# Mojeek Web Search API vs Parallel Search and Task APIs (slim)

> Parallel Search and Task scores 75 (BB) to Mojeek Web Search's 36.4 (F) for web search. Parallel Search and Task is cheaper for web search, $1 against $2.68 per 1,000 requests. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/mojeek-vs-parallel-search-api.md (~6,000 tokens) · this version ~3,180 tokens · JSON https://www.anchorterminal.com/compare/mojeek-vs-parallel-search-api.json · canonical https://www.anchorterminal.com/compare/mojeek-vs-parallel-search-api
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Parallel Search and Task APIs scores 75 (BB) on agent readiness against Mojeek Web Search API's 36.4 (F), and leads in 6 of 7 scored categories. Both do web search. Parallel Search and Task APIs is cheaper for web search, $1 against $2.68 per 1,000 requests.

- Mojeek Web Search API: F 36.4, rank #1387 of 1510 · https://www.anchorterminal.com/tools/mojeek.min.md
- Parallel Search and Task APIs: BB 75, rank #73 of 1510 · https://www.anchorterminal.com/tools/parallel-search-api.min.md
- Mojeek Web Search API, good for Agents and products that want a second, independent index beside Google-derived results, or European data handling with no sub-processors.
- Parallel Search and Task APIs, good for Agents that mix quick search with long research or enrichment jobs and want one vendor and one bill. Ahead on Reliability, 75 against 45; Schema & documentation, 94 against 29; Agent ergonomics, 87 against 66; Security & auth, 45 against 15; Payments & pricing, 75 against 20; Maintenance & community, 87 against 10. Also Cheaper for web search, $1 against $2.68 per 1,000 requests; Agent-ready, a grade of BB or better; A hosted endpoint, with nothing to install.

| Category | Mojeek Web Search API | Parallel Search and Task APIs |
| --- | --- | --- |
| Reliability (16%) | 45 | 75 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 29 | 94 |
| Agent ergonomics (13%) | 66 | 87 |
| Security & auth (14%) | 15 | 45 |
| Payments & pricing (10%) | 20 | 75 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 10 | 87 |
| Transparency & trust (7%) | 68 | 65 |

| Fact (where they differ) | Mojeek Web Search API | Parallel Search and Task APIs |
| --- | --- | --- |
| Vendor | Mojeek Limited | Parallel Web Systems |
| Hosted endpoint | no (local only) | `https://api.parallel.ai/v1/search` |
| Transports |  | HTTP, Streamable HTTP |
| Auth | API key | OAuth or key |
| Pricing | Pay per use | Freemium |
| Price for web search | $2.68 per 1,000 requests | $1 per 1,000 requests |
| x402 | no | payer tooling only |
| Tools exposed | 0 | 6 |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| MCP registry | not listed | `ai.parallel/search-mcp` |
| Last release | none | 2026-10-28 |
| Terms last updated | no date given | 2026-10-17 |
| Privacy policy last updated | 2022-02-02 | 2026-08-11 |
| Customer content may train models | not found in the text | yes |
| Terms or service can change without notice | yes | not found in the text |
| Popularity | none | 28 stars, 250k npm/wk, 994k PyPI/wk |
| Agent reviews | none | 3.6/5 (8) |

Why the edge:
- Maintenance & community, Parallel Search and Task APIs +77: Mojeek Web Search API 10 (Read for a closed service. No API changelog, release notes or dated API change were found, and the blog's posts since 2024 are about search in general, so the last change can't be dated (0). No dated changes in the 90 days from 8 August (0). A staff member answered API questions on the community forum within a day in December 2025 and October 2026, and support is by email; no public changelog (10 of 15). No official SDKs or MCP server (0). No public packages or CI to measure (0). 0 + 0 + 10 + 0 + 0 = 10.); Parallel Search and Task APIs 87 (parallel-web 1.3.7 for Python on 2026-10-23 and for TypeScript on 2026-10-28, and changelog entries on 19 and 26 October, the second launching the Decisions API (30). Counted from the tags and the changelog, the 90 days from 3 August hold Python SDK releases 1.3.1 to 1.3.7, TypeScript 1.3.1 to 1.3.7 and ten changelog entries from 19 August to 26 October (20). The SDK releases since 1.3.5 are dependency bumps. Closed service with a changelog and support@parallel.ai. We didn't test whether support answers (12). Current Python and TypeScript SDKs, and ai.parallel/search-mcp and ai.parallel/task-mcp in the official registry (15). The Python SDK runs lint and build in CI on push, plus a workflow that detects breaking changes (10).)
- Schema & documentation, Parallel Search and Task APIs +65: Mojeek Web Search API 29 (No OpenAPI or other machine-readable contract (0). No llms.txt (404) and no Markdown pages for agents (0). The parameters page states what each parameter does, with notes on when not to use `reg` and `clufmt`, but nothing on when another endpoint fits better (12 of 20). Every parameter has a type, defaults and valid ranges (tlen 0 to 127, dlen 0 to 511, rbb and lbb 1 to 100, up to 25 domains), though `reg` is called an enum without listing its values (11 of 15). One curl example and annotated JSON and XML response formats; errors appear only as a `status` string with one example (6 of 15). No API version, changelog or dated release notes, and the quickstart and the parameters page give different hosts (0). 0 + 0 + 12 + 11 + 6 + 0 = 29.); Parallel Search and Task APIs 94 (Public OpenAPI at docs.parallel.ai/public-openapi.json, linked from llms.txt (25). llms.txt and Markdown pages (10). A live `tools/list` on search.parallel.ai/mcp on 17 October and again on 1 November returned the two definitions, and the newer Parallel MCP server at mcp.parallel.ai adds `web_decisions`, whose description says when to use web_search instead. `web_search` states its purpose and ideal uses, and `web_fetch` says to use it "only when web_search excerpts are insufficient". The docs add that domain filters are hard filters that can cut quality. `web_search` has no when-not-to line of its own (17). Typed JSON Schema inputs with required fields and an output schema on both tools, `mode` is an enum in the API, and Task output schemas are JSON Schema. The MCP inputs carry no enums (12). The errors page lists each code with whether to retry and what to do, and 422s carry a structured `detail` (15). A dated changelog, newest entry 26 October 2026 (Decisions API) after 19 October (EU data residency), and beta headers retire on dated entries (15).)
- Payments & pricing, Parallel Search and Task APIs +55: Mojeek Web Search API 20 (No x402, MPP or L402 (0). Per-request prices published without login, £2 and £3 per 1,000 requests (20). The FAQ says a free credit comes with the Startup plan, but a bank card is required to open an account (0). A person signs up in a browser and adds a card (0). 0 + 20 + 0 + 0 = 20.); Parallel Search and Task APIs 75 (Parallel runs a separate gateway at parallelmpp.dev that takes x402 (USDC on Base) and MPP (Stripe or Tempo) for search and extract at $0.01 and an ultra task at $0.30. Our unpaid POST to /api/search on 6 October returned 402 with an x402 v2 challenge for 10000 base units on eip155:8453 and a Tempo MPP challenge. Nothing on api.parallel.ai, and the gateway sells one price per endpoint with no mode choice, so partial (25). Per-unit prices published without login (20). Up to 5,000 free requests a month, $5 monthly credit and up to $80 at signup on the pricing page, which still doesn't say whether a card is needed (10). The hosted Search MCP works with no key, and the gateway needs only a wallet (20).)
- Reliability, Parallel Search and Task APIs +30: Mojeek Web Search API 45 (Read with the hosted lines. status.mojeek.com is a Site24x7 StatusIQ page with Search, Website, Blog and Community components. It is drawn by script, so only its RSS feed could be read, which shows each component's current state (Search operational since 7 September 2026) and no incident entries (15 of 20). No readable incident history (5). Rate limits are published per plan, 5 a second and 100,000 a day on Startup, 10 a second and 400,000 a day on Business (15). Over the daily limit the JSON `status` reads 'ERROR: Daily Limit Reached'; no HTTP 429, Retry-After or backoff guidance was found (0). No SLA, and the API terms say the service is provided as is and may be interrupted without notice (0). Generally available, with only the `lr` parameter marked beta (10). 15 + 5 + 15 + 0 + 0 + 10 = 45.); Parallel Search and Task APIs 75 (incident.io page at status.parallel.ai with Search, Task, Chat, Monitor, FindAll and Entity Search components and history (20). The feed, re-read on 1 November, has nothing after 13 October, so the 90 days from 3 August hold the same four incidents, all partial or degraded. Elevated 503s on 6 August, about an hour of Task API latency on 2 September, intermittent 4xx errors on 7 September, and transient 502s from the network gateway on 13 October, degraded performance from 01:23 to 01:43 UTC. Most have no duration listed (20). Published limits, 600 a minute for Search, Image Search, Extract, Decisions and Entity Search, 2,000 for Tasks, 300 for Chat and Monitor (15). The errors page marks 429 as retryable with exponential backoff, but there's no `Retry-After` and no idempotency guidance for creating Task runs, which the SDKs retry twice by default (10). No SLA found (0). Search, Extract and Task are GA (10).)
- Security & auth, Parallel Search and Task APIs +30: Mojeek Web Search API 15 (One key per account, documented only as the `api_key` query parameter, and rotation or revocation is by email to the API team (a staff reply of 22 October 2026 on the community forum asks for the key's last 8 digits). One all-powerful key (10) less 10 for the key in the URL (0). Search is read-only and there is nothing to write, but no scoped or restricted key (10 of 20). Results are third-party titles and snippets, with no prompt-injection guidance found (0). No audit log or per-call usage view was found in the docs; the FAQ mentions budget alerts on the account (0 of 15). security.txt names security@mojeek.com, with no Expires field. No bug bounty, disclosure policy, SOC 2 or ISO 27001 found; the API page claims compliance with European rules such as the EU Data Act without a certification (5 of 20). 0 + 10 + 0 + 0 + 5 = 15.); Parallel Search and Task APIs 45 (API key in `x-api-key`. The Search MCP takes a Bearer key or OAuth at /mcp-oauth. We found no key scopes (20). Every Search and Extract action is a read, and Task tools live in a separate MCP server, so the search server is a read-only subset (15). Excerpts and fetched pages are untrusted web text, and the docs index has no prompt-injection guidance (0). No audit log found (0). The privacy policy shows a SOC 2 badge and links trust.parallel.ai, which rendered only its title to our reader on 6 October. security.txt is 404 on parallel.ai and docs.parallel.ai, and no bug bounty found (10).)
- Agent ergonomics, Parallel Search and Task APIs +21: Mojeek Web Search API 66 (Responses can be sized with `t` (up to 10, 40 or 100 results by plan), `tlen`, `dlen` and opt-in date and size fields (22 of 25). `s` for paging, `since` and `before`, `site`, included and excluded domains, region and language boosting and safe search (20). Errors are a free-text `status` with no documented codes, which an agent can't branch on reliably (5 of 20). Searches only read, so a retry is safe, but no page says whether failed or empty requests are billed (12 of 20). Only `q` and `api_key` are required, with recommended values for the boosts. No official SDK in any language (7 of 15). 22 + 20 + 5 + 12 + 7 = 66.); Parallel Search and Task APIs 87 (The Search MCP has two tools, about 5,700 characters of names, descriptions and input schemas on 1 November, and the Parallel MCP server lists three without a key (about 9,700 characters) and a fourth, `web_research`, after sign-in. `web_fetch` returns excerpts unless `full_content` is set, and the docs cap excerpts at roughly 25,000 characters a call and warn full pages can run to tens of thousands of tokens (25). Result counts, excerpt settings and source policies for domains and paths (18). The errors table gives each code a retry column and a resolution, with troubleshooting for 402 and 429 and a structured `detail` on 422 (20). Both Search MCP tools carry readOnlyHint true, destructiveHint false and idempotentHint true in the live `tools/list`, and searches are safe to repeat. There's still no idempotency key for Task creation, the SDKs retry creates on 429 and 5xx, and the Task MCP needs a key, so its annotations weren't read (14). Python and TypeScript SDKs, but `mode` defaults to advanced, the $5 per 1,000 tier, when you leave it out (10).)