Reka Edge vs Hy-MT2-1.8B
Reka Edge costs 1.8x less per output token than Hy-MT2-1.8B ($0.10 vs $0.177 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.10
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.177
Reka Edge or Hy-MT2-1.8B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Reka Edge for output tokens 1.8x cheaper ($0.10 vs $0.177 per million) and a larger context window (16K against 8K tokens).
No benchmark has tested either model yet, so price and context are the only way to compare them.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Long documents
Listed context window
Reka Edge
Reka Edge takes 16K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy-MT2-1.8B
Reka Edge $0.0001, Hy-MT2-1.8B $0.0001 per turn.
List prices
At a glance
- Coding index
- Reka Edge not benchmarked, Hy-MT2-1.8B not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Reka Edge $0.10 against Hy-MT2-1.8B $0.177 per million output tokens, 1.8x apart.
- Context window
- Reka Edge takes 16K tokens, Hy-MT2-1.8B 8K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Hy-MT2-1.8B costs less
Repository review
50K input + 3K output tokens
Hy-MT2-1.8B costs less
Agent loop
200K input + 10K output tokens
Hy-MT2-1.8B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Reka Edge | Tencent Hy-MT2-1.8B |
|---|---|---|
| Maker | Reka | Tencent |
| Weights | Open weights | Open weights |
| Released | March 20, 2026 | August 20, 2026 |
| Context window | 16K | 8K |
| Input $/Mtok | $0.10 | $0.044 |
| Output $/Mtok | $0.10 | $0.177 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Reka Edge better than Hy-MT2-1.8B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Reka Edge for output tokens 1.8x cheaper ($0.10 vs $0.177 per million) and a larger context window (16K against 8K tokens).
Which is cheaper, Reka Edge or Hy-MT2-1.8B?
Reka Edge costs $0.10 per million input tokens and $0.10 per million output tokens; Hy-MT2-1.8B costs $0.044 and $0.177. Cost per solved task is known for neither of them.
Which has the bigger context window, Reka Edge or Hy-MT2-1.8B?
Reka Edge, with 16K tokens against 8K.
Has any benchmark tested both Reka Edge and Hy-MT2-1.8B?
No benchmark has tested either model yet, so price and context are the only way to compare them. Data as of October 22, 2026.