Model
Llama-3.3-70B-Instruct
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
2 providersreleased knowledge cutoff 2023-12open weights
$0.22
best input /M · Merge Gateway
$0.5
best output /M
128K
context window
4K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| Nvidia meta/llama-3.3-70b-instruct | — | — | — | — | 128K | no reasoningtoolsstructuredno vision | Nov 26, 2024 | |
| Merge Gateway meta/llama-3.3-70b-instruct | $0.22 | $0.5 | $0.11 | — | 131K | no reasoningtoolsno structuredno vision | Dec 6, 2024 |
Price badge
https://models.sutraworks.ai/badge/meta/llama-3.3-70b-instruct.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Benchmarks
- Artificial Analysis Coding Index ↗(index)report ↗10.7
- SciCode(percent correct)report ↗26
- Terminal-Bench Hard ↗(success rate)report ↗3
Weights
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.