Claude Sonnet 4.5
ClaudeBalanced
ThinkingTool UseVisionStructured Output
About this model
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
Performance Tier
Balanced
Claude Sonnet 4.5 is a balanced model from Claude : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $3.00 |
| Output (completion) | $15.00 |
| Cache read | $0.300 |
| Cache write | $3.75 |
Capabilities
Context Length1.0M
Max Output Tokens64K
TokenizerClaude
Inputtext, image, file
Outputtext
Release DateSeptember 29, 2025
Benchmarks
General Intelligence
MMLU
88.7%
GPQA Diamond
68.6%
Mathematics
MATH-500
80.6%
AIME 2025
87%
Programming
HumanEval
93%
SWE-bench Verified
70.3%
Recommended Use Cases
CodingAnalysisCreative WritingGeneral Chat
Strengths
- Best balance of speed and intelligence in the Claude family
- Extended thinking mode for complex reasoning tasks
- Strong code generation with SWE-bench 70.3%
- Excellent creative writing and nuanced communication
Limitations
- Extended thinking adds latency for complex queries
- Less capable than Opus on graduate-level science reasoning
Resources
This model may use your data for training