DeepSeek V3.2 Reasoner vs Codestral: Pricing Comparison

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

DeepSeek

DeepSeek V3.2 Reasoner

Pricing (per 1M tokens)

Input$0.2800
Output$0.4200
Cached Input$0.0280

Context & Output

Context Window128K tokens
Max Output64K tokens

Capabilities

Categorymid
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 V3.2 Reasoner

6.7% cheaper

Cheaper Output Price

DeepSeek V3.2 Reasoner

53.3% cheaper

Larger Context Window

Codestral

+128K tokens

Cost Comparison

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

DeepSeek V3.2 Reasoner

$0.7000

$0.2800/1M input + $0.4200/1M output

Codestral

$1.20

$0.3000/1M input + $0.9000/1M output

DeepSeek V3.2 Reasoner is 41.7% cheaper for this workload.

Frequently Asked Questions

Which is cheaper, DeepSeek V3.2 Reasoner or Codestral?
For input tokens, DeepSeek V3.2 Reasoner is cheaper at $0.2800 per 1M tokens. For output tokens, DeepSeek V3.2 Reasoner is cheaper at $0.4200 per 1M tokens. The overall cost depends on your workload's input/output ratio.
What is the context window size of DeepSeek V3.2 Reasoner vs Codestral?
DeepSeek V3.2 Reasoner has a context window of 128K tokens, while Codestral has 256K tokens. Codestral supports a larger context window of 256K tokens, which is beneficial for processing longer documents.

Need more tools?

Explore our complete suite of LLM calculators and comparison tools.