Get the better AI models and infrastructure for code generation
Relace supports pricing models for teams of all sizes, designed to meet you as you grow.
Individual models (based on token usage)
Models
Repos
relace-apply-3
$0.80
/million
(Input Tokens)
$1.20
/million
(Output Tokens)
relace-search
$1.00
/million
(Input Tokens)
$3.00
/million
(Output Tokens)
relace-rank
$0.05
/million
(Input Tokens)
relace-embed
$0.18
/million
(Input Tokens)
For information about our policies, including refunds, subscription cancellation, rate limits, and SLAs, please visit our Policies page.
Individual models (based on token usage)
Models
Repos
relace-apply-3
$0.80
/million
(Input Tokens)
$1.20
/million
(Output Tokens)
relace-search
$1.00
/million
(Input Tokens)
$3.00
/million
(Output Tokens)
relace-rank
$0.05
/million
(Input Tokens)
relace-embed
$0.18
/million
(Input Tokens)
For information about our policies, including refunds, subscription cancellation, rate limits, and SLAs, please visit our Policies page.
Individual models (based on token usage)
Models
Repos
relace-apply-3
$0.80
/million
(Input Tokens)
$1.20
/million
(Output Tokens)
relace-search
$1.00
/million
(Input Tokens)
$3.00
/million
(Output Tokens)
relace-rank
$0.05
/million
(Input Tokens)
relace-embed
$0.18
/million
(Input Tokens)
For information about our policies, including refunds, subscription cancellation, rate limits, and SLAs, please visit our Policies page.
Trusted by the best leading brands:
Trusted by the best leading brands:
Trusted by the best leading brands:
FAQs
Frequently asked questions
Why Relace?
Relace is purpose-built for coding workflows. Instead of relying on general-purpose LLMs, our in-house models specialize in retrieval, merging, and code generation — making them faster, more reliable, and easier to integrate into engineering pipelines. Teams use Relace to cut down errors, accelerate development, and gain a real competitive edge.
Is Relace SOC 2 compliant?
Yes. Relace is built with enterprise security in mind, and our systems are SOC 2 compliant. This ensures your data is handled with the highest standards of confidentiality and integrity.
Can I self-host Relace models?
Absolutely. For teams with stricter compliance or latency requirements, we offer on-premise and VPC-isolated deployments. You get full control of your environment while still benefiting from Relace's optimized inference stack.
How does Relace handle sensitive code?
Your code never leaves your controlled environment when using self-hosted or VPC deployments. Even on our hosted tier, all data is encrypted in transit and at rest.
What’s the main advantage for source control workflows?
Relace outperforms frontier LLMs at code retrieval and merging. Our models can search a codebase in under a second and merge at 10,000 tokens per second — speeding up PR reviews, automated fixes, and CI/CD processes.
How fast in onboarding?
You can start experimenting within minutes using our hosted API. For enterprise and self-hosted setups, our team provides guided onboarding to help you deploy Relace quickly and securely in your stack.
Why Relace?
Relace is purpose-built for coding workflows. Instead of relying on general-purpose LLMs, our in-house models specialize in retrieval, merging, and code generation — making them faster, more reliable, and easier to integrate into engineering pipelines. Teams use Relace to cut down errors, accelerate development, and gain a real competitive edge.
Is Relace SOC 2 compliant?
Yes. Relace is built with enterprise security in mind, and our systems are SOC 2 compliant. This ensures your data is handled with the highest standards of confidentiality and integrity.
Can I self-host Relace models?
Absolutely. For teams with stricter compliance or latency requirements, we offer on-premise and VPC-isolated deployments. You get full control of your environment while still benefiting from Relace's optimized inference stack.
How does Relace handle sensitive code?
Your code never leaves your controlled environment when using self-hosted or VPC deployments. Even on our hosted tier, all data is encrypted in transit and at rest.
What’s the main advantage for source control workflows?
Relace outperforms frontier LLMs at code retrieval and merging. Our models can search a codebase in under a second and merge at 10,000 tokens per second — speeding up PR reviews, automated fixes, and CI/CD processes.
How fast in onboarding?
You can start experimenting within minutes using our hosted API. For enterprise and self-hosted setups, our team provides guided onboarding to help you deploy Relace quickly and securely in your stack.
Why Relace?
Relace is purpose-built for coding workflows. Instead of relying on general-purpose LLMs, our in-house models specialize in retrieval, merging, and code generation — making them faster, more reliable, and easier to integrate into engineering pipelines. Teams use Relace to cut down errors, accelerate development, and gain a real competitive edge.
Is Relace SOC 2 compliant?
Yes. Relace is built with enterprise security in mind, and our systems are SOC 2 compliant. This ensures your data is handled with the highest standards of confidentiality and integrity.
Can I self-host Relace models?
Absolutely. For teams with stricter compliance or latency requirements, we offer on-premise and VPC-isolated deployments. You get full control of your environment while still benefiting from Relace's optimized inference stack.
How does Relace handle sensitive code?
Your code never leaves your controlled environment when using self-hosted or VPC deployments. Even on our hosted tier, all data is encrypted in transit and at rest.
What’s the main advantage for source control workflows?
Relace outperforms frontier LLMs at code retrieval and merging. Our models can search a codebase in under a second and merge at 10,000 tokens per second — speeding up PR reviews, automated fixes, and CI/CD processes.
How fast in onboarding?
You can start experimenting within minutes using our hosted API. For enterprise and self-hosted setups, our team provides guided onboarding to help you deploy Relace quickly and securely in your stack.