-pass
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Agentic tool use
Kubernetes incident root-cause analysis
Visual reasoning
Medical long context reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
GLM-5.3 (max) | 1.05M | Open | 45 | $2.31 | 43 | 1.13 | 59.03 | 46.32 | |||
Kimi K3 (max) | 1.05M | Open | 44 | $2.55 | 36 | 1.31 | 71.41 | 56.08 | |||
GLM-5.3-Flash | 1.05M | Open | 42 | $0.33 | 49 | 3.01 | 53.93 | 40.73 | |||
Qwen3.8 2.4T A95B | 262k | Open | 40 | $1.81 | 59 | 2.09 | 44.44 | 33.88 | |||
DeepSeek V4.1 Flash (max) | 1M | Open | 39 | $0.29 | 57 | 0.98 | 45.13 | 35.32 | |||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.83 | 90 | 0.88 | 28.78 | 22.32 | |||
DeepSeek V4 Flash 0731 (max) | 1.05M | Open | 34 | $0.56 | 51 | 1.00 | 50.16 | 39.33 | |||
MiniMax-M2.5 | 197k | Open | 23* | -- | 83 | 1.07 | 31.37 | 24.24 | |||
DeepSeek V3.2 | 128k | Open | 21* | -- | 86 | 0.94 | 29.88 | 23.16 | |||
Qwen3.5 397B A17B (Non-reasoning) | 262k | Open | 21* | -- | 5 | 1.97 | 100.29 | -- | |||
Qwen3.5 397B A17B | 262k | Open | 18 | $0.17 | 10 | 1.67 | 379.99 | 327.01 | |||
DeepSeek V3.2 (Non-reasoning) | 128k | Open | 16* | -- | 76 | 1.11 | 7.66 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about DigitalOcean
DigitalOcean offers 12 models that we track: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, Qwen3.8 2.4T A95B, DeepSeek V4.1 Flash (max), DeepSeek V4 Pro 0813 (max), DeepSeek V4 Flash 0731 (max), MiniMax-M2.5, DeepSeek V3.2, Qwen3.5 397B A17B (Non-reasoning), Qwen3.5 397B A17B, and DeepSeek V3.2 (Non-reasoning).
The most intelligent model available on DigitalOcean is GLM-5.3 (max) with an Intelligence Index score of 45.
The fastest model on DigitalOcean by output speed is DeepSeek V4 Pro 0813 (max) at 89.6 tokens per second.
The model with the lowest time to first answer token on DigitalOcean is DeepSeek V3.2 (Non-reasoning) at 1.11s. Lower latency means faster initial response time.
The most affordable model on DigitalOcean by blended price is DeepSeek V4 Flash 0731 (max) at $0.08 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on DigitalOcean vary up to 31x across models, from $0.08 per 1M tokens for DeepSeek V4 Flash 0731 (max) to $2.31 per 1M tokens for Kimi K3 (max).
Yes, DigitalOcean offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 12 models on DigitalOcean support JSON mode for structured output.
Yes, all 12 models on DigitalOcean support function calling (tool use).
Yes, DigitalOcean offers 10 reasoning models: GLM-5.3 (max), Kimi K3 (max), GLM-5.3-Flash, Qwen3.8 2.4T A95B, DeepSeek V4.1 Flash (max), DeepSeek V4 Pro 0813 (max), DeepSeek V4 Flash 0731 (max), MiniMax-M2.5, DeepSeek V3.2, and Qwen3.5 397B A17B. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 12 models on DigitalOcean are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on DigitalOcean, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.