HASTATAgent stack guide llama
Llama 3.1 70B Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context128K
Output128K
Providers5
CapabilitiesTool calling
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Nvidiameta/llama-3.1-70b-instruct | $0.00 | $0.00 | Unavailable | 128K | 2024-07-16 |
 OpenRoutermeta-llama/llama-3.1-70b-instruct | $0.40 | $0.40 | Unavailable | 128K | 2024-07-23 |
 LLM Gatewayllama-3.1-70b-instruct | $0.72 | $0.72 | Unavailable | 128K | 2024-07-23 |
 Kilo Gatewaymeta-llama/llama-3.1-70b-instruct | $0.40 | $0.40 | Unavailable | 128K | 2024-07-23 |
 Weights & Biasesmeta-llama/Llama-3.1-70B-Instruct | $0.80 | $0.80 | $0.80 | 128K | 2024-07-23 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text → text