Llama 3.2 90B Vision vs Yi Large
Compare Llama 3.2 90B Vision and Yi Large: pricing, performance, context window, latency, and best use cases. Side-by-side comparison on XALEN.
Updated 2026-05-21 · By Abhishek Raj · Our methodology
| Feature | Llama 3.2 90B Vision | Yi Large |
|---|---|---|
| Category | Vision | Open Source |
| Parameters | 90B | 300B |
| Context Window | 128K | 200K |
| Input Price | $0.06/1M tokens | $0.06/1M tokens |
| Output Price | $0.10/1M tokens | $0.12/1M tokens |
| Latency | ~500ms | ~450ms |
Choose Llama 3.2 90B Vision when:
- ✓ Chart image analysis
- ✓ Document scanning
- ✓ Visual Q&A
Vision + language, Open weights, Good reasoning
Choose Yi Large when:
- ✓ Long document analysis
- ✓ Research
- ✓ Complex tasks
200K context, Strong analysis, Good reasoning
Verdict: Llama 3.2 90B Vision vs Yi Large
For cost efficiency, Yi Large wins at $0.06/1M input tokens. For speed, Yi Large is faster at ~450ms. Llama 3.2 90B Vision excels at Chart image analysis while Yi Large is better for Long document analysis. Both are available on XALEN through a single API — try them in the Playground to see which fits your workload.
Detailed Analysis
Pricing Comparison
Llama 3.2 90B Vision costs $0.06/1M input tokens and $0.10/1M output tokens. Yi Large costs $0.06 input and $0.12 output. Both models are similarly priced. XALEN offers batch processing at 50% discount on both models.
Performance & Context
Llama 3.2 90B Vision has a 128K context window with ~500ms latency. Yi Large offers 200K context at ~450ms. Yi Large has the larger context window.
Best For
Llama 3.2 90B Vision (Vision) is optimized for: Chart image analysis, Document scanning, Visual Q&A. Yi Large (Open Source) works best for: Long document analysis, Research, Complex tasks.
Try Both on XALEN
Both models are available through XALEN's OpenAI-compatible API. Switch between them by changing the model parameter:
from xalen import XALEN
client = XALEN(api_key="xln_test_YOUR_KEY")
# Use Llama 3.2 90B Vision
response_a = client.chat.completions.create(
model="llama-3-2-90b-vision",
messages=[{"role": "user", "content": "Your question here"}]
)
# Use Yi Large
response_b = client.chat.completions.create(
model="yi-large",
messages=[{"role": "user", "content": "Your question here"}]
)
Frequently Asked Questions
Which is better, Llama 3.2 90B Vision or Yi Large?
Llama 3.2 90B Vision (Vision, 90B) offers Vision + language. Yi Large (Open Source, 300B) offers 200K context. Choose Llama 3.2 90B Vision for Chart image analysis or Yi Large for Long document analysis.
How much does Llama 3.2 90B Vision cost vs Yi Large?
Llama 3.2 90B Vision: $0.06/1M input, $0.10/1M output. Yi Large: $0.06/1M input, $0.12/1M output. Both available on XALEN with batch processing at 50% discount.
Can I use both models on XALEN?
Yes. XALEN provides 200+ models through a single OpenAI-compatible API. Switch between Llama 3.2 90B Vision and Yi Large by changing the model parameter. No code changes needed.
Related Comparisons
Last updated: 2026-05-21. Pricing and specifications may change. Check pricing page for latest rates.