Voxtral Small 24B 2507
Mistral AIReleased Jul 15, 2025Open weights · Apache 2.0voxtral-small-24b
- Reasoning
- no
- Context
- 131K tokens
- Max output
- 26k tokens
- Input
- text, audio
- API features
- tools, structured outputs, JSON mode, seed
- Mistral AI's API
- yes, as voxtral-small-2507
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Mistral AI
Its only host, Mistral AI, serves a 32K context (maker: 128K). Weights and context per host
Run it yourself
open weights, Apache 2.0 · fits 6 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 24B
- dense
- Memory needed
- 14 GB
- in INT4 · 29 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.17/h, about $124 a month
- Worth it above
- 310M tokens
- a month, against the cheapest API at $0.40 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 14 GB | RTX 3090 · $0.17/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 29 GB | A100 · $1.19/h | near-lossless |
| FP16 (full) | 58 GB | A100 · $1.19/h | reference quality |
At home: in INT4 it fits a RTX 5090 (32 GB) + host PC (plus a host PC), about $3,500 once, or $0.1332/h over 3 years, electricity aside; it pays for itself after about 9B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Mistral AI32K ctx (128K) · 26K out | $0.10 | $0.30 | $0.01 | 84 | 0.62 s | 100% | Oct 23 |
1 provider · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Mistral AI | not checked yet | 32K | 26K | yes | yes | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Voxtral Small 24B 2507 spec sheet, field by field, with sources
Voxtral Small 24B 2507 spec sheetmaker-declared
What Mistral AI declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 131,072 tokens
- Parameters
- 24,261,800,960≈ 24.3B
- Active experts
- none declared in the weights
- Weight precision
- bfloat16
- License
- Apache 2.0 — open weights, permissivecurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the makermaker's docs · read 2026-09-07
- Modalities
- text · audio
- Max output (official)
- to verify
- Release date
- July 15, 2025maker's docs · read 2026-09-07
- Maker lifecycle status
- General availabilitymaker's docs · read 2026-09-07
Also declared in the weights
- Architecture class
- VoxtralForConditionalGeneration
- Layers
- 40
- Vocabulary
- 131,072 tokens
- Weights first published
- July 1, 2025
- Weights last updated
- December 20, 2025
- Languages declared
- English · French · German · Spanish · Italian · Portuguese · Dutch · Hindi
- Paper
- arXiv:2507.13264
mistralai/Voxtral-Small-24B-2507 · config.json @ da5b424 · read 2026-10-08 · 7 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Sep 5 | Mistral AI | $0.11 → $0.10 | $0.33 → $0.30 | −9% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Mistral AI | $0.25 | $0.95 | $0.70 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Mistral AI models · all its models, hosts and history ›
- Mistral Nemo6 providers · from $0.038
- Mistral Small 3.2 24B4 providers · from $0.28
- Mistral Small 42 providers · from $0.75
- Codestral 25081 provider · from $1.20
- Devstral 2 25121 provider · from $2.40
- Ministral 3 14B 25121 provider · from $0.40