Mistral Small 3 pricing & benchmarks
Released Jan 30, 2025 · served by 1 provider
What Mistral Small 3 is
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
- Model ID:
mistralai/mistral-small-24b-instruct-2501 - Modality: text->text
- Knowledge cutoff: 2023-10-31
- Tool calling: not supported · Structured output: supported
- Weights:
mistralai/Mistral-Small-24B-Instruct-2501on Hugging Face
Providers and prices for Mistral Small 3
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| DeepInfracheapest | $0.050 | $0.080 | 33K | fp8 | 100.0% | — |
FAQ
How much does the Mistral Small 3 API cost?
$0.050 per 1M input tokens and $0.080 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.07.
Is Mistral Small 3 free?
No. It is a paid model starting at $0.050 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for Mistral Small 3?
DeepInfra at $0.050 input / $0.080 output per 1M tokens (fp8 quantization).
Can I self-host Mistral Small 3?
Yes — weights are published as mistralai/Mistral-Small-24B-Instruct-2501 on Hugging Face, so you can run it on your own hardware.