Claude Sonnet 4.5 vs GPT-5
API pricing, context window and capabilities for Claude Sonnet 4.5 and GPT-5, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersClaude Sonnet 4.5 wins on context window. GPT-5 wins on price. Benchmark data is unavailable for one or both models.
Price
GPT-5
Terminal-Bench
Not called
Intelligence
Not called
Context window
Claude Sonnet 4.5
Key takeaways
who wins on what, from the published numbersClaude Sonnet 4.5 wins
- Larger context window (1M vs 410K)
GPT-5 wins
- Cheaper input ($3.00 vs $1.25 /1M)
- Cheaper output ($15.00 vs $10.00 /1M)
- Higher max output (64K vs 128K)
- More serving providers (8 vs 9)
- Has web search
Cheaper overall
GPT-5
$1.25 + $10.00 /1M
Larger context
Claude Sonnet 4.5
1M
More providers
GPT-5
9 providers
Pricing & specs
cheapest listed route · per 1M tokensOn-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
| Claude Sonnet 4.5 | GPT-5 | |
|---|---|---|
| Input $/1M | $3.00via Databricks | $1.25via Databricks best |
| Output $/1M | $15.00via Anthropic | $10.00via Databricks best |
| Context window | 1M best | 410K |
| Max output | 64K | 128K best |
| Serving providers | 8 | 9 best |
| Date | Released Sep 29, 2025 | Released Aug 7, 2025 |
Benchmarks
Benchmark scores, side by side| Claude Sonnet 4.5 | GPT-5 | |
|---|---|---|
| Intelligence | Not available | 23.0 |
| Terminal-Bench | Not available | 35% |
| GPQA Diamond | Not available | 85% |
| Output speed | Not available | 102 t/s |
| Latency (TTFT) | Not available | 78.80s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Claude Sonnet 4.5
via Databricks
$30
GPT-5
via Databricks
$16
Capabilities
feature support, side by side| Feature | Claude Sonnet 4.5 | GPT-5 |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | ✓ |
Related comparisons
Frequently asked questions
Which is cheaper, Claude Sonnet 4.5 or GPT-5?
GPT-5 is cheaper for input ($3.00 vs $1.25 per 1M tokens) from Databricks. GPT-5 is cheaper for output ($15.00 vs $10.00 per 1M tokens) from Databricks.
What is the context window difference between Claude Sonnet 4.5 and GPT-5?
Claude Sonnet 4.5 has a 1M-token context window and GPT-5 has 410K tokens, so Claude Sonnet 4.5 can take a larger prompt.
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI