Price Per TokenPrice Per Token
Mistral AI
Mistral AI
vs
OpenAI
OpenAI

Devstral 2 2512 vs GPT-5 Nano

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

100 out of our 304 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Devstral 2 2512 wins:

  • Cheaper output tokens
  • Better at coding

GPT-5 Nano wins:

  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at math
  • Supports vision
Price Advantage
Devstral 2 2512
Benchmark Advantage
GPT-5 Nano
Context Window
GPT-5 Nano
Speed
GPT-5 Nano

Pricing Comparison

Price Comparison

MetricDevstral 2 2512GPT-5 NanoWinner
Input (per 1M tokens)$0.05$0.05Tie
Output (per 1M tokens)$0.22$0.40 Devstral 2 2512
Cache Read (per 1M)N/A$5000.00 GPT-5 Nano
Using a 3:1 input/output ratio, Devstral 2 2512 is 33% cheaper overall.

Devstral 2 2512 Providers

Chutes $0.05 (Cheapest)
Mistral $0.40

GPT-5 Nano Providers

OpenAI $0.05 (Cheapest)
Azure $0.05 (Cheapest)

Benchmark Comparison

6
Benchmarks Compared
1
Devstral 2 2512 Wins
5
GPT-5 Nano Wins

Benchmark Scores

BenchmarkDevstral 2 2512GPT-5 NanoWinner
Intelligence Index
Overall intelligence score
22.026.7
Coding Index
Code generation & understanding
23.720.3
Math Index
Mathematical reasoning
36.783.7
MMLU Pro
Academic knowledge
76.278.0
GPQA
Graduate-level science
59.467.6
LiveCodeBench
Competitive programming
44.878.9
GPT-5 Nano shows stronger mathematical reasoning abilities.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Devstral 2 2512
Other models

Context & Performance

Context Window

Devstral 2 2512
262,144
tokens
Max output: 65,536 tokens
GPT-5 Nano
400,000
tokens
Max output: 128,000 tokens
GPT-5 Nano has a 34% larger context window.

Speed Performance

MetricDevstral 2 2512GPT-5 NanoWinner
Tokens/second64.0 tok/s118.7 tok/s
Time to First Token0.41s122.66s
GPT-5 Nano responds 86% faster on average.

Capabilities

Feature Comparison

FeatureDevstral 2 2512GPT-5 Nano
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyDevstral 2 2512GPT-5 Nano
LicenseOpen SourceProprietary
AuthorMistral AIOpenAI
ReleasedDec 2025Aug 2025

Devstral 2 2512 Modalities

Input
text
Output
text

GPT-5 Nano Modalities

Input
textimagefile
Output
text

Related Comparisons

Compare Devstral 2 2512 with:

Compare GPT-5 Nano with:

Frequently Asked Questions

Devstral 2 2512 has cheaper input pricing at $0.05/M tokens. Devstral 2 2512 has cheaper output pricing at $0.22/M tokens.
Devstral 2 2512 scores higher on coding benchmarks with a score of 23.7, compared to GPT-5 Nano's score of 20.3.
Devstral 2 2512 has a 262,144 token context window, while GPT-5 Nano has a 400,000 token context window.
Devstral 2 2512 does not support vision. GPT-5 Nano supports vision.