Magnum v4 72B vs Ember-1
Magnum v4 72B costs 3.0x less per output token than Ember-1 ($5.00 vs $15.00 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $5.00
- Coding
- 52.6
- Overall
- No data
- Output $/M
- $15.00
Magnum v4 72B or Ember-1: which to pick
Only Ember-1 has a coding score, 52.6 on the Vibe Coding Index; Magnum v4 72B has none, so the two cannot be ranked on coding.
Pick Magnum v4 72B for output tokens 3.0x cheaper ($5.00 vs $15.00 per million).
No benchmark has tested both yet. Magnum v4 72B has none yet; Ember-1 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI). Compare them on price and context instead.
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
Only Ember-1 has a coding score, so no call is made.
One side not measured
Long documents
Listed context window
Ember-1
Ember-1 takes 1.05M tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Magnum v4 72B
Magnum v4 72B $0.0050, Ember-1 $0.011 per turn.
List prices
At a glance
- Coding index
- Magnum v4 72B not benchmarked, Ember-1 52.6 from 2 benchmarks.
- 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
- Magnum v4 72B $5.00 against Ember-1 $15.00 per million output tokens, 3.0x apart.
- Context window
- Magnum v4 72B takes 33K tokens, Ember-1 1.05M.
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.
CodingDirectional onlySix of these boards feed the Vibe Coding Index5 boards measured
| Benchmark | Magnum v4 72B | Ember-1 | Leader |
|---|---|---|---|
| Terminal-Bench 4 (Vals AI) | Not measured | 20.7% | Only Ember-1 measured |
| Vibe Code Bench (Vals AI) | Not measured | 83.9% | Only Ember-1 measured |
| Code migration (Vals AI) | Not measured | 32.5% | Only Ember-1 measured |
| IOI (Vals AI) | Not measured | 46.3% | Only Ember-1 measured |
| CyberBench (Vals AI) | Not measured | 69.5% | Only Ember-1 measured |
| Neither model has a result on the other 38 boards here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index7 boards measured
| Benchmark | Magnum v4 72B | Ember-1 | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | Not measured | 51.8% | Only Ember-1 measured |
| Tax Agent Bench (Vals AI) | Not measured | 31.1% | Only Ember-1 measured |
| Legal Research Bench (Vals AI) | Not measured | 44.7% | Only Ember-1 measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 63.4% | Only Ember-1 measured |
| BioMysteryBench (Vals AI) | Not measured | 67.0% | Only Ember-1 measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 5.7% | Only Ember-1 measured |
| Vals Science Index | Not measured | 31.8% | Only Ember-1 measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Magnum v4 72B | Ember-1 | Leader |
|---|---|---|---|
| MysteryMechanism (Vals AI) | Not measured | 22.5% | Only Ember-1 measured |
| Neither model has a result on the other 22 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
| Benchmark | Magnum v4 72B | Ember-1 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 66.2% | Only Ember-1 measured |
| Neither model has a result on the other 47 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
Magnum v4 72B costs less
Repository review
50K input + 3K output tokens
Magnum v4 72B costs less
Agent loop
200K input + 10K output tokens
Magnum v4 72B 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 | Magnum v4 72B | Fireworks Ember-1 |
|---|---|---|
| Maker | Anthracite | Fireworks |
| Weights | Open weights | No public weights listed |
| Released | October 22, 2024 | September 24, 2026 |
| Context window | 33K | 1.05M |
| Input $/Mtok | $2.50 | $3.00 |
| Output $/Mtok | $5.00 | $15.00 |
| Coding index | Not benchmarked | 52.6 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Magnum v4 72B better than Ember-1 for coding?
Only Ember-1 has a coding score, 52.6 on the Vibe Coding Index; Magnum v4 72B has none, so the two cannot be ranked on coding. Pick Magnum v4 72B for output tokens 3.0x cheaper ($5.00 vs $15.00 per million).
Which is cheaper, Magnum v4 72B or Ember-1?
Magnum v4 72B costs $2.50 per million input tokens and $5.00 per million output tokens; Ember-1 costs $3.00 and $15.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Magnum v4 72B or Ember-1?
Ember-1, with 1.05M tokens against 33K.
Has any benchmark tested both Magnum v4 72B and Ember-1?
No benchmark has tested both yet. Magnum v4 72B has none yet; Ember-1 on Terminal-Bench 4 (Vals AI), Vibe Code Bench (Vals AI) and Code migration (Vals AI). Compare them on price and context instead. Data as of October 22, 2026.