Schematron V2 Small vs Hy-MT2-1.8B vs Reka Edge
Reka Edge comes out ahead, 64 to 52 and 49 on our weighted score, though Hy-MT2-1.8B is 25% cheaper per token.
Inference.net
Schematron V2 Small
52/100- ECI—
- Price$0.05 / $0.23
- Context128K
TencentHy-MT2-1.8B
49/100- ECI—
- Price$0.044 / $0.177
- Context8K
- Our pick
Reka AIReka Edge
64/100- ECI—
- Price$0.102 / $0.102
- Context16K
Reka Edge is our pick
Reka Edge is the better all-round choice, scoring 64/100 against Schematron V2 Small (52) and Hy-MT2-1.8B (49). It leads on inputs & features. Schematron V2 Small wins on context window. Hy-MT2-1.8B wins on price. 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 priceHy-MT2-1.8BHy-MT2-1.8B $0.077 · Schematron V2 Small $0.095 · Reka Edge $0.102 per 1M tokens (3:1 blend)
- Longest contextSchematron V2 SmallSchematron V2 Small 128,000 · Reka Edge 16,384 · Hy-MT2-1.8B 8,192 tokens
- Widest inputsReka EdgeSchematron V2 Small: Text · Hy-MT2-1.8B: Text · Reka Edge: Text, Images, Video
- Self-hostingHy-MT2-1.8B and Reka EdgePublishes downloadable weights
| Measure | Weight | Schematron V2 Small | Hy-MT2-1.8B | Reka Edge |
|---|---|---|---|---|
| Price | 50% | 94 | 98 | 93 |
| Inputs & features | 30% | 0 | 0 | 60 |
| Context window | 20% | 24 | 0 | 0 |
| Overall | 100% | 52/100 | 49/100 | 64/100 |
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 | Schematron V2 SmallInference.net | Hy-MT2-1.8BTencent | Reka EdgeReka AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.05 | $0.044 (best) | $0.102 |
| Output | $0.23 | $0.177 | $0.102 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.095 | $0.077 (best) | $0.102 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 5 providers | Median of 3 providers | Median of 4 providers |
| Limits | |||
| Context window | 128,000 tokens (best) | 8,192 tokens | 16,384 tokens |
| Max output | 4,096 tokens | 4,096 tokens | 14,745 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | No |
| Tool calling | No | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | — | — | — |
| API providers | 5 (best) | 3 | 4 |
| Released | Apr 16, 2026 | May 21, 2026 | Mar 11, 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.
- Schematron V2 Small$0.96
- Hy-MT2-1.8B$0.794
- Reka Edge$1.23
Which should you choose?
Which is better: Schematron V2 Small, Hy-MT2-1.8B or Reka Edge?
Reka Edge is the better all-round choice, scoring 64/100 against Schematron V2 Small (52) and Hy-MT2-1.8B (49). It leads on inputs & features. Schematron V2 Small wins on context window. Hy-MT2-1.8B wins on price. 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, Schematron V2 Small, Hy-MT2-1.8B or Reka Edge?
Hy-MT2-1.8B is cheaper at $0.044 input / $0.177 output per million tokens (median across 3 API providers). Schematron V2 Small costs $0.05 input / $0.23 output per million tokens (median across 5 API providers); Reka Edge costs $0.102 input / $0.102 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $0.077 per million tokens for Hy-MT2-1.8B versus $0.095 for Schematron V2 Small (1.2× as much) and $0.102 for Reka Edge (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Schematron V2 Small has not been scored yet, Hy-MT2-1.8B has not been scored yet and Reka Edge has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Schematron V2 Small, Hy-MT2-1.8B and Reka Edge yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Schematron V2 Small and Hy-MT2-1.8B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Schematron V2 Small has the largest context window at 128,000 tokens, against 16,384 for Reka Edge and 8,192 for Hy-MT2-1.8B. Maximum output per response: Schematron V2 Small up to 4,096, Hy-MT2-1.8B up to 4,096, Reka Edge up to 14,745 tokens.
Which can read images, PDFs, audio or video?
Schematron V2 Small accepts text; Hy-MT2-1.8B accepts text; Reka Edge accepts text, images and video. Reka Edge handles the widest range of inputs.
Are any of these open source?
Hy-MT2-1.8B and Reka Edge publishes its weights and can be self-hosted; Schematron V2 Small is proprietary.
Which is newer?
Hy-MT2-1.8B is the newest, released May 21, 2026. Schematron V2 Small came out Apr 16, 2026; Reka Edge came out Mar 11, 2026.
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.
