Mistral: Mistral Small 3mistralai
Bottom Line
Mistral: Mistral Small 3: $0.05/1M input, $0.08/1M output, 33K context. 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...
API Pricing (per 1M tokens)
| Input | $0.05 |
| Output | $0.08 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.06 |
Specs & Performance
| Context Length | 33K |
| Max Output | 16K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from mistralai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Mistral: Mistral Small 3 API cost?
Mistral: Mistral Small 3 costs $0.05/1M input tokens and $0.08/1M output tokens. Blended cost at a 3:1 ratio is about $0.06/1M tokens.
What is the context window of Mistral: Mistral Small 3?
Mistral: Mistral Small 3 supports a 33K token context window with up to 16K output tokens.
Is Mistral: Mistral Small 3 worth it?
Mistral: Mistral Small 3 has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.