GPT-5 nano vs Codestral: Pricing Comparison

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

OpenAI

GPT-5 nano

Pricing (per 1M tokens)

Input$0.0500
Output$0.4000
Cached Input$0.005000
Batch Input$0.0250
Batch Output$0.2000

Context & Output

Context Window400K tokens
Max Output128K 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

GPT-5 nano

83.3% cheaper

Cheaper Output Price

GPT-5 nano

55.6% cheaper

Larger Context Window

GPT-5 nano

+144K tokens

Cost Comparison

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

GPT-5 nano

$0.4500

$0.0500/1M input + $0.4000/1M output

Codestral

$1.20

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

GPT-5 nano is 62.5% cheaper for this workload.

Frequently Asked Questions

Which is cheaper, GPT-5 nano or Codestral?
For input tokens, GPT-5 nano is cheaper at $0.0500 per 1M tokens. For output tokens, GPT-5 nano is cheaper at $0.4000 per 1M tokens. The overall cost depends on your workload's input/output ratio.
What is the context window size of GPT-5 nano vs Codestral?
GPT-5 nano has a context window of 400K tokens, while Codestral has 256K tokens. GPT-5 nano supports a larger context window of 400K tokens, which is beneficial for processing longer documents.

Need more tools?

Explore our complete suite of LLM calculators and comparison tools.