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.
| Meta-Llama-3-8b-Instruct hf/meta-llama/meta-llama-3-8b-instruct | Llama-3-8b-Instruct-Awq meta/llama-3-8b-instruct-awq | |
|---|---|---|
| Provider | Hugging Face | Meta |
| Family | Llama 3 | Llama 3 |
| Modality | text | text |
| Context window | 4,096 tok | 8,192 tok |
| Max output | 4,096 tok | 4,096 tok |
| Released | 2024-04-18 | 2024-05-09 |
| Input price | $0.050 /1M | $0.120 /1M |
| Output price | $0.100 /1M | $0.270 /1M |
| Cache read | — | — |
| Tools | — | — |
| Streaming | yes | yes |
| Vision | — | — |
| JSON mode | — | — |
| Reasoning | — | — |
| Prompt caching | — | — |
Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.
Quantized (int4) generative text model with 8 billion parameters from Meta.
# 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 Meta-Llama-3-8b-Instruct
client.chat.completions.create(
model="hf/meta-llama/meta-llama-3-8b-instruct",
messages=[{"role":"user","content":"hello"}],
)
# Try Llama-3-8b-Instruct-Awq — same client, same key
client.chat.completions.create(
model="meta/llama-3-8b-instruct-awq",
messages=[{"role":"user","content":"hello"}],
)