Mistral 7B Instruct
AI model by Mistral. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Mistral 7B Instruct is a budget-tier option from Mistral at $0.25/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 7B Instruct reports 110 tok/s output speed and 740ms 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 7B Instruct costs $0.28 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 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Mistral 7B InstructCurrent | $0.25 | $0.25 | 110 tok/s |
| Qwen3.5 9B (Non-reasoning) | $0.17 | $0.25 | 91 tok/s |
| Granite 3.3 8B (Non-reasoning) | $0.03 | $0.25 | 15 tok/s |
| Granite 4.0 H Small | $0.06 | $0.25 | 10 tok/s |
| Granite 4.2 8B | $0.06 | $0.25 | 144 tok/s |
| Llama 2 Chat 7B | $0.05 | $0.25 | — |