Model Comparison
105B (high)
vs. 30B (high)
Comparing 2 AI models · 0 benchmarks · Sarvam
Recommended Pick
Sa105B (high)3 metric winsStrongest on: Value, Reasoning, Intelligence
Best Value
105B (high)
100.0 value score
11.9 reasoning / $0.07/1M
Lowest Price
30B (high)
$0.03/1M input price
Best Reasoning
105B (high)
11.9 reasoning score
Blends available reasoning benchmarks
Differences That Matter
Best value
105B (high) has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
30B (high) is 1.3x cheaper on input tokens than 105B (high).
Reasoning gap
105B (high) leads 30B (high) by 5.5 points on reasoning.
Top-pick rationale
105B (high) wins 3 measurable categories, including Value, Reasoning, Intelligence.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
105B (high)
Sarvam
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
30B (high)
Sarvam
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Secure AI Chat made in Europe
Processing terms vary by selected model. Review the current Privacy Policy and DPA before using sensitive data.
OpenAI-compatible inference
Choose from the current model catalog. Processing terms vary by selected model and service.
Full Comparison
| Metric | Top Pick Sa 105B (high) | Sa 30B (high) |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $0.04/1M | $0.03/1M |
| Output Cost | $0.17/1M | $0.11/1M |
| Blended (3:1) | $0.07/1M | $0.05/1M |
| Specifications | ||
| Organization | Sarvam | Sarvam |
| Release Date | Mar 6, 2026 | Mar 6, 2026 |
| Performance & Speed | ||
| Throughput | — | — |
| TTFT | — | — |
| Latency | — | — |
| Composite Indices | ||
| Value Score | 100.0 | 78.0 |
| Reasoning Score | 11.9 | 6.4 |
| Intelligence | 11.9 | 6.4 |
Key Takeaways
30B (high) offers the best value at $0.03/1M,making it ideal for high-volume applications and cost-conscious projects.
105B (high) has the strongest reasoning profile with a 11.9 reasoning score,combining the available reasoning-heavy benchmarks.
All models support context windows of ∞+ tokens,suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
105B (high)
- Complex reasoning tasks
- Research & analysis
30B (high)
- Cost-sensitive applications
- High-volume processing
