Granite-4.0-H-Micro vs Laguna XS 2.1 vs PaddleOCR VL
Laguna XS 2.1 comes out ahead, 68 to 62 and 62 on our weighted score, and it is the cheaper option too.
IBMGranite-4.0-H-Micro
62/100- ECI—
- Price$0.018 / $0.115
- Context131K
- Our pick
PoolsideLaguna XS 2.1
68/100- ECI—
- PriceFree / Free
- Context262K
PaddlePaddle
PaddleOCR VL
62/100- ECI—
- Price$0.02 / $0.02
- Context131K
Laguna XS 2.1 is our pick
Laguna XS 2.1 is the better all-round choice, scoring 68/100 against Granite-4.0-H-Micro (62) and PaddleOCR VL (62). It leads on inputs & features and context window. 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 priceLaguna XS 2.1Laguna XS 2.1 Free · PaddleOCR VL $0.02 · Granite-4.0-H-Micro $0.042 per 1M tokens (3:1 blend)
- Longest contextLaguna XS 2.1Laguna XS 2.1 262,144 · Granite-4.0-H-Micro 131,072 · PaddleOCR VL 131,072 tokens
- Widest inputsPaddleOCR VLGranite-4.0-H-Micro: Text · Laguna XS 2.1: Text · PaddleOCR VL: Text, Images
- 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 | PaddleOCR VL |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 25 | 35 | 25 |
| Context window | 20% | 25 | 37 | 25 |
| Overall | 100% | 62/100 | 68/100 | 62/100 |
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 | PaddleOCR VLPaddlePaddle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.018 | Free (best) | $0.02 |
| Output | $0.115 | Free (best) | $0.02 |
| Cached input | — | — | — |
| Blended (3:1) | $0.042 | Free (best) | $0.02 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Official Poolside API | Median of 1 providers |
| Limits | |||
| Context window | 131,072 tokens | 262,144 tokens (best) | 131,072 tokens |
| Max output | 131,072 tokens (best) | 32,768 tokens | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | OpenApache-2.0 |
| API model ID | — | poolside/laguna-xs-2.1 | — |
| API providers | 2 | 3 (best) | 1 |
| Released | Oct 2, 2025 | Jul 2, 2026 | Oct 16, 2025 |
| 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$0.405
- Laguna XS 2.1Free
- PaddleOCR VL$0.24
Which should you choose?
Which is better: Granite-4.0-H-Micro, Laguna XS 2.1 or PaddleOCR VL?
Laguna XS 2.1 is the better all-round choice, scoring 68/100 against Granite-4.0-H-Micro (62) and PaddleOCR VL (62). It leads on inputs & features and context window. 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 PaddleOCR VL?
Laguna XS 2.1 is cheaper at Free input / Free output per million tokens (official Poolside API price). PaddleOCR VL costs $0.02 input / $0.02 output per million tokens (median across 1 API provider); Granite-4.0-H-Micro costs $0.018 input / $0.115 output per million tokens (median across 2 API providers). Laguna XS 2.1 is listed as free.
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 PaddleOCR VL 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 PaddleOCR VL yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that PaddleOCR VL does not support tool calling, which most coding agents need.
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 131,072 for PaddleOCR VL. Maximum output per response: Granite-4.0-H-Micro up to 131,072, Laguna XS 2.1 up to 32,768, PaddleOCR VL up to 16,384 tokens.
Which can read images, PDFs, audio or video?
Granite-4.0-H-Micro accepts text; Laguna XS 2.1 accepts text; PaddleOCR VL accepts text and images. PaddleOCR VL handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Laguna XS 2.1 is the newest, released Jul 2, 2026. PaddleOCR VL came out Oct 16, 2025; 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 Nov 2, 2026.
