OpenRouter text-embedding-3-smallPricing & API costs
Small embedding model
Input token limit
8,192 tokens
Output format
Embedding vector
Release date
2025-10-30
API model ID
openai/text-embedding-3-smallModel overview
Understand the model before estimating your workload.
Use the model ID openai/text-embedding-3-small through OpenRouter. The prices and limits on this page apply to that specific listing, with source data checked on 2026-10-12.
OpenRouter text-embedding-3-small accepts up to 8,192 input tokens within the published context limit. It returns an embedding vector rather than a generated text response. Vector dimensions describe the size of that output and are separate from the input token limit. Split longer inputs to stay within the provider's request limits.
This listing covers text-embedding-3-small through OpenRouter. Its model ID and rates belong to that channel. Check routing and endpoint availability before treating a direct API and a routed call as interchangeable.
Pricing
Rates are grouped by usage type and available tier.
Per 1M tokens
Input
$0.02
Output
$0.00
Batch pricing
OpenRouter has separate batch model IDs; those rates are not included in the standard listing.
How billing works
The details that turn a token rate into an actual bill.
Input tokens and vector output
OpenRouter text-embedding-3-small converts your input into embedding vectors. Use the listed input rate and the provider's reported input token count to estimate spend. Vector dimensions describe output size; they are not generated text tokens.
A missing rate is not free usage
If a price, discount, or limit is marked not published, confirm it with the provider before estimating spend. The calculator does not invent a separate cache discount when no cached-input rate is available.
Check discounts and rate tiers
No batch multiplier is applied to the examples on this page. Check the pricing source before assuming an asynchronous job receives a discount. Review the provider's pricing terms for workload-specific conditions.
Account for the complete workflow
Retries, follow-up calls, and agent tool loops increase request counts. Search, storage, and other tool charges can be billed separately from model inference. Use actual API usage logs to calibrate a budget before scaling traffic.
Capabilities and limits
What the API supports and where limits apply.
- Provider
- OpenRouter
- Model type
- Embedding
- Family
- gpt
- Access
- OpenRouter
- Modalities
- Text · Embedding
- Input token limit
- 8,192 tokens
- Output format
- Embedding vector
- Released
- 2025-10-30
- Deprecation date
- Not announced
Compare API channels
Check the model ID, rate, and limit for each access route.
The same model can have a different ID, price, or output limit depending on how you access it. These are the channels currently tracked in this catalog; they are not a complete list of every hosting provider.
Text: $0.02 input / 1M tokens
$0.02 input · $0.00 output / 1M tokens
Sources
Official pages and the date this information was checked.
- Last checked
- 2026-10-12
- Source links
- 2
Next step
Browse related models from this provider.
Frequently asked questions
OpenRouter pricing checked on 2026-10-12: $0.02 input · $0.00 output / 1M tokens. These are OpenRouter channel rates; a different endpoint may have different pricing.
OpenRouter text-embedding-3-small accepts up to 8,192 input tokens within the published context limit. It returns an embedding vector rather than a generated text response. Vector dimensions describe the size of that output and are separate from the input token limit. Split longer inputs to stay within the provider's request limits.
The recorded status is Active. Use the exact model ID openai/text-embedding-3-small and confirm that your API account has access.
Recent updates
Added to the model directory.
View sourceModel details changed in the provider's documentation.
View source