# AX Check: vonage.com
Checked 2026-09-29.

Vonage pricing is clear, but its llms.txt skips developer docs.
13 of 23 checks passed: quickstarts and pricing are directly readable, but llms.txt indexes only marketing content, not APIs or docs.

## Onboarding needs a login

## Coding sessions
All three independent sessions (DeepSeek V4.1 Flash, Kimi K3, Qwen 3.8 Max) completed successfully, each producing per-message and per-minute pricing broken down by channel with clearly stated assumptions like destination country and message segmentation, no login wall encountered.

### DeepSeek V4.1 Flash
[View public run](https://agents.withgauge.com/p/runs/739337d4-9492-4541-ba20-691507b83729) · [Read transcript](https://www.ax-check.com/vonage.com/sessions/deepseek.json)
Final output gives per-message/pay-as-you-go pricing broken down by channel (SMS/MMS, Messages API, Messenger ~$0.0011/msg) and names assumptions like destination country/carrier rate variance, free signup credit/sandbox, and setup minimums for some channels.
#### End-to-end onboarding
- **End-to-end onboarding not demonstrated**: The agent never obtained or used real Vonage credentials. It confirmed the sandbox had no VONAGE_API_KEY/SECRET set, and both example scripts were designed to fall back to a local 'dry-run' that only prints the request it would make, without ever calling the real hosted API. No authenticated operation against Vonage was demonstrated.
  Event 6:

  ```text
  ---ENV---
  ---keys check done---
  ```
  Event 64:

  ```text
  [dry-run] No VONAGE_API_KEY / VONAGE_API_SECRET set.
  [dry-run] Would POST https://rest.nexmo.com/sms/json
  ```
  Event 77:

  ```text
  No Vonage credentials exist in this environment, so I could not execute a real send or verify actual delivery. That's the only blocker.
  ```

#### Hallucinated URLs
None identified in this transcript.

#### Blockers
- **No Vonage account credentials available in sandbox**: The session environment had no VONAGE_API_KEY, VONAGE_API_SECRET, VONAGE_APPLICATION_ID, or private key. This is a test-environment limitation (missing human-supplied credentials), not a product defect. The agent worked around it by shipping a dry-run mode rather than getting blocked entirely.
  Event 6:

  ```text
  ---ENV---
  ---keys check done---
  ```
  Event 77:

  ```text
  No Vonage credentials exist in this environment, so I could not execute a real send or verify actual delivery. That's the only blocker.
  ```

#### Suggested Changes
None identified in this transcript.

### Kimi K3
[View public run](https://agents.withgauge.com/p/runs/82ccd11c-ea6d-40dd-8315-f5819c697db7) · [Read transcript](https://www.ax-check.com/vonage.com/sessions/kimi.json)
Final output gives per-message/per-minute pricing (e.g. $0.005–0.01/SMS to US, ~$0.01–0.03/min voice) with named assumptions: destination country, message segmentation, number rental (~$1/mo), and trial credit limits on sender ID.
#### End-to-end onboarding
- **Onboarding needs a login**: Agent never obtained real Vonage credentials. It only tested the unauthenticated API endpoint and a deliberately fake key/secret pair, which returned a 'Bad Credentials' error as expected. Signup requires phone-number verification which the agent could not complete, so it stopped and asked the human to supply real API_KEY/API_SECRET values.
  Event 26:

  ```text
  I can't get credentials. Vonage has a real developer workflow (REST API, SDKs for Node/Python/etc., ~€2 free trial credit), but signup at dashboard.nexmo.com requires an email and phone-number verification, which I can't complete.
  ```
  Event 19:

  ```text
  {"message-count":"1","messages":[{"status":"4","error-text":"Bad Credentials"}]}
  ```
  Event 26:

  ```text
  If you drop VONAGE_API_KEY/VONAGE_API_SECRET into the environment, the example will run immediately. Per your instruction, I'm stopping here rather than pretending further.
  ```

#### Hallucinated URLs
None identified in this transcript.

#### Blockers
- **Vonage signup requires phone verification, blocking self-service credentials**: The agent could not create a Vonage account because dashboard signup requires email plus phone-number verification, which it cannot complete autonomously. This is a normal product security control, not a defect, but it fully blocked any authenticated use of the SDK/API in this session.
  Event 26:

  ```text
  signup at dashboard.nexmo.com requires an email **and phone-number verification**, which I can't complete. There's no anonymous sandbox.
  ```

#### Suggested Changes
None identified in this transcript.

### Qwen 3.8 Max
[View public run](https://agents.withgauge.com/p/runs/582097d6-fc7a-469a-9472-95e84db339c9) · [Read transcript](https://www.ax-check.com/vonage.com/sessions/qwen.json)
Final output gives per-service pricing (SMS ~$0.005-$0.10, Voice per-minute, Verify ~$0.05-$0.10, numbers ~$1-3/mo) and names assumptions (pay-per-use, per-country variance, 153-char SMS segments, free trial ~€2 credit with verified-number restriction).
#### End-to-end onboarding
- **Onboarding needs a login**: The agent never obtained Vonage credentials on its own. It checked the environment for VONAGE/NEXMO variables, found none, and the SMS script it wrote failed at a manual credential check. No account signup or key retrieval was attempted or completed; the agent explicitly says it cannot create an account or verify a phone number itself. No authenticated API call to the real Vonage service ever happened.
  Event 3:

  ```text
  env | grep -i -E "vonage|nexmo"
  ```
  Event 18:

  ```text
  Missing VONAGE_API_KEY / VONAGE_API_SECRET. Set them and retry.
  ```
  Event 24:

  ```text
  No Vonage credentials exist in this environment**, so I can't execute a live send. Getting them requires creating an account at dashboard.nexmo.com (signup + phone verification), which I can't do for you.
  ```

#### Hallucinated URLs
None identified in this transcript.

#### Blockers
- **No Vonage API credentials available in sandbox**: The example script requires VONAGE_API_KEY and VONAGE_API_SECRET, which do not exist in the environment and require human signup plus phone verification at the Vonage dashboard. This is a normal credential/login requirement, not a product defect, and it stopped the agent from making a live API call.
  Event 18:

  ```text
  Missing VONAGE_API_KEY / VONAGE_API_SECRET. Set them and retry.
  ```
  Event 24:

  ```text
  Getting them requires creating an account at dashboard.nexmo.com (signup + phone verification), which I can't do for you.
  ```
- **SDK package.json subpath not exported under ESM**: A diagnostic command tried to read @vonage/server-sdk/package.json via require() inside an ESM context, which Node rejected because the package's exports map doesn't expose that subpath. This was an agent scripting error (mixing require with ESM), not a Vonage product bug, and did not block the main script from working correctly.
  Event 18:

  ```text
  Error [ERR_PACKAGE_PATH_NOT_EXPORTED]: Package subpath './package.json' is not defined by "exports" in /sandbox/repo/node_modules/@vonage/server-sdk/package.json
  ```

#### Suggested Changes
None identified in this transcript.

### Task given to each agent
Help me build a simple example using Vonage. Tell me how pricing works, and briefly tell me whether this product will be easy for you to manage. Let me know if you get blocked. If this product has no developer workflow you can act on, say so plainly and stop. Stay light: use the hosted product through its SDK or API. Do not start local service stacks or wait for long-running commands; if the quickstart requires either, say so plainly and stop.

No product credentials were supplied and no purchases were authorized.

## Score: C · 63/100 (provisional)
Grades come from completed site checks. Coding sessions and skipped checks do not affect the score.

### Clarity
- **Failed** — Homepage answers Markdown requests

  ```text
  Homepage returned text/html for a Markdown Accept header; no Markdown representation offered.
  ```

- **Failed** — llms.txt provides an actionable documentation index

  ```text
  llms.txt exists but indexes only resources, publications, customers, webinars and articles, not developer docs or APIs.
  ```

- **Failed** — llms.txt provides navigation guidance

  ```text
  llms.txt lists marketing content only, with no starting guidance or navigation toward developer documentation.
  ```

- **Failed** — llms.txt mentions offered API, MCP, and skills

  ```text
  llms.txt never mentions the offered APIs, SDKs, CLI or MCP surfaces.
  ```

- **Pass** — A compact guide representation exists

  ```text
  llms.txt served as text/plain markdown with discovery files and organized resource links.
  ```

- **Pass** — A focused guide is directly retrievable

  ```text
  Getting Started with SMS guide fetched directly, listing prerequisites, app creation and webhook setup.
  ```

- **Pass** — Equivalent instructions fit a token budget

  ```text
  SMS quickstart is 995 tokens, well under the 8000-token budget.
  ```

- **Skipped** — Product-docs links survive format changes

  ```text
  Homepage Markdown unsupported, so link preservation across formats cannot be measured.
  ```

- **Pass** — The compact guide is independently actionable

  ```text
  SMS quickstart gives concrete steps: dashboard settings, create Application, configure webhooks, further reading.
  ```

- **Pass** — Install and next-step links resolve

  ```text
  Fetched quickstart and API reference pages returned HTTP 200 with usable content.
  ```


### Onboarding
- **Pass** — Docs lead to a relevant quickstart

  ```text
  SMS and Facebook getting-started guides give concrete setup steps from the docs index.
  ```

- **Skipped** — Installation commands are extractable

  ```text
  Fetched pages show dashboard setup steps but no install commands for a package or CLI.
  ```

- **Skipped** — Code examples are available without interaction

  ```text
  Fetched getting-started pages contain no code examples, only dashboard configuration steps.
  ```

- **Pass** — Prerequisites and auth boundaries are explicit

  ```text
  SMS guide states prerequisites: dashboard account, create Application for credentials, configure webhooks.
  ```


### Pricing
- **Pass** — Pricing is readable without interaction

  ```text
  Pricing pages render plan prices and per-unit API rates directly in fetched HTML without interaction.
  ```

- **Pass** — Prices are stated, not gated

  ```text
  VBC plans show $19.99–$39.99 per line; API rates like $0.00860/message are stated openly.
  ```

- **Pass** — Pricing units and limits are explicit

  ```text
  Units explicit: per month/per line, per message, per minute, per successful verification.
  ```

- **Pass** — Agents identify pricing and its assumptions

  ```text
  3 of 3 sessions were judged on pricing; 0 fell short. DeepSeek V4.1 Flash: Final output gives per-message/pay-as-you-go pricing broken down by channel (SMS/MMS, Messages API, Messenger ~$0.0011/msg) and names assumptions like destination country/carrier rate variance, free signup credit/sandbox, and setup minimums for some channels. Kimi K3: Final output gives per-message/per-minute pricing (e.g. $0.005–0.01/SMS to US, ~$0.01–0.03/min voice) with named assumptions: destination country, message segmentation, number rental (~$1/mo), and trial credit limits on sender ID. Qwen 3.8 Max: Final output gives per-service pricing (SMS ~$0.005-$0.10, Voice per-minute, Verify ~$0.05-$0.10, numbers ~$1-3/mo) and names assumptions (pay-per-use, per-country variance, 153-char SMS segments, free trial ~€2 credit with verified-number restriction). This behavioural item does not affect the fast grade.
  ```


### Activation
- **Pass** — An API reference or OpenAPI spec is reachable

  ```text
  Messages API reference page fetched at developer.vonage.com/en/api/messages, linked from SMS getting-started guide.
  ```

- **Skipped** — An MCP server is documented and well-formed

  ```text
  No MCP server documentation found in the fetched Vonage pages.
  ```

- **Pass** — A CLI install path is documented

  ```text
  Vonage CLI overview documents command index, auth, applications and numbers management.
  ```

- **Skipped** — SDK packages resolve on their registries

  ```text
  No registry lookup results for Vonage SDK packages were supplied.
  ```

- **Skipped** — Agent skills are published

  ```text
  No agent skills documentation found in the fetched Vonage pages.
  ```



[Full report data](https://www.ax-check.com/vonage.com/report.json)
