Easy work goes to efficient models.
- fix a typoDeepSeek V4.1 Flash
- write unit testsQwen 3.8 Flash
- design auth systemClaude Fable 5.1
Picked for every request, automatically. And fully customizable.
Current frontier modelsClaude Fable 5.1 · GPT-6 Astra
More intelligence
per dollar.
Save up to 70% on AI costs. Compliance-ready, hosted in your region.
$300/moyour AI spend
−$147smart routing
−$64best provider rates
$89/mowith Standard Compute
Runs every major agent
Claude Code
Hermes Agent
OpenAI Codex CLIGemini CLIAny OpenAI-compatible SDKOpenClawKilo CodeCursorGitHub CopilotAny OpenAI-compatible SDKClineWindsurf
Aider
ContinueAny OpenAI-compatible SDKOpenCode
Oh My Pi
AmpAny OpenAI-compatible SDK
Hermes Agent
OpenAI Codex CLIGemini CLIAny OpenAI-compatible SDKOpenClawKilo CodeCursorGitHub CopilotAny OpenAI-compatible SDKClineWindsurf
Aider
ContinueAny OpenAI-compatible SDKOpenCode
Oh My Pi
AmpAny OpenAI-compatible SDKBuilt in Norway. Trusted by 3,400+ developers and businesses in 33 countries.
- Open-source modelsDeepSeekQwenKimiMiniMaxand more+
- Frontier modelsClaudeGPTGemini
- Works with any AI toolClaude CodeCodexGemini CLIOpenCodeHermesand more+
- Hosted in the region of your choiceEUUS
How you save
Two ways your money goes further.
Same model, best provider.
Z.AI official API$2.15
DeepInfra$1.05
Novita✓ vetted$0.65−70%
GLM 5.3, per million tokens. Vetted providers only.
Your workload
See how much you can save.
What you pay for today
How Standard Compute could optimize your workload
Estimated savings
- Claude Max 20×$200/mo1
Your AI spend today
$200/month
- Claude Fable 5.126%
- GLM 5.330%
- DeepSeek V4.1 Flash44%
Fully customizable. You choose which models the router can use.
55%
Regions & privacy
Your data, your region.
We select for providers that don't train on your prompts or retain them. Traffic stays inside the region you choose.
- GDPRCompliant
- ISO 27001Aligned
- SOC 2Aligned
Pricing
A clear budget. A fixed monthly bill.
One flat monthly price — and every individual plan starts with more compute than you pay for.
Launch offer
1.5×
Sign up now — your first month comes with 1.5× the compute you pay for.
On the $39 plan that’s a $61 budget in month one, then $41 every month after. Individual plans.
№ 01 / 08
Starter
$19/mo
Starter lane
Includes:
- $30 compute budget your first month
- Every model, smart-routed
- One agent at a time
- 1 API key
7-day fair refund — cancel and pay only what you used
Requests stop at your budget until renewal or an upgrade. No overages.
Most popular
№ 02 / 08
Economy
$39/mo
Standard lane
Everything in Starter, plus:
- $61 compute budget your first month
- Run agents in parallel
- Shared execution pool
7-day fair refund — cancel and pay only what you used
Requests stop at your budget until renewal or an upgrade. No overages.
№ 03 / 08
Standard
$89/mo
Priority lane
Everything in Economy, plus:
- $142 compute budget your first month
- Priority scheduling
- Higher-capacity pool
7-day fair refund — cancel and pay only what you used
Requests stop at your budget until renewal or an upgrade. No overages.
№ 04 / 08
Pro
$249/mo
Maximum lane
Everything in Standard, plus:
- $403 compute budget your first month
- Highest priority scheduling
7-day fair refund — cancel and pay only what you used
Requests stop at your budget until renewal or an upgrade. No overages.
№ 05 / 08
Pro Plus
$499/mo
Maximum lane
Everything in Pro, plus:
- $549 monthly compute budget
- Unlimited API keys
7-day fair refund — cancel and pay only what you used
Requests stop at your budget until renewal or an upgrade. No overages.
№ 06 / 08
Growth
$999/mo
High-capacity lane
Everything in Pro Plus, plus:
- $1,119 monthly compute budget
- More capacity for parallel agents
7-day fair refund — cancel and pay only what you used
Requests stop at your budget until renewal or an upgrade. No overages.
№ 07 / 08
Scale
$2,499/mo
Dedicated throughput
Everything in Growth, plus:
- $2,849 monthly compute budget
- Priority support
- Direct line to our engineers
7-day fair refund — cancel and pay only what you used
Requests stop at your budget until renewal or an upgrade. No overages.
№ 08 / 08
Business
Let’s talk
Sized to your volume
Everything in Scale, plus:
- Compute sized to your volume
- Flat price for your whole team
- Uptime SLA & custom terms
- Consolidated invoicing
Reply within a business day
Setting up a team?
Create your teamEstimate team cost →Running agents for clients? →Create your company for free. Each member's key gets its own plan from $19/month, approved by an admin. Your team can mix plans.
Kudos guys! Really impressed with the model quality. Code output is better… Went from about $200 a month to just using your Standard plan. You really set a new standard for what compute should look like.
The new standard
Side by side.
| Pay as you go | Subscriptions | Standard Compute | |
|---|---|---|---|
| A budget you can see | ~ | ✕ | ✓ |
| No surprise cut-offs | ✓ | ✕ | ✓ |
| A bill that never surprises | ✕ | ✓ | ✓ |
| Smart routing | ~ | ✕ | ✓ |
| Best provider rates | ~ | ✕ | ✓ |
| Unused budget given back | ✓ | ✕ | ✓ |
| More compute than you pay for | ✕ | ~ | ✓ |
01 · How it works
Where the extra intelligence comes from.
- routeSmart routing
Every request is sized up and sent to the right model — efficient models for easy work, frontier intelligence when it matters.
- sourceProvider optimization
The same model runs on many providers. We route each request to whichever is fastest and cheapest right now.
- poolSubscription economics
Not every customer runs hot at once. Unused capacity in the pool becomes extra value for everyone in it.
2–7×more compute per dollaruser reported
$1.44saved vs frontier pricing150k context
"hi"Standard Compute
02 · Full speed for always-on agents
Leave your agent running overnight. Same speed on day thirty.
Monthly compute budgetvisible
Slowdowns as usage growsnone
Automatic overage chargesnone
Requests run at full speed whether you have used 5% of your monthly compute budget or 95%. There are no 5-hour or weekly windows inside the month. When the budget is used, requests stop until renewal or an upgrade. Watch the balance live in your dashboard. There are no automatic overage charges.
The internet did it. Streaming did it. Compute is next.
1996The internetpaid by the minute → flat monthlySpeed depends on plan
2007Streamingpaid per movie → flat monthlyResolution depends on plan
NowIntelligencepaid per token → flat monthlyIntelligence depends on plan
03 · The economics
You get 2–7× more compute per $.
Three mechanisms stack in your favor.
04 · The models
Every frontier lab.
Always current.
The leading models, through one API. Each one editorially reviewed and routed across providers for price, speed, and quality.
The model collectionExplore all models
Frontier
For demanding work- AnthropicClaude Opus 5.5
- OpenAIGPT-6 Astra
- GoogleGemini 3.1 Pro Preview
Open frontier
Leading open-weight models- Z.AIGLM 5.3
- QwenQwen 3.8 27B
- MoonshotKimi K3
Efficient
For everyday agent work- OpenAIGPT-6 Luna
- AnthropicClaude Haiku 5.5
- DeepSeekDeepSeek V4.1 Flash
Editorially reviewed. Continuously re-scored.
A selection from our model lineup. Availability evolves as models and providers are reviewed.
05 · Integration
Two minutes to switch.
- Change the base URLapi.stdcmpt.com/v1
- Paste your API keyfrom your dashboard
- Set the model"standardcompute"
const client = new OpenAI({
baseURL: "https://api.openai.com/v1", baseURL: "https://api.stdcmpt.com/v1", apiKey: process.env.OPENAI_API_KEY, apiKey: process.env.STANDARD_COMPUTE_KEY,});
await client.chat.completions.create({
model: "gpt-5.2", model: "standardcompute", // the router takes it from here messages,
});06 · Reliability
Boring, the way infrastructure should be.
api.stdcmpt.com — last 90 days99.97% uptime
FAQ
Common questions.
How does the monthly compute budget work?
Every plan states its budget up front, and you can watch it live in your dashboard. Requests run at full speed until the budget is used, then they stop until your period renews. No per-token billing, no overage charges, no surprise invoice. The exact policy is on the fair-use page.
How can it be this much cheaper than what I pay now?
Three mechanisms, no magic. Most agent traffic is routine, so smart routing sends it to efficient models and saves 10x or more on those requests. The same model usually runs on several providers, and we buy from whichever offers the best rate at that moment. And unused budget in the shared pool goes back into serving members instead of expiring. It’s the same boring math your ISP runs, just pointed in your favor.
Do cheaper models mean worse results?
Smart routing chooses among the models in your selection for each request. You can include frontier models such as Claude Opus 5.5 and GPT-6 Astra for demanding work, alongside efficient models for routine steps. For more control, choose exactly which models the router may use, or select a single model. Compare results on your own tasks when changing your lineup.
What happens when my budget runs out?
Requests stop, and it never sneaks up on you. The dashboard shows exactly how much you have left at any moment. If you need more, an upgrade takes effect immediately; otherwise everything resets when your period renews. Nothing bills on top of your plan price unless you turn on Pay as you go top-ups (Economy and above) in your dashboard.
Will it work with my agent?
If it speaks the OpenAI API, yes. Nearly every agent does. Three edits: point the base URL at api.stdcmpt.com/v1, paste your key, set the model to "standardcompute". Most people are done in about two minutes, and there are step-by-step guides for every major agent.
Is my data used to train models?
Standard Compute does not use your prompts or outputs to train models. The Regions & privacy page shows whether no-training and zero data retention enforcement are active for your keys. When active, both are required for upstream routing. Zero data retention covers prompt and response content; temporary provider caches may still apply, and service metadata is retained. Details on the Data & Privacy page.
Which models do I get?
Choose from frontier models including Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, GPT-6 Astra, GPT-5.6 Sol, and Gemini 3.1 Pro Preview; open-weight options including GLM 5.3, Kimi K3, DeepSeek V4 Pro, Qwen 3.8 27B, and MiniMax M3; and efficient models such as GPT-6 Luna, Claude Haiku 5.5, DeepSeek V4.1 Flash, Gemini 3.8 Flash, and GLM 5.3 Flash. Select up to five models in your dashboard, or keep the default smart-routing lineup. New models become selectable after provider checks; adding a model does not change your saved selection.
What if it's not for me?
You’ll know before you pay. Eligible new accounts get a $0.25 trial with no credit card, so you can test it in your own agent first. Paid plans carry a 7-day fair refund: cancel in the first week and you only pay for the compute you actually used. After that, cancel anytime from the billing portal and your plan simply runs to the end of the period.