What embedding models are in the catalog?
24 embedding models listed with pricing and endpoint data.
o10 State of Inference Spend 2026 found up to 638× compliant price spread across venues for identical workloads.
o10Last updated 2026-06-14b
Embedding models
24 embedding models in the unified inference model catalog.
Browse embedding models with gateway pricing and eval-gated routing notes.
Dashboards observe.
o10 enforces.
o10 enforces.
Every page in this index follows the same structure as the home site — answer-first, passage blocks, operational steps, and expanded FAQs. o10 State of Inference Spend 2026 found up to 638× compliant price spread across venues for identical workloads.
Start hereQuick overview
How to use this index
Embedding24 models
Qwen3 Embedding 0.6B
alibaba · alibaba/qwen3-embedding-0.6b
Qwen3 Embedding 4B
alibaba · alibaba/qwen3-embedding-4b
Qwen3 Embedding 8B
alibaba · alibaba/qwen3-embedding-8b
Titan Text Embeddings V2
amazon · amazon/titan-embed-text-v2
Embed v4.0
cohere · cohere/embed-v4.0
Gemini Embedding 001
google · google/gemini-embedding-001
Gemini Embedding 2
google · google/gemini-embedding-2
Text Embedding 005
google · google/text-embedding-005
Text Multilingual Embedding 002
google · google/text-multilingual-embedding-002
Codestral Embed
mistral · mistral/codestral-embed
Mistral Embed
mistral · mistral/mistral-embed
text-embedding-3-large
openai · openai/text-embedding-3-large
text-embedding-3-small
openai · openai/text-embedding-3-small
text-embedding-ada-002
openai · openai/text-embedding-ada-002
voyage-3-large
voyage · voyage/voyage-3-large
Voyage 3.5
voyage · voyage/voyage-3.5
Voyage 3.5 Lite
voyage · voyage/voyage-3.5-lite
Voyage 4
voyage · voyage/voyage-4
Voyage 4 Large
voyage · voyage/voyage-4-large
Voyage 4 Lite
voyage · voyage/voyage-4-lite
Voyage Code 2
voyage · voyage/voyage-code-2
Voyage Code 3
voyage · voyage/voyage-code-3
Voyage Finance 2
voyage · voyage/voyage-finance-2
Voyage Law 2
voyage · voyage/voyage-law-2
FAQFrequently asked questions
Common questions
How many embedding models?
24 in the gateway catalog snapshot.
How does o10 route embedding workloads?
o10 State of Inference Spend 2026 found up to 638× compliant price spread across venues for identical workloads. Route each workload to the cheapest compliant model tier after shadow-mode proof.
Where is catalog pricing sourced?
Unified inference gateway catalog snapshot — confirm live rates with your provider before enforce mode.
o10Set the envelope. o10 holds it.
See what you're overpaying.
Paste a week of traffic. Get the number that books the audit.
See what you're overpaying →