Claude Sonnet 5 vs Gemini 3.1 Pro Preview
API pricing, context window and capabilities for Claude Sonnet 5 and Gemini 3.1 Pro Preview, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.
Verdict
computed from the published numbersClaude Sonnet 5 wins on price, on coding and on intelligence.
Price
Claude Sonnet 5
Coding
Claude Sonnet 5
Intelligence
Claude Sonnet 5
Context window
Tied
Key takeaways
who wins on what, from the published numbersClaude Sonnet 5 wins
- Cheaper output ($10.00 vs $12.00 /1M)
- Higher max output (128K vs 66K)
Gemini 3.1 Pro Preview wins
- Supports audio
- Has web search
Cheaper overall
Claude Sonnet 5
$2.00 + $10.00 /1M
Larger context
Tied
More providers
Tied
Pricing & specs
cheapest serving route · per 1M tokens| Claude Sonnet 5 | Gemini 3.1 Pro Preview | |
|---|---|---|
| Input $/1M | $2.00 | $2.00 |
| Output $/1M | $10.00 best | $12.00 |
| Context window | 1M | 1M |
| Max output | 128K best | 66K |
| Serving providers | 4 | 4 |
| Released | 2026-06-30 | 2026-02-19 |
Benchmarks
Artificial Analysis indices, side by side| Claude Sonnet 5 | Gemini 3.1 Pro Preview | |
|---|---|---|
| Intelligence | 53.4 best | 46.5 |
| Coding | 71.5 best | 68.8 |
| GPQA Diamond | 91% | 94% best |
| Output speed | 67 t/s | 154 t/s best |
| Latency (TTFT) | 42.19s | 34.98s best |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Claude Sonnet 5
via Amazon Bedrock
$20
Gemini 3.1 Pro Preview
via Vertex AI
$22
Capabilities
feature support, side by side| Feature | Claude Sonnet 5 | Gemini 3.1 Pro Preview |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | ✓ |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | ✓ |
Related comparisons
Frequently asked questions
Which is cheaper, Claude Sonnet 5 or Gemini 3.1 Pro Preview?
Claude Sonnet 5 is cheaper for output ($10.00 vs $12.00 per 1M tokens).
What is the context window difference between Claude Sonnet 5 and Gemini 3.1 Pro Preview?
Both Claude Sonnet 5 and Gemini 3.1 Pro Preview have about a 1M-token context window.
How do Claude Sonnet 5 and Gemini 3.1 Pro Preview compare on benchmarks?
On the tracked Artificial Analysis indices, Claude Sonnet 5 leads on coding, and Claude Sonnet 5 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI