Llama 3.1 8B vs Llama 3.3 70B
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Meta
|
by Together
2 providers:
Meta $0.590/$0.790
Together $1.04/$1.04
|
|---|---|---|
| Overview | ||
| Status | Current open weights Open weights | Current open weights Open weights |
| Released | Jul 23, 2024 | Dec 6, 2024 |
| Pricing per million tokens | ||
| Input | $0.050/Mtok | $1.04/Mtok |
| Output | $0.080/Mtok | $1.04/Mtok |
| Blended avg | $0.058/Mtok | $1.04/Mtok |
| Specifications | ||
| Context window | 128K tokens | 128K tokens |
| Parameters | 8B | 70B |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks source: Vellum LLM Leaderboard (Jun 2026), Kaggle dataset | ||
| Avg benchmark score | 34 | 46.6 |
| Perf / dollar | 591.3 | 44.8 |
| GPQA Diamond | 30 | 50.5 |
| SWE-Bench Verified | 12 | 22 |
| Humanity's Last Exam | 5 | 10 |
| ARC-AGI 2 | 6 | 12 |
| AIME 2025 | 20 | 38 |
| MMMLU | 65 | 72 |
| BFCL | 48 | 77.3 |
| HumanEval | 72 | 78 |
| MATH 500 | 48 | 60 |
| Providers | ||
| Available from |
Meta — $0.050/$0.080/Mtok
|
Meta — $0.590/$0.790/Mtok
Together — $1.04/$1.04/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Llama 3.1 8B | Llama 3.3 70B | Savings |
|---|---|---|---|
| 1M tokens | $0.06 | $1.04 | $0.98 (94.2%) |
| 10M tokens | $0.58 | $10.4 | $9.83 (94.5%) |
| 100M tokens | $5.75 | $104 | $98.25 (94.5%) |
| 1000M tokens | $57.5 | $1040 | $982.5 (94.5%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.058/Mtok blended vs $1.04 — 94.5% less on the same 50/50 token mix
- raw capability matters more than price: 46.6 vs 34 average benchmark score
- provider flexibility: available from 2 providers, so you can price-shop hosts or fail over
Price movement
recorded changes since we began tracking each model · last checked Aug 9, 2026| Model | Changes | Latest move | Old → new $/M |
|---|---|---|---|
| Llama 3.1 8B | 0 | — no move | Stable since we began tracking — no change recorded |
| Llama 3.3 70B | 1 | price rise on Jun 25, 2026 | $0.88/$0.88 → $1.04/$1.04/Mtok |
Summary
Llama 3.1 8B by Meta costs $0.050/Mtok input and $0.080/Mtok output, with a 128K-token context window. It supports text input.
Llama 3.3 70B by Together costs $1.04/Mtok input and $1.04/Mtok output, with a 128K-token context window. It supports text input and is available from 2 providers.
On a blended cost basis, Llama 3.1 8B is 94.5% cheaper than Llama 3.3 70B.
On benchmarks, Llama 3.3 70B scores higher (46.6 vs 34) on average. In terms of value, Llama 3.1 8B has better performance per dollar (591.3 vs 44.8).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.