POST
Authentication
Meridian uses short-lived bearer tokens issued via mutual TLS handshake. Every token is cryptographically scoped to a single tenant and expires after 900 seconds by default.
DEVELOPER HUB
Search documentation…
⌘K
POST
Authentication
Meridian uses short-lived bearer tokens issued via mutual TLS handshake. Every token is cryptographically scoped to a single tenant and expires after 900 seconds by default.
POST
Authentication
Meridian uses short-lived bearer tokens issued via mutual TLS handshake. Every token is cryptographically scoped to a single tenant and expires after 900 seconds by default.
POST
Authentication
Meridian uses short-lived bearer tokens issued via mutual TLS handshake. Every token is cryptographically scoped to a single tenant and expires after 900 seconds by default.
POST
Webhooks
Meridian webhooks deliver signed, ordered event payloads to your infrastructure with sub-200ms P99 latency. Built-in retry logic and dead-letter queues eliminate the need for polling loops.
POST
Webhooks
Meridian webhooks deliver signed, ordered event payloads to your infrastructure with sub-200ms P99 latency. Built-in retry logic and dead-letter queues eliminate the need for polling loops.
POST
Webhooks
Meridian webhooks deliver signed, ordered event payloads to your infrastructure with sub-200ms P99 latency. Built-in retry logic and dead-letter queues eliminate the need for polling loops.
INFO
Rate Limits
Every Meridian API surface enforces tiered, per-tenant rate limits tracked in a sliding window against a distributed token bucket. Exceeding a limit returns a structured 429 with precise retry metadata — never a silent drop.
INFO
Rate Limits
Every Meridian API surface enforces tiered, per-tenant rate limits tracked in a sliding window against a distributed token bucket. Exceeding a limit returns a structured 429 with precise retry metadata — never a silent drop.
INFO
Rate Limits
Every Meridian API surface enforces tiered, per-tenant rate limits tracked in a sliding window against a distributed token bucket. Exceeding a limit returns a structured 429 with precise retry metadata — never a silent drop.
GET
Edge Caching
Meridian's edge cache layer sits within 12ms of every major cloud egress point, serving deterministic inference responses with microsecond reads. Cache semantics are fully programmable via policy objects — no CDN configuration required.
GET
Edge Caching
Meridian's edge cache layer sits within 12ms of every major cloud egress point, serving deterministic inference responses with microsecond reads. Cache semantics are fully programmable via policy objects — no CDN configuration required.
GET
Edge Caching
Meridian's edge cache layer sits within 12ms of every major cloud egress point, serving deterministic inference responses with microsecond reads. Cache semantics are fully programmable via policy objects — no CDN configuration required.
POST
LLM Fallbacks
Meridian's model router enforces waterfall fallback chains across heterogeneous LLM providers, cutting over within 800ms of a detected provider fault. Zero manual intervention. Zero dropped requests.
POST
LLM Fallbacks
Meridian's model router enforces waterfall fallback chains across heterogeneous LLM providers, cutting over within 800ms of a detected provider fault. Zero manual intervention. Zero dropped requests.
POST
LLM Fallbacks
Meridian's model router enforces waterfall fallback chains across heterogeneous LLM providers, cutting over within 800ms of a detected provider fault. Zero manual intervention. Zero dropped requests.
POST
Telemetry Export
Meridian emits full-fidelity OpenTelemetry traces, metrics, and logs from every inference and pipeline execution. Export to any OTLP-compatible backend in under 5 minutes with zero instrumentation overhead on your side.
POST
Telemetry Export
Meridian emits full-fidelity OpenTelemetry traces, metrics, and logs from every inference and pipeline execution. Export to any OTLP-compatible backend in under 5 minutes with zero instrumentation overhead on your side.
POST
Telemetry Export
Meridian emits full-fidelity OpenTelemetry traces, metrics, and logs from every inference and pipeline execution. Export to any OTLP-compatible backend in under 5 minutes with zero instrumentation overhead on your side.
DEPLOY / MERIDIAN
Two ways in — pick your path.
01
For humans
Get started with our Next.js and Python SDKs in seconds.
02
For agents
Tools to connect your autonomous agents to our edge infrastructure.

Aquire $129

Aquire $129

Aquire $129