Granite-4.0-H-Micro vs Laguna XS 2.1 vs Sarvam 30B
Too close to call on our weighted score (Laguna XS 2.1 68, Granite-4.0-H-Micro 65, Sarvam 30B 65). The right pick depends on what you value most.
IBMGranite-4.0-H-Micro
65/100- ECI—
- Price$0.017 / $0.112
- Context131K
PoolsideLaguna XS 2.1
68/100- ECI—
- Price$0.06 / $0.12
- Context262K
Sarvam AI
Sarvam 30B
65/100- ECI—
- Price$0.02 / $0.10
- Context128K
Too close to call
It is close. Our weighted score puts them within 2 points (Laguna XS 2.1 68/100, Granite-4.0-H-Micro 65/100, Sarvam 30B 65/100), so choose by what matters most for your work: Sarvam 30B on price and Laguna XS 2.1 for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceSarvam 30BSarvam 30B $0.04 · Granite-4.0-H-Micro $0.041 · Laguna XS 2.1 $0.075 per 1M tokens (3:1 blend)
- Longest contextLaguna XS 2.1Laguna XS 2.1 262,144 · Granite-4.0-H-Micro 131,072 · Sarvam 30B 128,000 tokens
- Widest inputsSame inputsGranite-4.0-H-Micro: Text · Laguna XS 2.1: Text · Sarvam 30B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Granite-4.0-H-Micro | Laguna XS 2.1 | Sarvam 30B |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 35 | 35 | 35 |
| Context window | 20% | 24 | 37 | 24 |
| Overall | 100% | 65/100 | 68/100 | 65/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Granite-4.0-H-MicroIBM | Laguna XS 2.1Poolside | Sarvam 30BSarvam AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.017 (best) | $0.06 | $0.02 |
| Output | $0.112 | $0.12 | $0.10 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.041 | $0.075 | $0.04 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Median of 1 providers | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 128,000 tokens |
| Max output | 131,072 tokens (best) | 32,768 tokens | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | Yes · low · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | poolside/laguna-xs-2.1 | sarvam-30b |
| API providers | 1 | 4 (best) | 2 |
| Released | Oct 2, 2025 | Jul 2, 2026 | Feb 18, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Granite-4.0-H-Micro$0.394
- Laguna XS 2.1$0.84
- Sarvam 30B$0.40
Which should you choose?
Which is better: Granite-4.0-H-Micro, Laguna XS 2.1 or Sarvam 30B?
It is close. Our weighted score puts them within 2 points (Laguna XS 2.1 68/100, Granite-4.0-H-Micro 65/100, Sarvam 30B 65/100), so choose by what matters most for your work: Sarvam 30B on price and Laguna XS 2.1 for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Granite-4.0-H-Micro, Laguna XS 2.1 or Sarvam 30B?
Sarvam 30B is cheaper at $0.02 input / $0.10 output per million tokens (median across 1 API provider). Granite-4.0-H-Micro costs $0.017 input / $0.112 output per million tokens (median across 1 API provider); Laguna XS 2.1 costs $0.06 input / $0.12 output per million tokens (median across 1 API provider; free on Poolside). At a typical mix of three input tokens to one output token, that is $0.04 per million tokens for Sarvam 30B versus $0.041 for Granite-4.0-H-Micro (1× as much) and $0.075 for Laguna XS 2.1 (1.9× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Granite-4.0-H-Micro has not been scored yet, Laguna XS 2.1 has not been scored yet and Sarvam 30B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Granite-4.0-H-Micro, Laguna XS 2.1 and Sarvam 30B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Laguna XS 2.1 has the largest context window at 262,144 tokens, against 131,072 for Granite-4.0-H-Micro and 128,000 for Sarvam 30B. Maximum output per response: Granite-4.0-H-Micro up to 131,072, Laguna XS 2.1 up to 32,768, Sarvam 30B up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Micro accepts text; Laguna XS 2.1 accepts text; Sarvam 30B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Laguna XS 2.1 is the newest, released Jul 2, 2026. Sarvam 30B came out Feb 18, 2026; Granite-4.0-H-Micro came out Oct 2, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
