DeepSeek V4 Flash vs Codestral: Pricing Comparison
Compare pricing, capabilities, and costs for your LLM workloads.
DeepSeek
DeepSeek V4 Flash
Pricing (per 1M tokens)
Input$0.1400
Output$0.2800
Cached Input$0.0280
Context & Output
Context Window1M tokens
Max Output384K tokens
Capabilities
Categorybudget
Multimodaltext
Fine-tuningNo
StreamingYes
Mistral
Codestral
Pricing (per 1M tokens)
Input$0.3000
Output$0.9000
Context & Output
Context Window256K tokens
Max Output32.8K tokens
Capabilities
Categorymid
Multimodaltext
Fine-tuningNo
StreamingYes
Quick Verdict
Cheaper Input Price
DeepSeek V4 Flash
53.3% cheaper
Cheaper Output Price
DeepSeek V4 Flash
68.9% cheaper
Larger Context Window
DeepSeek V4 Flash
+744K tokens
Cost Comparison
Sample workload: 1,000,000 input tokens + 1,000,000 output tokens
DeepSeek V4 Flash
$0.4200
$0.1400/1M input + $0.2800/1M output
Codestral
$1.20
$0.3000/1M input + $0.9000/1M output
DeepSeek V4 Flash is 65.0% cheaper for this workload.
Frequently Asked Questions
Which is cheaper, DeepSeek V4 Flash or Codestral?
For input tokens, DeepSeek V4 Flash is cheaper at $0.1400 per 1M tokens. For output tokens, DeepSeek V4 Flash is cheaper at $0.2800 per 1M tokens. The overall cost depends on your workload's input/output ratio.
What is the context window size of DeepSeek V4 Flash vs Codestral?
DeepSeek V4 Flash has a context window of 1M tokens, while Codestral has 256K tokens. DeepSeek V4 Flash 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.