Skip to main content
idapt
HomeAI ModelsExploreResourcesPricing
Sign inUse for Free
  • Home
  • Pricing
  • AI Models
  • Skills
  • Image models
  • Voice models
  • Video models
  • Rankings
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • Blog
  • About
  • Comparisons
  • Benchmarks
  • Model Match
  • Demos
  • Help center
  • FAQ
  • Privacy
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Migrate
  • Downloads
  • Desktop
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)Discord

GPT 6 Luna Pro vs Devstral (2512)

At a glance

OpenAI's GPT-6 Luna served in pro reasoning mode for the hardest problems.

1.1M ctx$0.10/$0.50 per M

Specialized coding and agentic reasoning model from Mistral and All Hands AI.

262K ctx$0.40/$2.00 per M
Demos
All demos

No shared demos for these models yet.

AI Output
All AI outputs

No captured outputs for these models yet.

Benchmarks
See rankings
Reasoning
CodingInsufficient data
AgenticInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:OpenRouter
Cheaper75%
CodingInsufficient data
AgenticInsufficient data
ReasoningInsufficient data
MathInsufficient data
Sources:OpenRouter
Specs
1.1M
Context
128K
Max output
Sep 2026
Released
262K
Context
210K
Max output
Dec 2025
Released
Capabilities
Vision
Audio
Reasoning
Vision
Audio
Reasoning
Pricing
Live pricing, shown before you run
Input75%$0.10/M tokens
Output75%$0.50/M tokens
Cache read75%$0.01/M tokens
Cache write$0.13/M tokens
Web search$0.01/search
Live pricing, shown before you run
Input$0.40/M tokens
Output$2.00/M tokens
Cache read$0.04/M tokens
Chat with GPT 6 Luna ProGo to model
Chat with Devstral (2512)Go to model
Frequently Asked Questions: GPT 6 Luna Pro vs Devstral (2512)▼

Which is better, GPT 6 Luna Pro or Devstral (2512)?

▼

Both GPT 6 Luna Pro and Devstral (2512) are capable AI models. The best choice depends on your specific use case: consider pricing, context window, speed, and which capabilities (vision, reasoning, audio) you need.

Which is cheaper, GPT 6 Luna Pro or Devstral (2512)?

▼

GPT 6 Luna Pro has a lower blended cost. GPT 6 Luna Pro: $0.10 input / $0.50 output. Devstral (2512): $0.40 input / $2.00 output.

Which has a larger context window, GPT 6 Luna Pro or Devstral (2512)?

▼

GPT 6 Luna Pro has a larger context window: GPT 6 Luna Pro supports 1.1M tokens vs Devstral (2512) at 262K tokens.

Do both GPT 6 Luna Pro and Devstral (2512) support vision?

▼

GPT 6 Luna Pro supports vision/image input, but Devstral (2512) does not.

What are the key differences between GPT 6 Luna Pro and Devstral (2512)?

▼

Key differences: GPT 6 Luna Pro is significantly cheaper; only GPT 6 Luna Pro supports vision input; only GPT 6 Luna Pro offers extended reasoning mode. Compare full specs on this page.

Which model should I choose for my use case?

▼

If cost is your priority, choose the cheaper option. If you need the highest intelligence for complex tasks, pick the higher-scoring model. For long documents or codebases, choose the larger context window. You can try both GPT 6 Luna Pro and Devstral (2512) for free on idapt.app to see which performs better for your specific needs.

Open in App