Mistral Small (Sep '24)
AI model by Mistral. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Mistral Small (Sep '24) is a budget-tier option from Mistral at $0.60/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Mistral Small (Sep '24) reports 143 tok/s output speed and 810ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Mistral Small (Sep '24) costs $0.26 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Mistral Small (Sep '24)Current | $0.20 | $0.60 | 143 tok/s |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | $0.20 | $0.60 | 120 tok/s |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | $0.20 | $0.60 | 163 tok/s |
| GPT-4o mini | $0.15 | $0.60 | 101 tok/s |
| Solar Pro 3 | $0.15 | $0.60 | 152 tok/s |
| gpt-oss-120b (high) | $0.15 | $0.60 | 161 tok/s |