Mistral Small 3.2 24B API pricing
Mistral · Budget price tier · Apache 2.0 · released 2025-06. Prices in USD per 1 million tokens. Data snapshot: 2026-10-22.
Deprecated. The model maker has announced retirement of this model's API · shutdown 2026-07-31 · suggested replacement: Mistral Small 4. It still carries a price because hosts still serve it; treat it as a model to migrate off, not one to start on.
Mistral Small 3.2 24B has held the same list price since 2026-10-18 and is the 47th cheapest of 164 models in the Budget price tier. Buying from DeepInfra rather than at the price we quote lowers the token price by about 20%, for a quantized fp8 build. Its maker has announced its retirement, so it is a model to migrate off rather than start on.
- Input: $0.0938 per 1M tokens
- Output: $0.25 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: Not published
- Context window: 256K tokens
- Arena ELO: 1356 as of 2026-10-08
Market position
On blended price ($0.2031 per 1M tokens at 30% input, 70% output) it is cheaper than 72% of models in the Budget price tier: 47th cheapest of 164. Across every price tier it is cheaper than 85% of priced text models in the catalogue: 47th cheapest of 308. Its Arena ELO of 1356 ranks 120th of the 156 models that carry one, above 23% of them.
Licence, size and capabilities
Mistral Small 3.2 24B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its published size is 24B parameters. Listed capabilities: Text, Vision, Agents. Filling its 256K context window once costs $0.024 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 4 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Cheapest host: DeepInfra at $0.075 input / $0.20 output per 1M tokens, 20% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. The dearest, Mistral, charges 1.5x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| DeepInfra | $0.075 | $0.20 | fp8 |
| Venice (price we quote) | $0.0938 | $0.25 | fp8 |
| Parasail | $0.09 | $0.30 | bf16 |
| Mistral (model maker) | $0.10 | $0.30 | not declared |
List prices as published on 2026-10-22, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Mistral publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $27 |
| Knowledge Q&A | 2,000 / 800 | $39 |
| Meeting Summary | 10,000 / 1,200 | $124 |
| Marketing Content | 2,500 / 1,800 | $68 |
| Coding Task | 3,000 / 2,000 | $78 |
| Invoice Processing | 1,500 / 600 | $29 |
| Call Summary | 2,000 / 700 | $36 |
| Agent Workflow | 6,000 / 3,000 | $131 |
Price history
Mistral Small 3.2 24B entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $0.0938 input / $0.25 output per 1M tokens that day. No list price change since 2026-10-18. Last checked against the 2026-10-22 snapshot.
Alternatives to Mistral Small 3.2 24B
- Next cheaper model in the Budget price tier: MiMo-V2.5 (Xiaomi) at $0.2023 blended, under 1% less.
- Next more expensive: Qwen3 14B (Alibaba) at $0.204 blended, under 1% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Mistral Small 3.2 24B.
- DeepSeek V3 (DeepSeek): $0.2574 in / $1.0287 out per 1M, Arena ELO 1358 (292% more expensive, 2 ELO points higher)
- GLM 4.5V (Zhipu): $0.60 in / $1.80 out per 1M, Arena ELO 1352 (609% more expensive, 4 ELO points lower)
- gpt-oss-120b (OpenAI): $0.15 in / $0.60 out per 1M, Arena ELO 1352 (129% more expensive, 4 ELO points lower)
- Nemotron 3.5 Lightning (Nvidia): $0.07 in / $0.20 out per 1M, Arena ELO 1349 (21% cheaper, 7 ELO points lower)
- Cheapest within 15 Arena points: Gemma 3 12B (Google), 41% cheaper, 14 ELO points lower, out of 17 models in that band.
- Highest Arena ELO within 20% of this price: MiMo-V2.6-Flash (Xiaomi), 17% more expensive, 95 ELO points higher, out of 10 models in that price band.
Other models from Mistral
The 8 nearest to Mistral Small 3.2 24B in price, of 19 other Mistral models in the catalogue. Prices per 1M tokens, input then output.
- Mistral Small 3: $0.05 / $0.08
- Ministral 3 3B 2512: $0.10 / $0.10
- Ministral 3 8B 2512: $0.15 / $0.15
- Ministral 3 14B 2512: $0.20 / $0.20
- Voxtral Small 24B 2507: $0.10 / $0.30
- Mistral Small 4: $0.15 / $0.60
- Saba: $0.20 / $0.60
- Mistral Small 3.1 24B: $0.351 / $0.555
All 20 Mistral models and prices
Common questions about Mistral Small 3.2 24B pricing
- How much does Mistral Small 3.2 24B cost?
- Mistral Small 3.2 24B costs $0.0938 per 1M input tokens and $0.25 per 1M output tokens at Venice, the host whose rate we quote. Venice serves a quantized fp8 build, which is not the same product as the full-precision model. The model maker, Mistral, lists it at $0.10 per 1M input tokens and $0.30 per 1M output tokens. Prices as listed on 2026-10-22.
- Which host is cheapest for Mistral Small 3.2 24B?
- Cheapest host: DeepInfra at $0.075 input / $0.20 output per 1M tokens, 20% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. The dearest, Mistral, charges 1.5x the cheapest. Host rates as listed on 2026-10-22.
- Does Mistral Small 3.2 24B offer batch or cached pricing?
- No. Neither a batch rate nor a prompt-cache rate is published for Mistral Small 3.2 24B as of 2026-10-22.
- What would Mistral Small 3.2 24B cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $27 on Mistral Small 3.2 24B at the list price quoted on 2026-10-22.
- Can Mistral Small 3.2 24B be self-hosted?
- Yes. Mistral Small 3.2 24B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- Has the price of Mistral Small 3.2 24B changed?
- Mistral Small 3.2 24B entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $0.0938 input / $0.25 output per 1M tokens that day. No list price change since 2026-10-18. Last checked against the 2026-10-22 snapshot.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server