Ember-1 vs Hy4 flash
Ember-1 leads Hy4 flash on coding, 52.6 to 44.5 on the Vibe Coding Index, and Hy4 flash costs 106.8x less per output token ($0.1405 vs $15.00 per million). Updated November 22, 2026; 5 benchmarks have a result for both.
Ember-1 or Hy4 flash: which to pick
Pick Ember-1 for coding: it scores 52.6 on the Vibe Coding Index against 44.5 for Hy4 flash.
Pick Hy4 flash for output tokens 106.8x cheaper ($0.1405 vs $15.00 per million).
- Shared results
- 5
- Ember-1 only
- 12
- Hy4 flash only
- 7
- Like-for-like categories
- 2 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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
Ember-1
Ember-1 scores 52.6 against 44.5.
2 benchmarks behind each score
Web design
Design Arena: websites
No call
Only Hy4 flash has a Design Arena: websites result, 1227.
Directional only
General
Vals Index
No call
Only Hy4 flash has a Vals Index result, 50.8%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy4 flash
Ember-1 $0.011, Hy4 flash $0.0001 per turn.
List prices
At a glance
- Coding index
- Ember-1 52.6 from 2 benchmarks, Hy4 flash 44.5 from 2 benchmarks.
- Widest category
- Coding, 9.6 points apart on average over 3 shared benchmarks.
- Widest single gap
- GameBench 2: Ember-1 63.0 against Hy4 flash 50.5, 12.5 points apart on a 0 to 100 scale.
- Output price
- Ember-1 $15.00 against Hy4 flash $0.1405 per million output tokens, 106.8x apart.
- Context window
- Both take 1.05M tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Ember-1 | Bars | Hy4 flash | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Agentic work | 2 | 0 | ||
| All shared boards | 5 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Terminal-Bench 4 (Vals AI) | 20.7% | 15.2% | Ember-1 |
| Vibe Code Bench (Vals AI) | 83.9% | 74.8% | Ember-1 |
| Code migration (Vals AI) | 32.5% | Not measured | Only Ember-1 measured |
| IOI (Vals AI) | 46.3% | Not measured | Only Ember-1 measured |
| CyberBench (Vals AI) | 69.5% | Not measured | Only Ember-1 measured |
| GameBench 2 | 63.0 | 50.5 | Ember-1 |
| Terminal-Bench 4.0 | 21.8% | Not measured | Only Ember-1 measured |
| Neither model has a result on the other 45 boards here | |||
IntelligenceNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Neither model has a result on 2 boards here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | 51.8% | Not measured | Only Ember-1 measured |
| Tax Agent Bench (Vals AI) | 31.1% | 23.3% | Ember-1 |
| Legal Research Bench (Vals AI) | 44.7% | 38.5% | Ember-1 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 5.4% | Only Hy4 flash measured |
| Excel Modeling Benchmark (Vals AI) | 63.4% | Not measured | Only Ember-1 measured |
| BioMysteryBench (Vals AI) | 67.0% | Not measured | Only Ember-1 measured |
| Terminal-Bench-Science (Vals AI) | 5.7% | Not measured | Only Ember-1 measured |
| Vals Science Index | 31.8% | Not measured | Only Ember-1 measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | 22.5% | Not measured | Only Ember-1 measured |
| Neither model has a result on the other 25 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Neither model has a result on 14 boards here | |||
KnowledgeNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Neither model has a result on 21 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1227 | Only Hy4 flash measured |
| Design Arena: UI components | Not measured | 1262 | Only Hy4 flash measured |
| Design Arena: game dev | Not measured | 1202 | Only Hy4 flash measured |
| Design Arena: 3D | Not measured | 1209 | Only Hy4 flash measured |
| Design Arena: all code categories | Not measured | 1225 | Only Hy4 flash measured |
| Neither model has a result on the other 4 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Vals Index | Not measured | 50.8% | Only Hy4 flash measured |
| Public Benefits Bench (Vals AI) | 66.2% | Not measured | Only Ember-1 measured |
| SAGE (Vals AI) | 86.4% | Not measured | Only Ember-1 measured |
| Neither model has a result on the other 46 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ember-1 | Hy4 flash | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
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
Hy4 flash costs less
Repository review
50K input + 3K output tokens
Hy4 flash costs less
Agent loop
200K input + 10K output tokens
Hy4 flash 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 | Fireworks Ember-1 | Tencent Hy4 flash |
|---|---|---|
| Maker | Fireworks | Tencent |
| Weights | No public weights listed | Open weights |
| Released | September 24, 2026 | November 16, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $3.00 | $0.035 |
| Output $/Mtok | $15.00 | $0.1405 |
| Coding index | 52.6 | 44.5 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Ember-1 better than Hy4 flash for coding?
Pick Ember-1 for coding: it scores 52.6 on the Vibe Coding Index against 44.5 for Hy4 flash. Pick Hy4 flash for output tokens 106.8x cheaper ($0.1405 vs $15.00 per million).
Which is cheaper, Ember-1 or Hy4 flash?
Ember-1 costs $3.00 per million input tokens and $15.00 per million output tokens; Hy4 flash costs $0.035 and $0.1405. Cost per solved task is known for neither of them.
Which has the bigger context window, Ember-1 or Hy4 flash?
Neither: both take 1.05M tokens.
How many benchmarks is the Ember-1 vs Hy4 flash comparison based on?
5 benchmarks have a result for both models as of November 22, 2026. Ember-1's coding index rests on 2 independent benchmarks and Hy4 flash's on 2. Where only one model has a result, the page says so instead of naming a winner.