Usage-based pricing built for scale
Purchase credits and pay for what you consume across all models and products.
On-demand
For developers and scaling startups
TTS-1.5 Mini
$5/1M chars. (0.5¢/min)
TTS-1.5 Max
$10/1M chars. (1¢/min)
Router
Underlying LLM usage (rates below)
Realtime API
Underlying model usage (rates below)
- #1 ranked TTS globally
- Intelligent model routing
- Semantic speech recognition
- Realtime speech-to-speech
- Instant voice cloning
- 220+ LLM models
- API access
- 100 RPS TTS rate limit
- GDPR & SOC 2 Type II
- Support bot & community support
Enterprise
For large-scale deployments
TTS-1.5 Mini
Volume-based discounts
TTS-1.5 Max
Volume-based discounts
Router
Volume-based discounts
Realtime API
Volume-based discounts
- All On-demand features
- Professional voice cloning
- Custom rate limits
- On-prem deployment options
- HIPAA & BAA
- DPA & SLA
- Zero data retention mode
- EU and India data residency
- Dedicated account manager & Slack channel
- Invoicing options
Compare plans
Start with on-demand and move to enterprise when you need volume discounts, higher rate limits, and custom terms.
On-demand
For developers and scaling startups
Enterprise
For large-scale deployments
Pricing
TTS-1.5 Mini: $5/1M chars. (0.5¢/min)
TTS-1.5 Max: $10/1M chars. (1¢/min)
Router: Underlying LLM usage (rates below)
Realtime API: Underlying model usage (rates below)
TTS-1.5 Max: $10/1M chars. (1¢/min)
Router: Underlying LLM usage (rates below)
Realtime API: Underlying model usage (rates below)
TTS-1.5 Mini: Volume-based discounts
TTS-1.5 Max: Volume-based discounts
Router: Volume-based discounts
Realtime API: Volume-based discounts
TTS-1.5 Max: Volume-based discounts
Router: Volume-based discounts
Realtime API: Volume-based discounts
#1 ranked TTS globally
Intelligent model routing
Semantic STT
Realtime speech-to-speech
Voice cloning
Instant
Professional
LLMs
220+ models
220+ models
API access
GDPR
SOC 2 Type II
On-prem deployment
—
HIPAA & BAA
—
DPA & SLA
—
Zero data retention mode
—
EU and India data residency options
—
TTS rate limits
100 RPS
Custom limits
Support
Support Bot
Community
Community
Dedicated account manager
Shared Slack channel
Shared Slack channel
Payment options
Credit card
Invoicing options
Pricing
TTS-1.5 Mini: $5/1M chars. (0.5¢/min)
TTS-1.5 Max: $10/1M chars. (1¢/min)
Router: Underlying LLM usage (rates below)
Realtime API: Underlying model usage (rates below)
TTS-1.5 Max: $10/1M chars. (1¢/min)
Router: Underlying LLM usage (rates below)
Realtime API: Underlying model usage (rates below)
#1 ranked TTS globally
Intelligent model routing
Semantic STT
Realtime speech-to-speech
Voice cloning
Instant
LLMs
220+ models
API access
GDPR
SOC 2 Type II
On-prem deployment
—
HIPAA & BAA
—
DPA & SLA
—
Zero data retention mode
—
EU and India data residency options
—
TTS rate limits
100 RPS
Support
Support Bot
Community
Community
Payment options
Credit card
Rates
TTS
Inworld TTS-1.5 Max
$10/1M characters ~$0.01/minute
Inworld TTS-1.5 Mini
$5/1Mcharacters ~ $0.005/minute
STT
Usable through Realtime API. If you're looking for a model that is not listed below, please reach out.
Model
Provider
Cost
Universal-Streaming Multilingual
AssemblyAI
Cost
$0.15/hour
Universal-Streaming English
AssemblyAI
Cost
$0.15/hour
Whisper Large v3
Groq
Cost
$0.111/hour
LLM
Usable through Router API and Realtime API. If you’re looking for a model that is not listed below, please reach out.
Promotion: Get 50% back in platform credits on all Mistral model usage
- When: Now until April 30.
- Who: Open to all users who have made at least one credit purchase.
- The Deal: For every $1.00 you spend on Mistral models, we'll give you $0.50 back in credits.
- Payout: Credits are automatically added to your balance within one week after the month ends.
google-ai-studio
Input Cost ($/1M tokens)
$0.08
Output Cost ($/1M tokens)
$0.30
google-vertex
Input Cost ($/1M tokens)
$0.10
Output Cost ($/1M tokens)
$0.40
google-ai-studio
Input Cost ($/1M tokens)
$0.10
Output Cost ($/1M tokens)
$0.40
google-ai-studio
Input Cost ($/1M tokens)
$0.25
Output Cost ($/1M tokens)
$1.50
google-ai-studio
Input Cost ($/1M tokens)
$2.00
Output Cost ($/1M tokens)
$12.00
openai
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.60
deepinfra
Input Cost ($/1M tokens)
$0.02
Output Cost ($/1M tokens)
$0.04
deepinfra
Input Cost ($/1M tokens)
$0.05
Output Cost ($/1M tokens)
$0.08
deepinfra
Input Cost ($/1M tokens)
$0.08
Output Cost ($/1M tokens)
$0.20
deepinfra
Input Cost ($/1M tokens)
$0.54
Output Cost ($/1M tokens)
$0.54
deepinfra
Input Cost ($/1M tokens)
$1.00
Output Cost ($/1M tokens)
$3.00
deepinfra
Input Cost ($/1M tokens)
$0.23
Output Cost ($/1M tokens)
$2.30
deepinfra
Input Cost ($/1M tokens)
$0.22
Output Cost ($/1M tokens)
$1.00
fireworks
Input Cost ($/1M tokens)
$0.60
Output Cost ($/1M tokens)
$2.50
deepinfra
Input Cost ($/1M tokens)
$0.10
Output Cost ($/1M tokens)
$0.40
xai
Input Cost ($/1M tokens)
$2.00
Output Cost ($/1M tokens)
$6.00
NousResearch/Hermes-3-Llama-3.1-405B
deepinfra
Input Cost ($/1M tokens)
$1.00
Output Cost ($/1M tokens)
$1.00
Prices reflect the best publicly available pricing from third party model providers and are subject to change.
FAQ
How are credits consumed and billed?
Credits are deducted based on your usage of each model. TTS is billed per million characters. LLM usage through Inworld is billed per million tokens at the provider’s cost, with no markup.
What happens when my credits run out?
If your credit balance reaches zero, API access is suspended immediately. No overage charges are applied. Service resumes as soon as you purchase additional credits.
Are there any free credits or minimum spend amounts?
All new accounts receive $2 in free credits on signup, so you can begin testing before purchasing. The minimum credit purchase is $10.
Do you mark up LLM provider pricing?
When you route LLM requests through Inworld, you pay the provider’s listed cost with no markup.
What payment methods do you accept?
For on-demand, we accept all major credit and debit cards. For enterprise accounts, we support invoicing and purchase orders. Contact sales for procurement options.
Are there any rate limits?
On-demand accounts have a rate limit for TTS of 100 requests per second (RPS), shared across all workspaces. For higher limits, contact sales.
Do you offer volume or enterprise pricing?
Yes. For high-volume usage, on-premises deployment, or custom requirements, contact our sales team for a tailored plan.
Start building
Join millions of developers building the next wave of AI applications.