Salesforce Models API
Researched 3d agoPlatformTier 2Salesforce
Salesforce Models API offers 10 tracked models (0 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.
Covers 7 workload areas across 10 tracked models; last verified 2026-10-13.
Use it for
- Operators routing coding, rag, and agents workloads through this API
Do not use it for
- Final benchmark picks without opening the relevant model detail page
- Strict price-per-token comparisons until output pricing is sourced
Tracked models
10
Models available through this provider
Priced output routes
0
Output pricing not yet tracked
Cheapest output
Unknown
Output pricing not yet tracked
Batch-ready models
0
No batch pricing tracked
Latest model release
2026-06-30
108d since newest release
Freshness
2026-10-13
Researched 3d ago
Information
Salesforce provides access to large language models inside its CRM platform. Through the Models API, Apex and REST calls reach Salesforce-managed models hosted on OpenAI, Azure OpenAI, Amazon Bedrock and Google Vertex AI, or a customer's own model connection. Usage is metered in Einstein Requests rather than per-token prices.
Where this host wins
- Coding: 3 tracked models with SWE-bench / HumanEval-style scores.
- RAG: 3 tracked models with ruler / needle retrieval benchmarks.
- Agentic: 3 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 3 tracked models with context-token or InfiniteBench-class signal.
Getting started
Platform Overview
The Models API sends prompts from Apex or REST to Salesforce-managed models or to bring-your-own models. Requests pass through the Einstein Trust Layer, and with data masking on, context is limited to 65,536 tokens. Each call consumes Einstein Requests: total input and output tokens divided by 2,000 and rounded up, then multiplied by a usage-type multiplier.
Available Models(10)
View all →All models available as Serverless
Contact provider for pricing