Credits & Rate Limits | Sarvam API Docs

Credits

Sarvam offers ₹1,000 worth of free credits for every user on signup. These credits can be used across any of our APIs — explore, prototype, and build without upfront cost.

Credits are universal and never expire. Once exhausted, add more credits or upgrade your plan from the Sarvam Dashboard.

How Rate Limits Work

Rate limits restrict the number of API requests your account can make within a given time window. Key points:

Per-account enforcement — limits apply to your account as a whole, not individual API keys. All keys share the same rate limit pool.
Continuous replenishment — capacity refills steadily over the window period rather than resetting all at once (token bucket model). Short bursts may still trigger limits.
Per-API granularity — each API has its own independent concurrency limits. WebSocket, Vision, and LLM APIs have different limits from standard REST APIs — check your specific API below.

Concurrency Modes

Each API enforces limits across three concurrency modes:

Mode	What it means
Provisioned	The number of requests you can run simultaneously, guaranteed. This capacity is always available to you regardless of platform load.
Burst	The peak number of simultaneous requests during a short traffic spike. Temporary extra capacity for sudden surges.
High Throughput	The number of simultaneous requests you can sustain when the system is under heavy overall load. During peak platform traffic, your capacity may scale down to this level.

Per-API Rate Limits by Plan

Rate limits vary significantly by API type and plan. Review the limits for each API below before building your integration.

Speech to Text

Real-time REST (`stt-rt`)

	Starter	Pro	Business
Provisioned	60 req/min	100 req/min	4,000 req/min
Burst	100 req/min	200 req/min	5,000 req/min
High Throughput	5 req/min	60 req/min	1,000 req/min

WebSocket Streaming (`stt-ws`)

	Starter	Pro	Business
Provisioned	20 concurrent	100 concurrent	100 concurrent
Burst	40 concurrent	150 concurrent	150 concurrent
High Throughput	5 concurrent	60 concurrent	100 concurrent

Batch (`stt-batch`)

	Starter	Pro	Business
Provisioned	20 req/min	100 req/min	500 req/min
Burst	50 req/min	200 req/min	1,000 req/min
High Throughput	5 req/min	60 req/min	300 req/min

For batch endpoints, implement a minimum 5ms delay between consecutive status polling requests to avoid hitting rate limits unnecessarily.

Text to Speech

Real-time REST (`tts-rt`)

	Starter	Pro	Business
Provisioned	60 req/min	200 req/min	1,000 req/min
Burst	100 req/min	300 req/min	1,200 req/min
High Throughput	5 req/min	60 req/min	800 req/min

For bulbul:v3 model specifically, Starter provisioned limit is 30 req/min (burst: 50). Pro and Business limits are the same as the default above.

WebSocket Streaming (`tts-ws`)

	Starter	Pro	Business
Provisioned	60 concurrent	200 concurrent	1,000 concurrent
Burst	100 concurrent	300 concurrent	1,200 concurrent
High Throughput	5 concurrent	60 concurrent	800 concurrent

For bulbul:v3 model specifically, Starter provisioned limit is 30 concurrent (burst: 50). Pro and Business limits are the same as the default above.

Translation & Text Services

Translate (`ms-ts`)

	Starter	Pro	Business
Provisioned	60 req/min	200 req/min	1,000 req/min
Burst	100 req/min	300 req/min	2,000 req/min
High Throughput	5 req/min	60 req/min	1,000 req/min

Chat Completion (LLM)

Default models (`ms-llm`)

	Starter	Pro	Business
Provisioned	60 req/min	200 req/min	1,000 req/min
Burst	100 req/min	300 req/min	2,000 req/min
High Throughput	5 req/min	60 req/min	1,000 req/min

Sarvam-30B & Sarvam-105B models

These large models have lower limits due to their compute requirements.

	Starter	Pro	Business
Provisioned	40 req/min	60 req/min	120 req/min
Burst	60 req/min	80 req/min	200 req/min
High Throughput	5 req/min	20 req/min	50 req/min

Applies to: sarvam-30b, sarvam-30b-16k, sarvam-105b, sarvam-105b-32k

Vision

Vision API limits are uniform across all plans (Starter, Pro, and Business). Upgrading your plan does not increase Vision limits.

Document Intelligence (`vis-doc-dig`)

	Starter	Pro	Business
Provisioned	10 req/min	10 req/min	10 req/min
Burst	20 req/min	20 req/min	20 req/min
High Throughput	5 req/min	5 req/min	5 req/min

Vision Real-time (`vis-rt`)

	Starter	Pro	Business
Provisioned	30 req/min	30 req/min	30 req/min
Burst	50 req/min	50 req/min	50 req/min
High Throughput	15 req/min	15 req/min	15 req/min

Plan Overview

	Starter	Pro	Business	Enterprise
Price	Pay as you go	₹10,000	₹50,000	Custom
Bonus Credits	—	₹1,000	₹7,500	Custom
Support	Community	Email	Email	Dedicated
Best For	Prototyping & testing	Startups & POCs	Production workloads	Scale deployments

Concurrency limits are measured per account, not per API key. All keys under an account share the same limit pool. Your current limits are visible on the Dashboard → Rate Limits page.

Upgrading Your Limits

Check your current limits

Visit the Dashboard → Rate Limits to see your exact per-API limits.

Upgrade your plan

Purchase a higher plan directly from the dashboard. Your rate limits increase immediately after upgrade — no downtime.

Need custom limits?

For limits beyond Business tier, contact our team for an Enterprise arrangement.

Upgrade Plan

View plans and upgrade directly from the dashboard. Rate limits update instantly.

Enterprise & Custom Limits

Need higher rate limits, dedicated infrastructure, or custom SLAs? Talk to our team.

Managing Your Credits

If your credits are exhausted, API requests will return errors. You can add credits at any time — adding credits does not change your plan or rate limits.

Add Credits — Top up from the Billing page at any time. Credits never expire.
Upgrade Your Plan — Higher plans include bonus credits and increased rate limits.
Enterprise — For volume discounts and custom billing arrangements, email developer@sarvam.ai.