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.
| Bge-M3 baai/bge-m3 | Llama-4-Scout-17b-16e-Instruct meta/llama-4-scout-17b-16e-instruct | |
|---|---|---|
| Provider | BAAI | Meta |
| Family | BGE | Llama 4 |
| Modality | embedding | text |
| Context window | 60,000 tok | 131,000 tok |
| Max output | — | 4,096 tok |
| Released | 2024-05-22 | 2025-04-05 |
| Input price | $0.012 /1M | $0.270 /1M |
| Output price | — | $0.850 /1M |
| Cache read | — | — |
| Tools | — | yes |
| Streaming | — | yes |
| Vision | — | yes |
| JSON mode | — | yes |
| Reasoning | — | — |
| Prompt caching | — | — |
Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.
Meta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
# 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 Bge-M3
client.chat.completions.create(
model="baai/bge-m3",
messages=[{"role":"user","content":"hello"}],
)
# Try Llama-4-Scout-17b-16e-Instruct — same client, same key
client.chat.completions.create(
model="meta/llama-4-scout-17b-16e-instruct",
messages=[{"role":"user","content":"hello"}],
)