OpenAI: Text Embedding 3 Large
openai/text-embedding-3-large
Pinned host: OpenAI, no recent checks Every request goes here. The response header X-PG-Host names it on every call.
List price, input
$0.13
per 1M input tokens
Context
8K
Modalities
text to embeddings
input to output
Released
Oct 30, 2025
first listed on OpenRouter
Hosts
The same model from 2 hosts. We pin one and show you the rest. Every host is billed at the same price.
| OpenAI, no recent checks pinned | $0.13 | $0.13 | not stated | - | no sample yet | 100.00% |
| Azure, no recent checks | $0.13 | $0.13 | not stated | - | no sample yet | 100.00% |
Prices read 2026-11-11 00:00 UTC. Uptime is OpenRouter's last day until our checks start.
Latency, last 24 hours
Median response time on the pinned host, per hour.
No health checks recorded for this host in the last 24 hours. The chart fills in as checks run.
Config
Copy the block for your client. Your key starts with sk-pg-v1-.
shell
curl https://api.plaingateway.com/api/v1/embeddings \
-H "Authorization: Bearer $PLAINGATEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/text-embedding-3-large","input":"Hello"}' \
-i | grep -i "x-pg-"FAQ
What does it cost?
The provider's list price per token, with 0% platform fee.
Can I choose a different host?
Yes. Use provider.order or provider.only exactly as on OpenRouter. See Docs.