Mistral · Model
Voxtral Small 24B 2507 pricing, context window and specs
Voxtral Small 24B 2507 costs $0.10 per million input tokens and $0.30 per million output tokens, and reads up to 32,768 tokens per request. By blended price it is number 3 of Mistral’s 8 current models here, counting from the cheapest.
- Input / 1M
- $0.10
- Output / 1M
- $0.30
- Cached / 1M
- $0.01
- Context
- 32,768
- Max output
- Not published
- Released
- 2025-10-30
Estimate your cost with Voxtral Small 24B 2507Compare all Mistral modelsCount tokens for Voxtral Small 24B 2507
Pricing
Voxtral Small 24B 2507 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.10 | $0.30 |
| Cached input (read) | $0.01 | – |
Output costs 3.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 10% of the normal input price.
Examples
What Voxtral Small 24B 2507 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.000203 | $6.16 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.000642 | $9.76 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.00172 | $10.46 |
| Document summariser | 8,000 / 600 | 300 | $0.00098 | $8.94 |
Change any number in the cost calculator.
Context
Context window
Voxtral Small 24B 2507 accepts up to 32,768 tokens per request, roughly 24,576 English words or 49 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $0.00328 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Check whether your text fits Voxtral Small 24B 2507’s window.
Features
Capabilities
- Image input
- No
- Tool / function calling
- Yes
- Reasoning mode
- No
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text, audio, file
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
Voxtral Small 24B 2507 model ID
- OpenRouter
mistralai/voxtral-small-24b-2507- Open weights
- mistralai/Voxtral-Small-24B-2507
Use the OpenRouter ID when calling it through OpenRouter; Mistral’s own API may name it differently. See the model ID reference for the providers we document.
Mistral
Where Voxtral Small 24B 2507 sits in Mistral’s line-up
Ranked by blended price (three parts input to one part output, $0.15 per 1M for Voxtral Small 24B 2507), it is number 3 of Mistral’s 8 current models here, counting from the cheapest. One step down, Ministral 3 8B 2512 costs $0.15 blended, the same. Unlike Voxtral Small 24B 2507, it accepts images, doesn’t accept files or audio and reads up to 262,144 tokens (32,768 here). One step up, Ministral 3 14B 2512 costs $0.20 (1.3× as much). Unlike Voxtral Small 24B 2507, it accepts images, doesn’t accept files or audio and reads up to 262,144 tokens (32,768 here). See every Mistral model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Ministral 3 3B 2512 | $0.10 | $0.10 | 131,072 | 2025-12-02 |
| Ministral 3 8B 2512 | $0.15 | $0.15 | 262,144 | 2025-12-02 |
| Voxtral Small 24B 2507 (this page) | $0.10 | $0.30 | 32,768 | 2025-10-30 |
| Ministral 3 14B 2512 | $0.20 | $0.20 | 262,144 | 2025-12-02 |
| Mistral Small 4 | $0.15 | $0.60 | 262,144 | 2026-03-16 |
| Codestral 2508 | $0.30 | $0.90 | 128,000 | 2025-08-01 |
| Mistral Large 4 | $0.68 | $2.09 | 1,048,576 | 2026-10-06 |
| Mistral Medium 3.5 | $1.50 | $7.50 | 262,144 | 2026-04-30 |
Mistral’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
Save
Cheaper alternatives
- Ministral 3 3B 2512Mistral33% cheaper
- Nemotron 3.5 LightningNVIDIA32% cheaper
- Gemma 4 26B A4BGoogle29% cheaper
- Qwen3.5-9BQwen25% cheaper
- Seed 1.6 FlashByteDance Seed13% cheaper
Current models from major providers, one per provider, that keep tool calling, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Gemma 4 31BGoogle$0.09 / $0.34
- Seed 1.6 FlashByteDance Seed$0.075 / $0.30
- Nemotron 3 SuperNVIDIA$0.08 / $0.45
- GPT-6 LunaOpenAI$0.10 / $0.50
- Claude Haiku 5.5Anthropic$0.10 / $0.50
Current models from other major providers, closest blended price.
FAQ
Voxtral Small 24B 2507 questions
How much does Voxtral Small 24B 2507 cost?
Voxtral Small 24B 2507 costs $0.10 per million input tokens and $0.30 per million output tokens, with cached input at $0.01. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00027. Use the LLM cost calculator for your own workload.
What is Voxtral Small 24B 2507’s context window?
32,768 tokens, about 24,576 English words or 49 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Voxtral Small 24B 2507 support prompt caching and batch requests?
Yes, cached input is billed at $0.01 per million tokens (10% of the normal input price). No batch price is published for it.
What are cheaper alternatives to Voxtral Small 24B 2507?
With the same essentials (tool calling), the cheapest options are Ministral 3 3B 2512 (33% cheaper), Nemotron 3.5 Lightning (32% cheaper), Gemma 4 26B A4B (29% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Voxtral Small 24B 2507?
On OpenRouter it is mistralai/voxtral-small-24b-2507. Mistral’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
Is Voxtral Small 24B 2507 open source?
Yes, Voxtral Small 24B 2507 has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.