Gemini 3.8 Flash vs Hy3 preview
API pricing, context window and capabilities for Gemini 3.8 Flash and Hy3 preview, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersGemini 3.8 Flash wins on intelligence and on context window. Hy3 preview wins on price. Benchmark data is unavailable for one or both models.
Price
Hy3 preview
Terminal-Bench
Not called
Intelligence
Gemini 3.8 Flash
Context window
Gemini 3.8 Flash
Key takeaways
who wins on what, from the published numbersGemini 3.8 Flash wins
- Larger context window (1M vs 262K)
- More serving providers (5 vs 1)
- Supports vision
- Supports audio
- Supports structured output
- Has web search
Hy3 preview wins
- Cheaper input ($0.75 vs $0.18 /1M)
- Cheaper output ($3.75 vs $0.60 /1M)
- Higher max output (66K vs 236K)
Cheaper overall
Hy3 preview
$0.18 + $0.60 /1M
Larger context
Gemini 3.8 Flash
1M
More providers
Gemini 3.8 Flash
5 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. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
| Gemini 3.8 Flash | Hy3 preview | |
|---|---|---|
| Input $/1M | $0.75via Google | $0.18OpenRouter routed quote best |
| Output $/1M | $3.75via Google | $0.60OpenRouter routed quote best |
| Context window | 1M best | 262K |
| Max output | 66K | 236K best |
| Serving providers | 5 best | 1 |
| Date | Released Sep 2, 2026 | Released Apr 20, 2026 |
Benchmarks
Benchmark scores, side by side| Gemini 3.8 Flash | Hy3 preview | |
|---|---|---|
| Intelligence | 40.9 best | 22.7 |
| Terminal-Bench | 88% | Not available |
| GPQA Diamond | 95% best | 87% |
| Output speed | 145 t/s | Not available |
| Latency (TTFT) | 24.48s | Not available |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Gemini 3.8 Flash
via Vertex AI
$7.50
Hy3 preview
via OpenRouter
$1.50
Capabilities
feature support, side by side| Feature | Gemini 3.8 Flash | Hy3 preview |
|---|---|---|
| Vision | ✓ | — |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | ✓ | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | — |
| Web search | ✓ | — |
Related comparisons
Frequently asked questions
Which is cheaper, Gemini 3.8 Flash or Hy3 preview?
Hy3 preview is cheaper for input ($0.75 vs $0.18 per 1M tokens) as an OpenRouter routed quote. Hy3 preview is cheaper for output ($3.75 vs $0.60 per 1M tokens) as an OpenRouter routed quote.
What is the context window difference between Gemini 3.8 Flash and Hy3 preview?
Gemini 3.8 Flash has a 1M-token context window and Hy3 preview has 262K tokens, so Gemini 3.8 Flash can take a larger prompt.
How do Gemini 3.8 Flash and Hy3 preview compare on benchmarks?
On the tracked benchmarks, Gemini 3.8 Flash leads on intelligence.
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