Open-weights privacy, self-hosting or ultra-cheap hosted inferencing
Stored values, not live provider measurements.
| Provider | Meta |
| Category | Open-Weights |
| Input cost / 1M tokens | $0.590 |
| Output cost / 1M tokens | $0.790 |
| Cache read / 1M tokens | $0.590 |
| Context window | 128k tokens |
| Max output | 8k tokens |
| Batch API | Not listed |
| Vision | Text only |
| Vision price / 1k images | — |
| Speed rating | Unrated |
| Intelligence score | Unrated |
| Throughput | Unrated |
| Time to first token | Unrated |
| Hardware | Groq LPU / Cerebras CS-3 |
Enter your own input, output, caching, and batch assumptions in the calculator.
Open calculatorPricing review: date not recorded
Performance review: source/date not recorded
Llama 3.3 70B (Groq/Together) costs $0.590 per 1M input tokens and $0.790 per 1M output tokens in the stored catalog. Blended cost depends on your input/output mix.
Llama 3.3 70B (Groq/Together) has a context window of 128k tokens (128,000 tokens). This is the maximum combined input and output for a single request.
Llama 3.3 70B (Groq/Together) is currently offered by Meta. Pricing is a stored catalog value — confirm current rates with the provider.