DeepSeek: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by DeepSeek for your use-case.
Most Intelligent
UpdatedDeepSeek V4.1 Flash (max)DeepSeek V4 Pro 0813 (max)DeepSeek V4 Flash Vision (max)DeepSeek V4 Flash 0731 (max)DeepSeek V4 Pro (max)Intelligence index
Total 7 models
Fastest
DeepSeek V4.1 Flash (max)DeepSeek V4 Flash Vision (max)DeepSeek V4 Flash 0731 (max)DeepSeek V4 Pro (Non-reasoning)DeepSeek V4 Pro 0813 (max)Output speed
Total 7 models
Lowest Price
DeepSeek V4 Pro (max)DeepSeek V4 Pro (high)DeepSeek V4 Pro (Non-reasoning)DeepSeek V4.1 Flash (max)DeepSeek V4 Flash Vision (max)Blended price (per 1M tokens)
Total 7 models
DeepSeek offers 7 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 DeepSeek are DeepSeek V4.1 Flash (max) (40), DeepSeek V4 Pro 0813 (max) (36), and DeepSeek V4 Flash Vision (max) (35).
- For output speed, the fastest models are DeepSeek V4.1 Flash (max) (214 t/s), DeepSeek V4 Flash Vision (max) (214 t/s), and DeepSeek V4 Flash 0731 (max) (213 t/s). Speed varies significantly across models, with a 174% difference between the fastest and slowest.
- For latency, DeepSeek V4 Pro (Non-reasoning) (1.57s), DeepSeek V4.1 Flash (max) (10.50s), and DeepSeek V4 Flash 0731 (max) (10.55s) offer the lowest time to first answer token.
- For pricing, DeepSeek V4 Pro (max) ($0.18), DeepSeek V4 Pro (high) ($0.18), and DeepSeek V4 Pro (Non-reasoning) ($0.18) offer the lowest blended prices per 1M tokens.
- For context window size, DeepSeek V4 Pro 0813 (max) (1M), DeepSeek V4.1 Flash (max) (1M), and DeepSeek V4 Flash Vision (max) (1M) support the largest context windows on DeepSeek.
- DeepSeek V4.1 Flash (max) offers the best combination of intelligence and speed. For cost optimization, DeepSeek V4 Pro (max) provides the most competitive pricing.
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
Instruction following
Agentic tool use
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual 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 | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
DeepSeek V4.1 Flash (max) | 1M | Open | 40 | $0.27 | 199 | 1.13 | 13.72 | 10.07 | |||
DeepSeek V4 Pro 0813 (max) | 1.05M | Open | 36 | $0.67 | 72 | 1.77 | 36.34 | 27.66 | |||
DeepSeek V4 Flash Vision (max) | 1M | Proprietary | 35 | $0.31 | 217 | 1.07 | 12.58 | 9.21 | |||
DeepSeek V4 Flash 0731 (max) | 1M | Open | 35 | $0.22 | 210 | 0.98 | 12.88 | 9.52 | |||
DeepSeek V4 Pro (max) | 1M | Open | 31 | $0.12 | 67 | 1.45 | 73.71 | 64.85 | |||
DeepSeek V4 Pro (high) | 1M | Open | 30* | -- | 65 | 1.58 | 39.90 | 30.63 | |||
DeepSeek V3.2 | 128k | Open | 21* | -- | -- | -- | -- | -- | |||
DeepSeek V4 Pro (Non-reasoning) | 1M | Open | 21* | -- | 67 | 1.61 | 9.09 | -- | |||
DeepSeek V3.2 Exp | 128k | Open | 17* | -- | -- | -- | -- | -- | |||
DeepSeek V3.2 (Non-reasoning) | 128k | Open | 16* | -- | -- | -- | -- | -- | |||
DeepSeek V3.2 Exp (Non-reasoning) | 128k | Open | 14* | -- | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about DeepSeek
DeepSeek offers 7 models that we track: DeepSeek V4.1 Flash (max), DeepSeek V4 Pro 0813 (max), DeepSeek V4 Flash Vision (max), DeepSeek V4 Flash 0731 (max), DeepSeek V4 Pro (max), DeepSeek V4 Pro (high), and DeepSeek V4 Pro (Non-reasoning).
The most intelligent model available on DeepSeek is DeepSeek V4.1 Flash (max) with an Intelligence Index score of 40.
The fastest model on DeepSeek by output speed is DeepSeek V4.1 Flash (max) at 214.4 tokens per second.
The model with the lowest time to first answer token on DeepSeek is DeepSeek V4 Pro (Non-reasoning) at 1.57s. Lower latency means faster initial response time.
The most affordable model on DeepSeek by blended price is DeepSeek V4 Pro (max) at $0.18 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on DeepSeek vary up to 4x across models, from $0.18 per 1M tokens for DeepSeek V4 Pro (max) to $0.69 per 1M tokens for DeepSeek V4 Pro 0813 (max).
Yes, DeepSeek offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 7 models on DeepSeek support JSON mode for structured output.
Yes, all 7 models on DeepSeek support function calling (tool use).
Yes, DeepSeek offers 6 reasoning models: DeepSeek V4.1 Flash (max), DeepSeek V4 Pro 0813 (max), DeepSeek V4 Flash Vision (max), DeepSeek V4 Flash 0731 (max), DeepSeek V4 Pro (max), and DeepSeek V4 Pro (high). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, 6 of 7 models on DeepSeek are open weight models: DeepSeek V4.1 Flash (max), DeepSeek V4 Pro 0813 (max), DeepSeek V4 Flash 0731 (max), DeepSeek V4 Pro (max), DeepSeek V4 Pro (high), and DeepSeek V4 Pro (Non-reasoning).
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 DeepSeek, 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.