This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
DeepSeek has launched a newer release, DeepSeek V3.2. We suggest considering it instead.
DeepSeek V3.2 Exp (Non-reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V3.2 Exp (Non-reasoning) for your use-case.
Fastest
Output speed
Total 1 provider
Lowest Latency
Time to first token
Total 1 provider
Lowest Price
DeepSeekBlended price (per 1M tokens)
Total 1 provider
DeepSeek V3.2 Exp (non-reasoning) is available through DeepSeek.
Please see the models page for DeepSeek V3.2 Exp (Non-reasoning) for details of the model and its intelligence compared to other models.
Pricing
Pricing: Cache Hit, Input, and Output: DeepSeek V3.2 Exp (Non-reasoning)
Cost per Intelligence Index Task: DeepSeek V3.2 Exp (Non-reasoning)
Output Speed vs. Price: DeepSeek V3.2 Exp (Non-reasoning)
Speed
Measured by Output Speed (tokens per second)
Output Speed: DeepSeek V3.2 Exp (Non-reasoning)
Time per Intelligence Index Task: DeepSeek V3.2 Exp (Non-reasoning)
Cost per Task vs. Time per Task: DeepSeek V3.2 Exp (Non-reasoning)
Latency
Measured by Time (seconds) to First Token
Time to First Token: DeepSeek V3.2 Exp (Non-reasoning)
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: DeepSeek V3.2 Exp (Non-reasoning)
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about DeepSeek V3.2 Exp (Non-reasoning) providers
DeepSeek V3.2 Exp (Non-reasoning) is available through 1 API provider: DeepSeek. Each provider offers different performance characteristics and pricing.
DeepSeek V3.2 Exp (Non-reasoning) is currently available through 1 API provider that we benchmark and track.
The most affordable provider for DeepSeek V3.2 Exp (Non-reasoning) by blended price is DeepSeek ($0.12 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The provider with the lowest input token pricing for DeepSeek V3.2 Exp (Non-reasoning) is DeepSeek ($0.28 per 1M input tokens).
The provider with the lowest output token pricing for DeepSeek V3.2 Exp (Non-reasoning) is DeepSeek ($0.42 per 1M output tokens).
The only provider of DeepSeek V3.2 Exp (Non-reasoning) supports JSON mode for structured output.
The only provider of DeepSeek V3.2 Exp (Non-reasoning) supports function calling (tool use).
When choosing a provider for DeepSeek V3.2 Exp (Non-reasoning), consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
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.
For information about DeepSeek V3.2 Exp (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview