Telnyx Inference API pricing - Telnyx

Pay-per-token. No minimums, no commitments. For current per-model pricing, see telnyx.com/pricing/inference-api.

Service tiers

For standard Inference API requests to Telnyx-hosted models, omitting service_tier uses default. Set service_tier to choose another tier supported by the model.

Service tier	Request value	Pricing and workload
Flex	`flex`	Lower-cost inference for workloads that can tolerate higher latency and variable availability
Default	`default`	Standard rates for general-purpose inference
Priority	`priority`	Priority rates for latency-sensitive workloads

Flex and Priority are available for select models. Check the model’s service_tiers field and use the corresponding tier’s rates on the pricing page. See Service tiers for model availability, request examples, and guidance on choosing a tier.

Billing units

Category	Basis	Notes
Text generation	Per 1M tokens (input + output)	Input and output priced separately; cached input tokens at a discount
Audio transcription	Per second of audio	Varies by model
Text-to-speech	Per 1M characters	Varies by voice/model
Embeddings	Per 1M tokens	Single rate