models/Preferred Networks/Plamo-Embedding-1b
PN
Preferred Networks

Plamo-Embedding-1b

embedding
Compare

PLaMo-Embedding-1B is a Japanese text embedding model developed by Preferred Networks, Inc. It can convert Japanese text input into numerical vectors and can be used for a wide range of applications, including information retrieval, text classification, and clustering.

MODALITIES
embedding
INPUT
$0.020 /1M
OUTPUT
$0 /1M
RELEASED
2025-09-24

Plamo-Embedding-1b (pfnet/plamo-embedding-1b) is a embedding model from Preferred Networks, released 2025-09-24. Context window: — tokens; max output —. Pricing via AIgateway: input $0.020/M tokens, output $0/M tokens. Call it via https://api.aigateway.sh/v1/embeddings — set model="pfnet/plamo-embedding-1b". Best for: RAG, Semantic search, Recommendation.

model · pfnet/plamo-embedding-1b

Use this model

model: pfnet/plamo-embedding-1b
curl https://api.aigateway.sh/v1/embeddings \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"pfnet/plamo-embedding-1b","input":"the quick brown fox"}'

Capabilities

Strengths

  • Semantic similarity
  • Vector search

Use cases

RAGSemantic searchRecommendation

Pricing

Input$0.020 / 1M tokens
Output$0 / 1M tokens
You pay pass-through · 5% applied at credit top-up, not per-call.
See API example →CompareAPI referenceSee usage ranking →

Collections

More embedding models →More from Preferred Networks →Frontier models →Free-tier models →
API schema

Call Plamo-Embedding-1b from any OpenAI SDK

POST https://api.aigateway.sh/v1/embeddings·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "pfnet/plamo-embedding-1b",
  "input": "Text to embed, or an array of strings for batch."
}

Response

json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0456, 0.0789, /* ... */]
    }
  ],
  "model": "pfnet/plamo-embedding-1b",
  "usage": { "prompt_tokens": 5, "total_tokens": 5 }
}

Quickstart

from openai import OpenAI
client = OpenAI(base_url="https://api.aigateway.sh/v1", api_key="sk-aig-...")

r = client.embeddings.create(model="pfnet/plamo-embedding-1b", input="hello world")
print(r.data[0].embedding[:5])

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Frequently asked questions

What is Plamo-Embedding-1b?
PLaMo-Embedding-1B is a Japanese text embedding model developed by Preferred Networks, Inc. It can convert Japanese text input into numerical vectors and can be used for a wide range of applications, including information retrieval, text classification, and clustering. It is a embedding model from Preferred Networks, accessible via AIgateway's OpenAI-compatible API at slug pfnet/plamo-embedding-1b.
How much does Plamo-Embedding-1b cost via AIgateway?
Input costs $0.020 per 1M tokens; output costs $0.000 per 1M tokens. Pass-through plus a 5% platform fee applied at top-up, not per call.
How do I call Plamo-Embedding-1b from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "pfnet/plamo-embedding-1b". The request and response shapes match OpenAI exactly.
Does Plamo-Embedding-1b support streaming, tool calling, vision, and JSON mode?
Streaming — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
What are the best use cases for Plamo-Embedding-1b?
RAG, Semantic search, Recommendation. Key strengths: Semantic similarity; Vector search.
Can I bring my own Preferred Networks API key (BYOK)?
Yes. Attach a Preferred Networks key in your AIgateway dashboard and this model flips to pass-through — you pay Preferred Networks directly and AIgateway waives the 5% platform fee on those calls.