# Vespa (slim)

> Vespa is an open-source search engine from Vespa.ai AS for vector, text and hybrid retrieval with ranking, run self-hosted or on Vespa Cloud. Agents reach it through HTTP query and document APIs, the Vespa CLI and a Python client.

- Full: https://www.anchorterminal.com/tools/vespa.md (~6,800 tokens) · this version ~1,780 tokens · JSON https://www.anchorterminal.com/tools/vespa.json · canonical https://www.anchorterminal.com/tools/vespa
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

**BB · 70/100 · rank #157 of 842 · #4 in Retrieval & vector search · agent-ready · confidence medium**


Assessment: Vespa Cloud publishes hourly unit prices, a 99.5% uptime agreement for paying customers and a trial with $300 of credits and no card. Every call needs an application package deployed first, no OpenAPI file was found in the reviewed documentation, and Vespa.ai says it has no official public MCP server.

## Facts

- Kind: HTTP API · vendor: Vespa.ai AS · category: Retrieval & vector search · legal entity: Vespa.ai AS · provenance 84/100
- Local only (HTTP): pypi `pyvespa`
- Auth: OAuth or key · pricing: Pay per use · x402: no · licence: Apache-2.0 for the engine, the Vespa CLI and pyvespa. Vespa Cloud is a paid hosted service
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: Vespa Cloud's data-plane HTTP APIs (the query API at `/search/` and `/document/v1`) and the Vespa CLI. The same engine can be self-hosted under Apache-2.0
- Search modes: Approximate nearest-neighbour search on HNSW, text search with BM25 and other ranking signals, and both in one YQL query with multi-phase ranking, per the docs
- Filters: Structured filters in YQL combined with nearest-neighbour and text operators in the same query
- Update delay: The docs index says data is searchable in milliseconds after being fed. This is the vendor's statement, not measured by us
- Setup: An application package with a schema and `services.xml` must be deployed before any feed or query. `vespa deploy` targets a dev zone by default
- Auth: mTLS client certificates or bearer tokens on the data plane, each client limited to `read`, `write` or both. Tokens expire after 30 days by default
- Limits: No request rate limit published for Vespa Cloud. Tenant quota of $2 an hour on trial and $10 an hour on other plans. Query timeout defaults to 0.5s, `hits` is capped at 400 by default, document requests time out at 180s
- Errors: `/document/v1` documents 400, 404, 405, 412, 413, 429, 500, 503, 504 and 507. The query API documents its status codes and an error code mapping
- MCP server: No official public server. An optional component in the engine serves `/mcp/` from the user's own application with three search tools
- Clients: Vespa CLI (Go, Homebrew `vespa-cli`), pyvespa 1.2.8 for Python 3.10 to 3.13, and a Java feed client
- Hosted cost: Startup $0.05 a vCPU-hour, $0.005 a GB-hour of memory, $0.0002 a GB-hour of disk. Basic from $0.10, Commercial from $0.145, Enterprise from $0.18 a vCPU-hour
- Self-hosted cost: Free software. The owner pays for compute, memory and disk. A paid Self Managed support plan is priced on request
- SLA: 99.5% monthly uptime for paying customers, with service credits of 90 to 100 per cent of monthly fees. Claims must be filed within 7 days
- Status: status.vespa.ai on Instatus, with components for the console, infrastructure, enclave and each zone
- Sub-processors: AWS and Google for application data in customer-chosen zones, Auth0, Grafana, HubSpot and Atlassian, with Stripe for billing. List updated 12 August 2026
- Prices: Startup plan, one vCPU for an hour $0.05 per vCPU-hour; Commercial plan, one vCPU for an hour (initial price) $0.145 per vCPU-hour

- Scores: Reliability 80, Performance pending, Schema & documentation 58, Agent ergonomics 80, Security & auth 75, Payments & pricing 40, Task success pending, Maintenance & community 91, Transparency & trust 85 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, Graded as a hosted service, on Vespa Cloud. · Schema & documentation, No OpenAPI file or other machine-readable contract was found in the docs index of 384 pages (0). · Agent ergonomics, Responses can be sized with `hits`, `offset`, `presentation.summary` document summaries and `fieldSet` on document reads (20). · Security & auth, Data-plane clients authenticate with mTLS certificates or bearer tokens, each limited to `read`, `write` or both in `services.xml`. · Payments & pricing, Scored on Vespa Cloud, the paid hosted option. · Maintenance & community, Tag v8.763.13 is dated 29 September 2026 and pyvespa 1.2.8 reached PyPI on 1 October 2026, both within 30 days (30). · Transparency & trust, Apache-2.0 for the engine and clients (30).
- Sources: 28, open questions: 8, both in the full twin
- Capabilities: db.vector, db.hybrid, db.fulltext, db.filters
- JSON: https://www.anchorterminal.com/api/v1/tools/vespa.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/vespa.svg` or a link to https://www.anchorterminal.com/tools/vespa from a page on vespa.ai or one of its subdomains, or the README of github.com/vespa-engine/vespa, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Deploy an application package with a schema before feeding or querying. Use `vespa deploy` and wait for the endpoint to report ready
2. Send a token as `Authorization: Bearer` only to the endpoint marked Token. The mTLS endpoint needs the client certificate and key
3. Set `hits`, `offset` and `presentation.summary` on queries. `hits` is capped at 400 by default and the query timeout defaults to 0.5s
4. On 429 from `/document/v1` reduce the feed rate and back off. On 507 stop feeding, because the cluster is out of memory or disk
5. Use the `condition` parameter for test-and-set writes and expect 412 when it fails or the document is missing

## Connect

```bash
brew install vespa-cli
```

```bash
curl -H "Authorization: Bearer $TOKEN" $ENDPOINT
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/vespa

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Pinecone API + MCP | BB | 76.2 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/pinecone.min.md |
| Supabase API + MCP | BB | 75.6 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/supabase-mcp.min.md |
| Qdrant API + MCP | BB | 75.3 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/qdrant.min.md |
| Typesense API + MCP | BB | 70.7 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/typesense.min.md |
| Weaviate API + MCP | B | 67.9 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/weaviate.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)