Codex vs FRED API

Codex 80

Closed service. Newest changelog entry 2 November 2026 (30). Weekly entries from 3 August to 2 November, and SDK releases 2.5.10 to 2.5.20 between 28 October and 5 November (20). Public changelog, a Discord, a support address and a status page with a report link; GitHub issue replies were not sampled (10 of 15). Current official TypeScript SDK, no other languages (12 of 15). The SDK repository runs lint and test on pull requests and a release workflow (8 of 10). 30+20+10+12+8 = 80.

FRED API 15

The last dated API change found is the version 2 launch on 4 November 2025, 339 days before the check (0 of 30). The FRED News feed carries eight posts in the last 90 days, four of them data additions and none an API change, so half credit (10 of 20). A public news feed and a contact form, with no developer forum or issue tracker found (5 of 15). No official SDK (0 of 15). No package to judge (0 of 10). The official MCP connector is recent but its launch date was not found, so it earns nothing here. Total 15.

Codex 91

The full GraphQL schema, 18,159 lines, is in the MIT SDK repository at src/resources/schema.graphql, updated on 5 November 2026, and introspection is free (25). llms.txt, llms-full.txt and a Markdown twin of every page (10). Reference pages give a one-line purpose per operation, and the API reference intro, the queries-versus-subscriptions page and llms.txt say which operation to use for which job and to batch rather than loop (13 of 20). GraphQL types with enums, input objects and non-null markers, and documented maxima per argument (14 of 15). Examples on every recipe and reference page, and an error table with code, HTTP status, meaning and retry advice (14 of 15). Weekly dated changelog from 26 August 2024 to 2 November 2026 with RSS and dated deprecations (15). 25+10+13+14+14+15 = 91.

FRED API 43

No OpenAPI or other machine-readable contract was found in the docs (0). fred.stlouisfed.org/llms.txt returns 404 (0). Each of the 31 version 1 requests has a description and a parameter list, and real-time periods have their own page, with little on when to choose one request over another (12 of 20). Parameters state type, range, default and allowed values in prose, such as nine units values and limit between 1 and 100,000 (12 of 15). Each page shows example requests and responses in XML and JSON, and the errors pages list status codes with sample bodies (12 of 15). Version 2 has its own path and a dated launch note, version 1 has no version in its path, and there is no API changelog (7 of 15). Total 43.

Codex 85

Hosted lines. Status page at status.codex.io (incident.io) with API, Dashboard and 25 network components and a history page (20). The history from 8 August to 6 November lists an elevated-latency incident on 11 August (balances queries, 42 minutes, labelled degraded performance), a 5xx spike the same day, degraded filterTokens on 12 August, and network delays on Robinhood, BNB, Cronos, Fogo and Solana pricing in late August and September, with none in October or November. All read as partial or degraded, so minor only (20). Per-plan rate limits (5 a second free, 300 on Growth with a 500 burst) and per-request maxima are published (15). 429 TOO_MANY_REQUESTS carries retryAfterSeconds and Retry-After, OVER_CAPACITY says to wait 30 seconds, and the errors page says which codes to retry; writes are limited to webhook and token mutations (15). The pricing page shows '99.9% Uptime SLA' as a headline figure and custom SLAs on Enterprise, with no SLA document found (5 of 10). The API is generally available (10). 20+20+15+15+5+10 = 85.

FRED API 38

Graded as a hosted API. No status page was found in the API docs, the FRED footer or the help pages (0), so there is no incident history to read (5). Rate limits are published, 120 requests a minute on version 1 and two a second on version 2 (15). The errors pages document 429 and warn of a temporary block, with no Retry-After header or backoff guidance. Every request is a read (8 of 15). No SLA, and the terms disclaim availability (0). Both versions are published without a beta label (10). 0 + 5 + 15 + 8 + 0 + 10 = 38.

Codex 80

MPP (Machine Payments Protocol) on every query endpoint, paid in USDC on Tempo; subscriptions and webhooks are not covered, and it is not x402 (35 of 40). $0.001 a query through MPP, compute-unit costs per operation, and Growth at $120 per million compute units, all public (20). The Almost free plan's 10,000 compute units need a one-time $1 activation fee by card or 1 USDC, which the terms say confirms a payment method (5 of 20). An agent can pay per query with no account or key (20). 35+20+5+20 = 80.

FRED API 40

No x402, MPP or L402 (0). Free, stated publicly, with nothing to buy (20). No card (20). A person has to create a FRED account and request the key in a browser (0). Total 40.

Codex 49

Secret API keys in a header, never in the URL. Short-lived tokens from createApiTokens with an expiry and a request limit, per-key compute-unit limits and key deactivation. No scopes (22 of 30). The surface is mostly reads; mutations create webhooks and short-lived tokens. No read-only key (12 of 20). Token names, symbols, social links and community notes come from token deployers and other sources, and the docs warn tokens may be scams, with no prompt-injection guidance (5 of 15). The dashboard usage page breaks compute units down by operation, apiUsage reports the period's use and usageData the cost of each request (10 of 15). security.txt returns 404, and no disclosure policy, bug bounty or certification was found on the site or docs (0 of 20). 22+12+5+10+0 = 49.

FRED API 35

One 32-character key for each application, with no scopes. Version 1 documents the api_key query parameter as its only method, so the secret travels in the URL, and version 2 moves it to a bearer header. Key deletion or rotation sits behind the account login and was not seen (20 less 10, 10 of 30). The API is read-only (15 of 20). Responses are curated statistics with series notes written by FRED or its sources (10 of 15). No request log or usage view was found (0 of 15). security.txt returns 404 on fred.stlouisfed.org and api.stlouisfed.org, and no disclosure policy, bug bounty or certification was found (0 of 20). Total 35.

Codex 79

GraphQL field selection, so a response holds only the fields asked for, and usageData reports the cost of a request (23 of 25). limit on filter queries up to 200, rankings and 100+ filter signals on filterTokens; some list arguments drop extra inputs silently rather than failing (18 of 20). Coded errors an agent can branch on, but most arrive as HTTP 200 in an errors array, and an inline input type mismatch returns only a message (16 of 20). Queries are reads and identical requests cost the same; errors are not billed except NOT_FOUND. No idempotency key on the webhook and token mutations (14 of 20). Few required arguments beyond networkId. One official SDK, TypeScript (8 of 15). 23+18+16+14+8 = 79.

FRED API 68

limit, observation_start, observation_end, frequency aggregation and units size an observations response, with no field selection and defaults of 100,000 and 500,000 observations (15 of 25). limit and offset, cursor paging on version 2, order_by, filter_variable and tag filters (18 of 20). Errors carry a status code and a message naming the failing variable, in a short list of codes (13 of 20). All requests are GETs and safe to retry (15 of 20). An observations call needs only series_id and the key, but version 1 answers in XML unless file_type=json is set, and no official SDK was found (7 of 15). Total 68.