Open Llama instruction model for multilingual chat, reasoning, and coding
Llama 3.3 70B by meta is offered by 5 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is STACKIT at $0.53 / $0.76 per 1M. Prices vary about 3.3× across the providers that host it.
The context window is 128,000 tokens at the reference host, but hosts report different limits, from 128,000 to 131,072, so the usable window depends on the provider you pick. It supports tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2023-12.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| STACKIT cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic | Cloud | $0.53 | $0.76 | — | — | 128,000 | 4,096 | |
| Groq llama-3.3-70b-versatile | Cloud | $0.59 | $0.79 | — | — | 131,072 ⚠ | 32,768 | |
| Together AI meta-llama/Llama-3.3-70B-Instruct-Turbo | Cloud | $1.04 | $1.04 | — | — | 131,072 ⚠ | 131,072 | |
| Venice AI | Gateway | $0.70 | $2.80 | — | — | 128,000 | 4,096 | |
| NanoGPT TEE/llama3-3-70b | Gateway | $1.75 | $2.75 | $1.75 | — | 128,000 | 16,384 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-13). Each future sync adds a point, and once accumulated a line is drawn here.