PSTN / phone-number telephony for agents

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

Depot Pick

Twilio · 8.40/10 for this job (curated estimate, high confidence)

Distinct from `voice-agent-platform` (orchestration+STT+TTS). Here capability = numbers, regulatory, SIP, global reach. Confidence: high.

Runner-up

Telnyx · 8.39/10

Scores higher than the pick on: Price / performance, Developer & agent DX, Privacy / data retention, Lock-in risk (higher = worse).

When not to use the pick

Want an all-in-one voice-agent stack (Vapi/Retell) instead of raw telephony, or Telnyx pricing/regions fit better.

Lock-in / migration

Runner-up Telnyx has lower stored lock-in risk (3.8 vs 5.5, 0–10, higher = more lock-in).

Sourced price (usd_per_minute)

Pick's lowest sourced SKU: US local calls, to make calls (outbound PSTN) $0.014 (usd_per_minute) — source, as of 2026-10-19

Cheapest matching SKU: Plivo US local calls, to make calls (outbound PSTN) $0.0115 — source, as of 2026-10-19. Not the pick; not quality-adjusted.

Price history: first seen 2026-10-19 · 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

• Prompt injection: Compare each tool call to the original user task. If the call only makes sense given text that arrived from a fetched page, file, or message, stop and ask. Record which source the instruction came from. This catalog does not store payloads or attack steps.
• 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.
• Identity confusion: Bind every tool call to a user or tenant id. Refuse the call if that id changed mid-task. For a public bot, the operator owns the words the bot shows.
• Non-determinism: Run the task more than once and compare the end state, not a single transcript. Record the trial count next to any success rate you cite.
• Over-refusal: Log refusals separately from successes. Review a sample against the written policy. Do not treat a refusal as a pass, and do not weaken a safety check to raise the pass rate.
• Partial tool success: Require a per-item status and a failure count. Success for the task requires the failed count to be zero or explicitly handed to a retry queue.

Reported outcomes (submitted reports only)

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

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

Same-job, same-unit comparisons: Twilio vs Plivo

Cite: Agent Provider Depot, Depot Pick for agent-pstn-telephony: twilio, scores as of 2026-10-19. Agents: GET /api/decide?jtbd=agent-pstn-telephony