Llama-3.1-8B-Instruct vs Nova Pro 1.0

API pricing, benchmark indices and specs — updated 19 October 2026.

meta-llama · A · Open weights
Params
8.0 B
Context
—
30d
4.9 M
llama3.1 licence · conditional
amazon · B · API-only
Input / 1M
$0.80
Output / 1M
$3.20
AA index
7
proprietary · 300K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification Llama-3.1-8B-Instruct Nova Pro 1.0
Deployment Open weights · also via API API-only (closed weights)
Parameters 8.0 B n/a — API-only
Architecture LlamaForCausalLM n/a — API-only
Context length 131,072 300,000
Licence llama3.1 Proprietary
Commercial use Conditional Per API terms
Languages 8 n/a — API-only
Downloads 30d 4,864,172 n/a — API-only
Downloads all time 191.0 M n/a — API-only
Quantizations on the Hub SAFETENSORS n/a — API-only
Gated Yes — accept licence n/a — API-only
First seen on the Hub 2024-07-18 n/a — API-only
API input price / 1M tokens $0.05 $0.80
API output price / 1M tokens $0.08 $3.20
Est. cost per 1M input + 1M output tokens $0.13 $4.00
Cached input / 1M tokens $0.025 —
AA Intelligence Index 6.9 7
AA Coding Index 5.4 —
AA Agentic Index — —
Max output tokens 117,964 5,120
API providers 5 1
Tool calling Yes Yes
Reasoning mode No No

API cost

Estimated cost of 1M input + 1M output tokens via OpenRouter

Llama-3.1-8B-Instruct $0.13
Nova Pro 1.0 $4.00

Llama-3.1-8B-Instruct is 30.8× cheaper at list price.

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Llama-3.1-8B-Instruct · fp16 19.4 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons