AP
Agent Provider Depot
Opinionated picks for agents
OpenAPI
← All jobs

Enterprise RAG stack

Managed retrieval quality with rerank, security, and support.

At a glance — Oct 2026

Updated 2026-10-27 · forward this page: /jtbds/rag-enterprise#brief

Scores as of 2026-10-19 (8 days old).

Depot Pick
Cohere · 7.99/10 for this job (curated estimate, high confidence)

privacy + capability + maturity.

Runner-up
Pinecone · 7.85/10

Scores higher than the pick on: Capability fit, Latency / reliability, Developer & agent DX, Maturity / track record.

When not to use the pick
Simple app RAG on Postgres — use supabase-pgvector instead of a dedicated RAG vendor.
Lock-in / migration
The pick has lower stored lock-in risk than runner-up Pinecone (4.5 vs 7).
Sourced price (usd_per_million_input_tokens)

Pick: no sourced price in this job's unit (no_matching_sourced_price).

Cheapest matching SKU: Amazon Bedrock Gemma 3 4B $0.04 — source, as of 2026-10-03, re-checked 2026-10-27. Not the pick; not quality-adjusted.

Price history: first seen 2026-10-03 · last changed no change recorded · history JSON

Free option
No free resource lists this job. A cheap paid SKU is not a free option.
Failure modes to watch
  • Runaway spend: Set a budget and a tool-call cap per task. Alert when spend jumps. Stop the run at the cap instead of summarizing a partial trace as success.
  • Policy conflict: If cited sources contradict each other, return the conflict and the URLs. Do not pick a winner silently.
  • Stale retrieval: Store the source URL and the time it was fetched. If a newer canonical page exists, or two stored sources disagree, do not answer from the older one.
  • Ungrounded answer: Require a source URL or passage id on factual sentences. Drop or mark any sentence whose source does not contain the claim.
  • Confirmation skip: Gate those tool names on an approval id recorded before the call. A missing approval is a failure even if the downstream tool returns success.
  • Context overflow: If the input exceeds the window, say so and retrieve a narrower slice. Do not answer from a truncated head as if it were the whole source.
Reported outcomes (submitted reports only)

This job: loading… JSON · reports never change scores · seed/test records excluded

Depot Pick (Cohere) on this job: loading… JSON · reports never change scores · seed/test records excluded

Cite: Agent Provider Depot, Depot Pick for rag-enterprise: cohere, scores as of 2026-10-19. Agents: GET /api/decide?jtbd=rag-enterprise

All sourced prices, cheapest first · for support agents · for rag agents

Depot Pick

Cohere

privacy + capability + maturity.

Pricing (directional): Command/Rerank/Embed families; competitive enterprise RAG pricing; private deployment options.

Cite: Depot Pick for rag-enterprise: cohere
Overall
8.0
curated_estimate
confidence: high · as of 2026-10-19
Capability fit
7.8
Price / performance
8.0
Latency / reliability
8.4
Developer & agent DX
7.8
Privacy / data retention
8.6
Lock-in risk (higher = worse)
4.5
Maturity / track record
8.8

Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.

Sources: Cohere: https://cohere.com · Cohere docs: https://docs.cohere.com

Use for retrieval stacks (embed+rerank), not as your primary agent brain. Quietly excellent at enterprise RAG.

Quote for Enterprise RAG stack

Depot Pick stays Cohere. Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=rag-enterprise

Only 1 candidate has a sourced input $/1M; nothing was compared, so pickIsPriceWinner is null.

  • Command (legacy) usd_per_million_input_tokens $1 source as of 2026-10-03
  • Command-light (legacy) usd_per_million_input_tokens $0.3 source as of 2026-10-03
  • Command (legacy) usd_per_million_output_tokens $2 source as of 2026-10-03
  • Command-light (legacy) usd_per_million_output_tokens $0.6 source as of 2026-10-03

6 of 8 candidates have no sourced price row. 7 are excluded from the Input $/1M comparison (chat_completion_input). min sourced input SKU among candidates; not quality-adjusted

Runners-up

When NOT to use the top pick

Simple app RAG on Postgres — use supabase-pgvector instead of a dedicated RAG vendor.

Full ranking (score table)

Ranked with this JTBD's weights. Scores are curated estimates unless marked otherwise. Agents: prefer /api/decide then this table for tie-breaks.

#ProviderOverallFit$/perfLatencyDXAs of
1Weaviate8.28.87.58.48.22026-09-14
2Elasticsearch Serverless8.19.06.89.07.62026-09-14
3CohereDepot Pick8.07.88.08.47.82026-10-19
4Amazon Bedrock7.98.86.09.26.82026-09-14
5Pinecone7.89.06.29.08.82026-09-14
6AI21 Labs7.57.67.28.27.22026-09-14
7Snowflake Cortex7.27.85.58.47.02026-09-14
8Databricks Mosaic AI7.28.44.88.56.82026-09-14

Score methodology for this job

privacy + capability + maturity.

  • capabilityFit: 20%
  • pricePerformance: 12%
  • latencyReliability: 12%
  • developerDx: 12%
  • privacyPosture: 25%
  • lockInRisk: 9%
  • maturity: 10%