Hy3 preview vs Inkling
API pricing, context window and capabilities for Hy3 preview and Inkling, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersHy3 preview wins on price. Inkling wins on intelligence and on context window. Benchmark data is unavailable for one or both models.
Price
Hy3 preview
Terminal-Bench
Not called
Intelligence
Inkling
Context window
Inkling
Key takeaways
who wins on what, from the published numbersHy3 preview wins
- Cheaper input ($0.18 vs $0.95 /1M)
- Cheaper output ($0.60 vs $4.05 /1M)
- Higher max output (236K vs 33K)
Inkling wins
- Larger context window (262K vs 1M)
- More serving providers (1 vs 6)
- Supports vision
- Supports structured output
Cheaper overall
Hy3 preview
$0.18 + $0.60 /1M
Larger context
Inkling
1M
More providers
Inkling
6 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.
| Hy3 preview | Inkling | |
|---|---|---|
| Input $/1M | $0.18OpenRouter routed quote best | $0.95via DeepInfra |
| Output $/1M | $0.60OpenRouter routed quote best | $4.05via Baseten |
| Context window | 262K | 1M best |
| Max output | 236K best | 33K |
| Serving providers | 1 | 6 best |
| Date | Released Apr 20, 2026 | Released Jul 16, 2026 |
Benchmarks
Benchmark scores, side by side| Hy3 preview | Inkling | |
|---|---|---|
| Intelligence | 22.7 | 25.0 best |
| Terminal-Bench | Not available | 55% |
| GPQA Diamond | 87% | 87% |
| Output speed | Not available | 186 t/s |
| Latency (TTFT) | Not available | 1.91s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
Hy3 preview
via OpenRouter
$1.50
Inkling
via DeepInfra
$8.80
Capabilities
feature support, side by side| Feature | Hy3 preview | Inkling |
|---|---|---|
| Vision | — | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | — | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, Hy3 preview or Inkling?
Hy3 preview is cheaper for input ($0.18 vs $0.95 per 1M tokens) as an OpenRouter routed quote. Hy3 preview is cheaper for output ($0.60 vs $4.05 per 1M tokens) as an OpenRouter routed quote.
What is the context window difference between Hy3 preview and Inkling?
Hy3 preview has a 262K-token context window and Inkling has 1M tokens, so Inkling can take a larger prompt.
How do Hy3 preview and Inkling compare on benchmarks?
On the tracked benchmarks, Inkling 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