Salesforce Llama Rank V1 (8B)
APISalesforce Llama Rank V1 (8B) is a rerank model from salesforce with a 8K-token context window. Provider list price is $0.10 per M tokens; on Allocate you pay $0.11 with the 7% transaction fee. It is a closed model served over API; the weights are not published.
Pricing
Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.
Salesforce Llama Rank V1 (8B) is served over API. Route traffic to it by name, meter every token, and swap it out in one click when a better fit ships.
Example usage
Point a route at salesforce/llama-rank-v1 and the endpoint never changes; swap the model behind it whenever you want.
curl https://api.allocate.network/v1/chat/completions \ -H "Authorization: Bearer $ALLOCATE_KEY" \ -d '{ "model": "salesforce/llama-rank-v1", "messages": [{"role": "user", "content": "Summarise the attached contract."}] }'
Common questions
How much does Salesforce Llama Rank V1 (8B) cost?
Provider list price is $0.10 per M tokens. On Allocate you pay list plus the 7% transaction fee: $0.11.
What context window does Salesforce Llama Rank V1 (8B) have?
8,192 tokens (8K). At roughly 0.75 words per token, that is about 6k words of English text per request.
Can I fine-tune Salesforce Llama Rank V1 (8B)?
No. Salesforce Llama Rank V1 (8B) is a closed model served over API; the weights are not published. If you want a model you can train and own, start from an open-weights base in the catalog and fine-tune that.
How do I call Salesforce Llama Rank V1 (8B) on Allocate?
Send salesforce/llama-rank-v1 in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.