# Bland — Enterprise voice AI platform for inbound and outbound phone agents, running on Bland's own self-hosted models.

> Source: The Agents Index — https://theagentsindex.com/bland-ai (structured, researched, re-verified)
> Facts last verified: 2026-09-11

Bland is an enterprise voice AI platform for building, testing and monitoring phone agents that handle inbound and outbound calls. The same agent also runs over SMS, iMessage and web chat with shared memory.

| Fact | Value |
| --- | --- |
| Website | https://www.bland.ai |
| Price | from $0.14/minute pay-as-you-go |
| Free tier | Yes |

Start plan: $0 platform fee, no card required, two credits plus an inbound number ($15/mo value). Capped at 100 calls/day, 100 calls/hour, 10 concurrent calls, 1 voice and 10 knowledge bases; talk time beyond the credits is billed at $0.14/min.

## What it does

**Writes code** · No — Norm turns a plain-English description into a conversation pathway, persona, voice and tools; nothing on the site describes it authoring application source code.

> Plain English in. Pathway, persona, voice, and tools out. You decide what to add next.
> — https://www.bland.ai/product · Describe the agent. Norm builds it. section, subheading

**Debugs and fixes** · Partly — Norm reproduces a failing call, finds the root cause and applies the fix, but the fix lands in a Bland pathway, not in your codebase.

> Norm pulls in the failing call and its pathway, reproduces the failure, applies a fix in a draft, and verifies it against the original call.
> — https://docs.bland.ai/tutorials/norm · What Norm can do, Fix issues from Triage

**Writes tests** · Partly — It generates and runs call-scenario suites with assertions against the agent, including scenarios derived from historical transcripts; these are conversation tests, not unit tests for code.

> Scenario suites with assertions. Back-test against historical calls. Run thousands in parallel.
> — https://www.bland.ai/product · Testing section, Break it before customers do.

**Reviews code** · No — Review runs the other direction: a human reviews Norm's draft before it merges. No surface reviews a diff someone else wrote.

> Every change Norm makes is reviewable on the issue, so you can see exactly what it touched before merging the fix into production.
> — https://docs.bland.ai/tutorials/norm · What Norm can do, Fix issues from Triage, closing paragraph

**Whole-codebase work** · No — The unit of work is a pathway YAML directory synced to one Bland account via push, pull, diff and watch; there is no repository-wide code migration.

> Create and manage conversational pathways as YAML files. Sync local YAML with the Bland API, run interactive tests, and automate test cases.
> — https://docs.bland.ai/sdks/cli · What you can do, Pathways accordion

**Ships it** · Partly — It ships agent versions to live phone traffic with canary, promotion and rollback; it does not deploy application code.

> Canary new versions against 1% of real calls. Promote, or roll back in seconds. Zero-downtime deploys, every time.
> — https://www.bland.ai/product · Releases section, Real traffic, before you commit.

**Done-for-you service** · Partly — You run the software yourself on the self-serve plans, but Enterprise buyers get Bland engineers building the first deployment.

> Our forward-deployed engineering team works directly with yours to build, optimize, and scale the deployment. Enterprise plans include FDE support.
> — https://www.bland.ai/pricing · Frequently asked questions, 'Who runs the implementation?' answer

## How much it does unattended

**Runs autonomously** · Yes — Agents run whole phone calls unattended at volume; a human only re-enters when a rail escalates or transfers.

> Bland automates the calls you thought required a human. Running entirely on your own infrastructure for maximum security.
> — https://www.bland.ai · 'One platform. Every call.' section, opening paragraph

**Multi-agent** · Partly — Warm transfer runs a second proxy-agent leg alongside the primary agent, but that is call handoff, not general orchestration.

> When a transfer is needed, the agent initiates a second proxy agent call in the background.
> — https://docs.bland.ai/platform/billing · Warm Transfer Billing section, explanatory paragraph under the billing table

**Agent permissions** · Partly — Guard rails bound what an agent may say and can end, transfer or reroute a call; custom rails are Enterprise-only.

> Guard rails continuously analyze every AI and user response during production calls. They catch severe failure modes like discrimination, self-harm encouragement, or compliance violations before they cause damage.
> — https://docs.bland.ai/tutorials/guard-rails · Guard Rails page, opening paragraph

## Which models it runs on

**Claude** · No — Claude never runs the call: Bland states no third-party AI provider is in the call path at all.

> Most voice AI vendors list OpenAI, Anthropic, ElevenLabs, and a telephony reseller as sub-processors handling your call data. Bland runs its own models, so no third-party AI provider touches your call.
> — https://www.bland.ai/trust-security · 'Things wrappers structurally cannot do' section, 'One DPA, not a folder of four'

**GPT** · No — OpenAI models are named as exactly what Bland does not use; inference stays on Bland's own speech and language models.

> Where other vendors wrap third parties, Bland runs its own model and speech.
> — https://www.bland.ai/trust-security · Page header, subtitle under 'Pass security review on day one.'

**Open models** · No — No open-weight option is offered; every model in the call path is Bland's own, purpose-built for telephony.

> With every model custom-made for phone calls, your data never goes through third parties. No sudden changes to your model, pricing, or terms of service.
> — https://www.bland.ai · 'Infrastructure — Reliability on every call' card

**Model choice** · No — The vendor picks the model and sells that as the differentiator; buyers get no model selection on any tier.

> Bland's per-minute rate covers the LLM, STT, and TTS in one number, with no token charges and no model-provider pass-throughs.
> — https://www.bland.ai/pricing · Frequently asked questions, 'How does Bland's pricing compare to platforms like Vapi or Retell?'

## Where you use it

**In your editor** · Yes — An MCP server puts agent building inside Claude Code, Cursor, VS Code and Codex; the agent itself still runs on calls.

> The same MCP server makes Bland reachable from Claude Code, Cursor, and any other AI editor your team already uses.
> — https://www.bland.ai/product · 'Or write it the way you write everything else.' section intro

**On the command line** · Yes — A published npm CLI drives calls, pathways, numbers, guard rails, evals and releases from a terminal.

> Manage your entire Bland account from the terminal: make calls, build and test pathways, configure phone numbers, and more.
> — https://docs.bland.ai/sdks/cli · Command Line Interface page, opening line

**In a browser** · Yes — A hosted dashboard covers call logs, transcripts, recordings and review; agents also embed as a web voice/chat widget.

> Call logs are the central hub for reviewing completed and active calls. Every call made through Bland — outbound, inbound, voice, web, or SMS — surfaces here with its full transcript, audio recording, extracted variables, and per-turn decision data.
> — https://docs.bland.ai/tutorials/call-logs · Call Logs page, Introduction

_Not established: In your pipeline_

## Whose machine it runs on

**Self-hosted** · Partly — VPC, on-premise and air-gapped deployments exist but the pricing table gates them to Enterprise contracts only.

> Self host Bland on your infrastructure (for Enterprise).
> — https://www.bland.ai/product · 'Your infrastructure, not ours.' panel, On-premise row

**Open source** · No — The platform is proprietary under the Terms. Only client tooling is published: bland-cli on npm declares an MIT licence and ships a build with no public repository named.

> All Materials are the copyrighted property of Bland AI or its subsidiaries or affiliates under the laws of the United States and other countries.
> — https://www.bland.ai/legal/terms · Ownership; Proprietary Rights paragraph

## What it costs to run

**How it meters** · Yes — Billing is per connected minute, prorated to the second, with a separate transfer-minute rate rather than seats or tokens.

> Prorated to the exact second. Only active call time is counted.
> — https://docs.bland.ai/platform/billing · Bland Voice Billing table, Call Time row, Description cell

**Free tier** · Yes — You can sign up and build without a sales call or a card, though call minutes are billed once the two credits are gone.

> Sign up on the Start plan and you get two credits plus an inbound number valued at $15/month, with no card required.
> — https://www.bland.ai/pricing · Frequently asked questions, 'How do I get started?' answer

**API access** · Yes — A documented public REST API covers calls, pathways, knowledge bases, numbers and webhooks on every plan.

> Hit the REST API from your terminal, your code, or the CLI.
> — https://www.bland.ai/product · 'Or write it the way you write everything else.' section intro

**MCP server** · Yes — Bland hosts a remote MCP server so another agent can place calls, read transcripts and manage pathways with an API key.

> It's a remote Model Context Protocol server hosted by Bland. There's nothing to run locally: point your client at the endpoint, authenticate with your API key, and your agent has the full toolset.
> — https://docs.bland.ai/integrations/mcp/overview · Bland MCP Server page, introduction

**Bring your own key** · Partly — You can bring your own telephony and, on Enterprise, your own cloud or hardware, but never your own model keys.

> Yes. Bland integrates with your existing Twilio account, with SIP trunks from any contact-center or telephony provider, or you can use Bland's built-in Twilio at pass-through cost.
> — https://www.bland.ai/pricing · Frequently asked questions, 'Can we bring our own telephony provider?' answer

## Buying it for a team

**A company can buy it** · Yes — Accounts are organisation-scoped with enterprise workspaces, contracted volume pricing and admin-managed identity.

> Bland supports both OIDC (OpenID Connect) and SAML 2.0 based Single Sign-On (SSO) for enterprise workspaces.
> — https://docs.bland.ai/enterprise-features/SSO · SSO Support page, Introduction

**Seat model** · No — Nothing is priced per user: plans charge a flat platform fee plus usage, and the comparison table meters calls, concurrency, voices and knowledge bases rather than seats.

> $299/month platform fee
> — https://www.bland.ai/pricing · Build plan card, price line under '$0.12/min'

**Pooled budget** · Yes — Credits and limits sit on the organisation, so everyone with a key draws from one shared balance and one set of caps.

> This one-time credit has been automatically applied to your organization and will support your upcoming usage. Each organization's credit is calculated based on their own prior month of connected minutes.
> — https://docs.bland.ai/platform/billing · Automatic Transition Credits section, closing paragraph

**Admin controls** · Partly — Admins constrain agent behaviour with time-based and continuous rails plus role-based access, but only Enterprise gets custom rails.

> Enterprise customers can create up to 5 custom guard rails for industry-specific concerns/company policies.
> — https://docs.bland.ai/tutorials/guard-rails · Enterprise Custom Guard Rails section

**Audit log** · Partly — Call-level auditing is thorough — every rail trigger and disclosure is logged — but no admin-action audit trail is documented.

> Audit trail Tamper-resistant call logs. Every disclosure recorded, every rail logged.
> — https://www.bland.ai/product · 'Built to pass your security review.' section, Audit trail cell

**Single sign-on** · Partly — Both OIDC and SAML 2.0 are supported with auto-provisioning, but the plan table shows SSO only in the Enterprise column.

> Bland supports both OIDC (OpenID Connect) and SAML 2.0 based Single Sign-On (SSO) for enterprise workspaces.
> — https://docs.bland.ai/enterprise-features/SSO · SSO Support page, Introduction

## What happens to your code

**Opt out of training** · Partly — No outside model provider sees your calls and zero-retention processing exists for sensitive work, but no general training opt-out is published.

> Zero-retention processing available for sensitive workflows
> — https://www.bland.ai/trust-security · Compliance section, HIPAA card, Controls in scope list

**Data residency** · Partly — US, EU and APAC regions with per-call pinning are offered, but the plan table restricts contractual data residency to Enterprise.

> Data residency US, EU, and APAC deployment options on request.
> — https://www.bland.ai · 'Built for complex, regulated industries.' section, Data residency cell

**Getting out** · Partly — Call data exports as CSV and via API, but the export window is capped at 180 days and credit expiry is never addressed.

> Click Export Calls in the header to export your call data as a CSV delivered via email.
> — https://docs.bland.ai/tutorials/call-logs · The Call Logs Table, Export subsection

**Certifications** · Yes — SOC 2 Type II, HIPAA with BAA, GDPR and PCI DSS v4.0 are all claimed, with reports released under NDA on Enterprise.

> Yes. SOC 2 Type I and Type II, HIPAA-eligible with a signed BAA, GDPR, and PCI DSS. Compliance documentation is available under NDA on Enterprise.
> — https://www.bland.ai/pricing · Frequently asked questions, 'Is Bland HIPAA, SOC 2, GDPR, and PCI compliant?' answer

## Provenance

Every fact above comes from the vendor. Nothing here is independently corroborated yet.

## Coverage elsewhere

Pages about this product that the vendor does not control. The label states how independent each one is.

| Source | Kind | Read |
| --- | --- | --- |
| lindy.ai | A competitor's comparison | 2026-08-22 |

## What changed

- 2026-09-11 — Capabilities · Commercial terms · Free tier · Price
- 2026-09-02 — Capabilities · Commercial terms · Free tier · Price
- 2026-08-31 — Capabilities · Commercial terms · Free tier · Price
- 2026-08-22 — Alternatives · Documentation link · LinkedIn link · One-liner · Summary

## Correcting this record

Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Bland, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth.

Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.