Free
Free
Pricing page invites teams to start with a free tier and playground access before scaling token usage.
- Access
- Pricing page invites teams to start with a free tier and playground access before scaling token usage.
Relace
● Identity checkedCode · Vendor site 2026-10-04
Relace provides purpose-built AI models and token-based infrastructure for coding agents, including relace-search, relace-compact, relace-apply, and relace-rank models. Pricing is consumption-based per million input and output tokens with a free tier to test models in the playground.
- Category
- Code
- Free access
- Pricing page invites teams to start with a free tier and playground access before scaling token usage.
- API access
- Models are offered through Relace infrastructure with per-token list prices for agent integrations.
Is Relace right for you?
A good fit for
Teams building autonomous coding agents who need fast retrieval, merge, and ranking models billed by tokens.
Before you choose
Costs scale with token volume rather than flat monthly seat pricing, and policies cover rate limits and SLAs separately.
Infrastructure for coding agents
Relace combines specialized code models with scalable hosting aimed at agent builders optimizing retrieval, apply, and ranking steps.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Agent models | Model lineup includes relace-search, relace-compact, relace-apply-3, and relace-rank for code workflows. | Facts sourced | 2026-10-04 |
| Token pricing | List prices such as $1 per million input tokens for relace-search are published on the pricing page. | Facts sourced | 2026-10-04 |
| Jacq IDE | Site promotes Jacq macOS app for trying Relace models alongside cloud infrastructure. | Facts sourced | 2026-10-04 |
Understand the total cost
Relace pricing & plans
Alternatives to Relace
View all ↗
CosineCosine, hosted at cosine.sh, is a sovereign AI lab training specialized coding agents and models for secure environments. It offers Lumen Scout, Outpost, and Sovereign models plus CLI and cloud surfaces with transparent credit-based plans for developers and regulated teams.
Explore tool
MaritimeMaritime hosts persistent AI agents, each in its own Firecracker micro-VM with durable disk. Agents sleep when idle, wake in about a second, and scale from a free tier to paid plans with configurable RAM, SSD, and always-on options.
Explore tool
Context.devContext.dev is a web data API for AI agents and LLMs to scrape pages into Markdown, crawl sites, map domains, run batches, research the web, monitor changes, and retrieve brand data through one REST platform with SDKs and MCP support.
Explore toolThe practical questions
Frequently asked questions
What is Relace used for?
Relace provides purpose-built AI models and token-based infrastructure for coding agents, including relace-search, relace-compact, relace-apply, and relace-rank models. Pricing is consumption-based per million input and output tokens with a free tier to test models in the playground.
Does Relace have a free plan?
Pricing page invites teams to start with a free tier and playground access before scaling token usage.. This record lists ongoing free access; check the plan limits before starting.
How much does Relace cost?
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use Relace through an API?
Models are offered through Relace infrastructure with per-token list prices for agent integrations.. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
Costs scale with token volume rather than flat monthly seat pricing, and policies cover rate limits and SLAs separately.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.
How this profile is supported
Identity and profile
Reviewed vendor source
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.