Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Llama-3.1-8b-Instruct-Fp8 meta/llama-3.1-8b-instruct-fp8 | Llama-3.3-70b-Instruct-Fp8-Fast meta/llama-3.3-70b-instruct-fp8-fast | |
|---|---|---|
| Provider | Meta | Meta |
| Family | Llama 3 | Llama 3 |
| Modality | text | text |
| Context window | 32,000 tok | 24,000 tok |
| Max output | 4,096 tok | 8,192 tok |
| Released | 2024-07-25 | 2024-12-06 |
| Input price | $0.150 /1M | $0.290 /1M |
| Output price | $0.290 /1M | $2.25 /1M |
| Cache read | — | — |
| Tools | — | yes |
| Streaming | yes | yes |
| Vision | — | — |
| JSON mode | — | yes |
| Reasoning | — | — |
| Prompt caching | — | — |
Llama 3.1 8B quantized to FP8 precision
Llama 3.3 70B quantized to fp8 precision, optimized to be faster.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Llama-3.1-8b-Instruct-Fp8
client.chat.completions.create(
model="meta/llama-3.1-8b-instruct-fp8",
messages=[{"role":"user","content":"hello"}],
)
# Try Llama-3.3-70b-Instruct-Fp8-Fast — same client, same key
client.chat.completions.create(
model="meta/llama-3.3-70b-instruct-fp8-fast",
messages=[{"role":"user","content":"hello"}],
)