Ministral 3 8B
AI model by Mistral. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Ministral 3 8B is a budget-tier option from Mistral at $0.15/M output tokens. Despite the low price, it scores competitively on Coding Index (9.7) and Intelligence Index (5.5) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Ministral 3 8B reports 89 tok/s output speed and 720ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Ministral 3 8B costs $0.16 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 2026-10-08.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Ministral 3 8BCurrent | $0.15 | $0.15 | 89 tok/s |
| Qwen3.5 4B (Non-reasoning) | $0.03 | $0.15 | 23 tok/s |
| Qwen3.5 4B (Reasoning) | $0.03 | $0.15 | 29 tok/s |
| Agnes 3.0 Flash | $0.05 | $0.15 | 237 tok/s |
| Solar Mini | $0.15 | $0.15 | — |
| HyperNova 60B 2605 (high, based on gpt-oss-120b) | $0.04 | $0.14 | 353 tok/s |