Mistral Small 3.2 24B
mistral/small-3-2-24b-instructVon Mistral · Familie: mistral-small · veröffentlicht 2025-06-20 · Wissensstand: 2023-10-31
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Fähigkeiten
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding65
- Tool calling40/40
- Structured output20/20
- Reasoning0/10
- Context window (100K → 1M)2/20
- Provider availability3/10
Agents73
- Tool calling35/35
- Structured output25/25
- Reasoning0/15
- Output token limit10/15
- Provider availability3/10
JSON / structured output100
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume20/20
Cost efficiency83
- Headline price (log-scaled)78/95
- Has prompt-cache pricing5/5
Long context45
- Context window (100K → 2M)35/90
- Has published price for full window10/10
Vision80
- Accepts image input50/50
- Context window (10K → 1M)17/30
- Has published price10/10
- Provider availability3/10
Production-readiness69
- Number of independent providers15/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers4/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.39 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $0.78 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.21 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $0.66 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $0.83 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Preis-Details
Empfohlene Preise von kilo · mistralai/mistral-small-3.2-24b-instruct
Bei 3 Anbietern verfügbar
| Anbieter | Anbieter-Modell-ID | Eingabe / 1M | Ausgabe / 1M | Kontext | Veröffentlicht |
|---|---|---|---|---|---|
| OpenRouter openrouter | mistralai/mistral-small-3.2-24b-instruct | $0.075 | $0.200 | 128K | 2025-06-20 |
| Venice AI venice | mistral-small-3-2-24b-instruct | $0.094 | $0.250 | 256K | 2026-01-15 |
| Kilo Gateway kilo | mistralai/mistral-small-3.2-24b-instruct | $0.060 | $0.180 | 131K | 2025-06-20 |
Datenunterschiede zwischen Anbietern
- context_window varies: 128000, 131072, 256000
- release_date varies (span 209d): 2025-06-20, 2026-01-15
- modalities varies across offerings
Anbieter melden unterschiedliche Werte für dieses Modell. Die Schnellinfos oben nutzen den repräsentativen Anbieter; pro Anbieter siehe Tabelle.
Frequently asked questions
How much does Mistral Small 3.2 24B cost?
Mistral Small 3.2 24B costs $0.060 per 1M input tokens and $0.180 per 1M output tokens, sourced from kilo. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Mistral Small 3.2 24B?
Mistral Small 3.2 24B has a context window of 128K tokens, with a max output of 16K tokens per reply. This is the total combined size of prompt + completion.
Does Mistral Small 3.2 24B support tool calling?
Yes. Mistral Small 3.2 24B supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Mistral Small 3.2 24B support structured output / JSON mode?
Yes. Mistral Small 3.2 24B supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Mistral Small 3.2 24B accept image input?
Yes. Mistral Small 3.2 24B accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check Mistral's docs for the exact rule.
Is Mistral Small 3.2 24B open-weight?
Yes. Mistral Small 3.2 24B's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Mistral Small 3.2 24B?
If Mistral Small 3.2 24B doesn't fit, consider Mistral Nemo, Mistral Large 3, Devstral 2. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Mistral models
- Mistral Nemo$0.15 in / $0.15 out
- Mistral Large 3$0.50 in / $1.50 out
- Devstral 2$0.40 in / $2.00 out
- Mistral Large 2.1$2.00 in / $6.00 out
- Mistral Nemo$0.02 in / $0.04 out
Capability lists this model is in
Zuletzt aktualisiert:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.