Llama 3.1 Instruct 8B
AI model by Meta. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Llama 3.1 Instruct 8B is a budget-tier option from Meta at $0.05/M output tokens. Despite the low price, it scores competitively on Intelligence Index (7.4) and Coding Index (5.4) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Llama 3.1 Instruct 8B reports 141 tok/s output speed and 820ms 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, Llama 3.1 Instruct 8B costs $0.03 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 |
|---|---|---|---|
Llama 3.1 Instruct 8BCurrent | $0.02 | $0.05 | 141 tok/s |
| Gemma 4 E4B (Non-reasoning) | $0.02 | $0.10 | 39 tok/s |
| Ministral 3 3B | $0.10 | $0.10 | 216 tok/s |
| Granite 4.1 8B | $0.05 | $0.10 | 104 tok/s |
| Gemma 4 E4B (Reasoning) | $0.02 | $0.10 | 38 tok/s |
| Sarvam 30B (high) | $0.03 | $0.11 | — |