LFM2.5-24B-A2B vs Voxtral Small 24B 2507
Voxtral Small 24B 2507 costs 2.3x less per output token than LFM2.5-24B-A2B ($0.30 vs $0.70 per million). Updated October 22, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.70
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.30
LFM2.5-24B-A2B or Voxtral Small 24B 2507: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick LFM2.5-24B-A2B for a larger context window (128K against 33K 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
LFM2.5-24B-A2B
LFM2.5-24B-A2B takes 128K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Voxtral Small 24B 2507
LFM2.5-24B-A2B $0.0004, Voxtral Small 24B 2507 $0.0003 per turn.
List prices
At a glance
- Coding index
- LFM2.5-24B-A2B not benchmarked, Voxtral Small 24B 2507 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
- LFM2.5-24B-A2B $0.70 against Voxtral Small 24B 2507 $0.30 per million output tokens, 2.3x apart.
- Context window
- LFM2.5-24B-A2B takes 128K tokens, Voxtral Small 24B 2507 33K.
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
Voxtral Small 24B 2507 costs less
Repository review
50K input + 3K output tokens
LFM2.5-24B-A2B costs less
Agent loop
200K input + 10K output tokens
LFM2.5-24B-A2B 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 | LiquidAI LFM2.5-24B-A2B | Mistral Voxtral Small 24B 2507 |
|---|---|---|
| Maker | Liquid | Mistral AI |
| Weights | Open weights | Open weights |
| Released | October 13, 2026 | October 30, 2025 |
| Context window | 128K | 33K |
| Input $/Mtok | $0.05 | $0.10 |
| Output $/Mtok | $0.70 | $0.30 |
| 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 LFM2.5-24B-A2B better than Voxtral Small 24B 2507 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick LFM2.5-24B-A2B for a larger context window (128K against 33K tokens).
Which is cheaper, LFM2.5-24B-A2B or Voxtral Small 24B 2507?
LFM2.5-24B-A2B costs $0.05 per million input tokens and $0.70 per million output tokens; Voxtral Small 24B 2507 costs $0.10 and $0.30. Cost per solved task is known for neither of them.
Which has the bigger context window, LFM2.5-24B-A2B or Voxtral Small 24B 2507?
LFM2.5-24B-A2B, with 128K tokens against 33K.
Has any benchmark tested both LFM2.5-24B-A2B and Voxtral Small 24B 2507?
No benchmark has tested either model yet, so price and context are the only way to compare them. Data as of October 22, 2026.