LLMversus

Codestral 22B vs Gemini 2.5 Pro: Pricing, Benchmarks & Verdict (2026)

Pricing verified Aug 3, 2026By LLMversusUpdated August 8, 2026View methodology

⚡ Quick Answer

Compare Codestral 22B and Gemini 2.5 Pro across pricing, benchmarks, and capabilities.

Updated: August 3, 2026 · ✓ Pricing verified

Side-by-Side Comparison

FeatureCodestral 22BGemini 2.5 Pro
ProviderMistral AIGoogle
Input Price / 1M tokens$0.300$1.25
Output Price / 1M tokens$0.900$10.00
Context Window
256K
1.048576M
Max Output Tokens
4,096
65,536
Arena ELON/A1,446
Coding ELO
1,250
1,446
TTFT (ms)
150
400
Tokens/sec
100
70
MultimodalNoYes
JSON ModeYesYes
Function CallingYesYes
VisionNoYes
When to Use Codestral 22B

Codestral 22B excels at coding, long-context tasks.

Strengths:

  • Best-in-class code generation
  • Huge context for repos
  • Function calling strength

Best for:

codinglong-context
When to Use Gemini 2.5 Pro

Gemini 2.5 Pro excels at coding, reasoning, long-context, multimodal tasks.

Strengths:

  • 1M token context window
  • Excellent reasoning capabilities
  • Strong coding performance
  • Native multimodal support

Best for:

codingreasoninglong-contextmultimodal

Related Comparisons

Claude Opus 4 vs Gemini 2.5 ProClaude Opus 4 vs Codestral 22BClaude Sonnet 4 vs Gemini 2.5 ProClaude Sonnet 4 vs Codestral 22BClaude Haiku 4 vs Gemini 2.5 ProDeepseek R1 vs Gemini 2.5 ProGemini 2.5 Pro vs Qwen 2 5 MaxGemini 2 0 Flash vs Gemini 2.5 ProDeepseek V3 vs Gemini 2.5 ProGemini 2.5 Pro vs O3 MiniGemini 2.5 Pro vs Gpt 4oGemini 2.5 Pro vs O3Gemini 2.5 Pro vs O1Gemini 2.5 Pro vs Qwen 3 235bGemini 2.5 Pro vs Gemini Exp 1206Gemini 2.5 Pro vs Gpt 4 5Gemini 2.5 Pro vs Groq Deepseek R1Gemini 2.5 Pro vs Llama 4 MaverickGemini 2.5 Pro vs Together Deepseek R1Gemini 2.5 Pro vs Grok 3