DeepSeek V4 Pro vs Magistral Small: Pricing Comparison

Compare pricing, capabilities, and costs for your LLM workloads.

DeepSeek

DeepSeek V4 Pro

Pricing (per 1M tokens)

Input$0.4350
Output$0.8700
Cached Input$0.003625

Context & Output

Context Window1M tokens
Max Output384K tokens

Capabilities

Categoryflagship
Multimodaltext
Fine-tuningNo
StreamingYes

Mistral

Magistral Small

Pricing (per 1M tokens)

Input$0.5000
Output$1.50

Context & Output

Context Window40K tokens
Max Output16.4K tokens

Capabilities

Categorymid
Multimodaltext
Fine-tuningNo
StreamingYes

Quick Verdict

Cheaper Input Price

DeepSeek V4 Pro

13.0% cheaper

Cheaper Output Price

DeepSeek V4 Pro

42.0% cheaper

Larger Context Window

DeepSeek V4 Pro

+960K tokens

Cost Comparison

Sample workload: 1,000,000 input tokens + 1,000,000 output tokens

DeepSeek V4 Pro

$1.31

$0.4350/1M input + $0.8700/1M output

Magistral Small

$2.00

$0.5000/1M input + $1.50/1M output

DeepSeek V4 Pro is 34.8% cheaper for this workload.

Frequently Asked Questions

Which is cheaper, DeepSeek V4 Pro or Magistral Small?
For input tokens, DeepSeek V4 Pro is cheaper at $0.4350 per 1M tokens. For output tokens, DeepSeek V4 Pro is cheaper at $0.8700 per 1M tokens. The overall cost depends on your workload's input/output ratio.
What is the context window size of DeepSeek V4 Pro vs Magistral Small?
DeepSeek V4 Pro has a context window of 1M tokens, while Magistral Small has 40K tokens. DeepSeek V4 Pro supports a larger context window of 1M tokens, which is beneficial for processing longer documents.

Need more tools?

Explore our complete suite of LLM calculators and comparison tools.