DeepSeek: Models Intelligence, Performance & Price
Analysis of DeepSeek's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by DeepSeek for your use-case.
Most Intelligent
UpdatedIntelligence index
Total 6 models
Fastest
Output speed
Total 6 models
Lowest Price
Blended price (per 1M tokens)
Total 6 models
DeepSeek offers 6 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 Pro (max) (44), DeepSeek V4 Pro (high) (41), DeepSeek V4 Flash (max) (40).
- For output speed, the fastest models are DeepSeek V4 Flash (115 t/s), DeepSeek V4 Flash (max) (109 t/s), DeepSeek V4 Flash (high) (106 t/s). Speed varies significantly across models, with a 80% difference between the fastest and slowest.
- For latency, DeepSeek V4 Flash (max) (1.16s), DeepSeek V4 Flash (high) (1.17s), DeepSeek V4 Flash (1.30s) offer the lowest time to first token.
- For pricing, DeepSeek V4 Flash (max) ($0.06), DeepSeek V4 Flash (high) ($0.06), DeepSeek V4 Flash ($0.06) offer the lowest blended prices per 1M tokens. Prices vary up to 3.0x across models.
- For context window size, DeepSeek V4 Pro (max) (1M), DeepSeek V4 Pro (high) (1M), DeepSeek V4 Flash (max) (1M) support the largest context windows on DeepSeek.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Agentic SaaS workflows
Legal agentic work, task all-pass rate
Agentic business operations
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence vs. Price
Context Window
Context Window
Pricing
Intelligence 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 Pro (max) | 1M | Open | 44 | $0.18 | 63 | 1.64 | 78.70 | 69.16 | |||
DeepSeek V4 Pro (high) | 1M | Open | 41* | $0.18 | 64 | 1.59 | 40.50 | 31.10 | |||
DeepSeek V4 Flash (max) | 1M | Open | 40 | $0.06 | 109 | 1.16 | 57.00 | 51.27 | |||
DeepSeek V4 Flash (high) | 1M | Open | 37* | $0.06 | 106 | 1.17 | 17.52 | 11.65 | |||
DeepSeek V3.2 | 128k | Open | 32 | $0.11 | -- | -- | -- | -- | |||
DeepSeek V4 Pro | 1M | Open | 31* | $0.18 | 67 | 1.60 | 9.05 | -- | |||
DeepSeek V4 Flash | 1M | Open | 29* | $0.06 | 115 | 1.30 | 5.65 | -- | |||
DeepSeek V3.2 Exp | 128k | Open | 25* | $0.12 | -- | -- | -- | -- | |||
DeepSeek V3.2 | 128k | Open | 25* | $0.29 | -- | -- | -- | -- | |||
DeepSeek V3.2 Exp | 128k | Open | 21* | $0.12 | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about DeepSeek
DeepSeek offers 6 models that we track: DeepSeek V4 Pro (max), DeepSeek V4 Pro (high), DeepSeek V4 Flash (max), DeepSeek V4 Flash (high), DeepSeek V4 Pro, and DeepSeek V4 Flash.
The most intelligent model available on DeepSeek is DeepSeek V4 Pro (max) with an Intelligence Index score of 44.
The fastest model on DeepSeek by output speed is DeepSeek V4 Flash at 115.0 tokens per second.
The model with the lowest time to first token on DeepSeek is DeepSeek V4 Flash (max) at 1.16s. Lower latency means faster initial response time.
The most affordable model on DeepSeek by blended price is DeepSeek V4 Flash (max) at $0.06 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on DeepSeek vary up to 3x across models, from $0.06 per 1M tokens for DeepSeek V4 Flash (max) to $0.18 per 1M tokens for DeepSeek V4 Pro.
Yes, DeepSeek offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 6 models on DeepSeek support JSON mode for structured output.
Yes, all 6 models on DeepSeek support function calling (tool use).
Yes, DeepSeek offers 4 reasoning models: DeepSeek V4 Pro (max), DeepSeek V4 Pro (high), DeepSeek V4 Flash (max), and DeepSeek V4 Flash (high). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 6 models on DeepSeek 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 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.