DevPass vs Standard Compute
From October 15, 2026, DevPass is a plan for interactive coding only, while Standard Compute is built for agents and automation: DevPass bans API and automation use and adds daily caps, and Standard Compute gives one monthly budget with no daily or weekly windows that its router spends on the most cost-efficient model per request.
Side by side
| DevPass | Standard Compute | |
|---|---|---|
| Pricing | Lite $29, Pro $79, Max $179 a month; 2x usage at list rates from Oct 15 ($58, $158, $358). LLM Gateway itself: 5% fee on credits | Flat monthly plan: $19, $39, $89 or $249 with $20 to $269 of compute included; Business from $499 |
| Who picks the model | Always smart-routed | Router picks per request (harder steps to stronger models, routine steps to efficient ones), or pin any model ID |
| Budget control | Monthly allowance with daily caps (8% to 10%) and weekly caps on premium models | Plan budget per key; new requests get HTTP 402 when it is used, no overage |
| Claude Code | Documented | Native Messages API |
| Codex | Documented (Responses API) | Native Responses API, any model in the catalog |
| Europe / US rules | Region pinning per model; full policy set on Enterprise | Opt-in Europe or US rules on every plan, per key, team or company |
| Teams | DevPass is single-person | Company and agency workspaces, a plan per key |
| Best for | One developer coding interactively | Coding agents and agent fleets that need one fixed monthly cost |
DevPass facts from its own pricing and docs pages. Standard Compute is our product.
Where they differ
- For billing periods starting on or after October 15, DevPass excludes API, automation and non-coding use, and breaking that can close the account without a refund. Standard Compute plans are made for agents, including automated ones.
- DevPass adds rolling daily caps of 8% to 10% of the monthly allowance and weekly caps on premium models. Standard Compute has one monthly budget.
- DevPass is for one person. Standard Compute company and agency workspaces give each key its own plan.
When DevPass is the better fit
DevPass is the better pick for one developer coding interactively who wants the most frontier usage per dollar on paper: twice the plan price at list rates after October 15.
Switch from DevPass in 2 minutes
Standard Compute speaks the same APIs, so switching is a base URL, a key and a model name. Your prompts, tools and streaming stay as they are.
| Setting | DevPass | Standard Compute |
|---|---|---|
| OpenAI-compatible base URL | https://api.llmgateway.io/v1 | https://api.stdcmpt.com/v1 |
| Claude Code base URL | https://api.llmgateway.io | https://api.stdcmpt.com |
| API key | Your DevPass key | Your Standard Compute key |
| Model | The model ID you use today | standardcompute, or any exact model ID |
# OpenAI-compatible clients (OpenCode, Cline, Kilo Code, SDKs)
base_url = "https://api.stdcmpt.com/v1"
api_key = "<your-standard-compute-key>"
model = "standardcompute" # or pin one, e.g. anthropic/claude-sonnet-5.5# Claude Code (Anthropic Messages API, no /v1)
export ANTHROPIC_BASE_URL="https://api.stdcmpt.com"
export ANTHROPIC_AUTH_TOKEN="<your-standard-compute-key>"# Codex CLI, ~/.codex/config.toml
model = "standardcompute"
model_provider = "standardcompute"
[model_providers.standardcompute]
name = "Standard Compute"
base_url = "https://api.stdcmpt.com/v1"
env_key = "STANDARD_COMPUTE_API_KEY"
wire_api = "responses"Run your agents on a fixed monthly budget
Every plan includes the compute and every model, and the router spends the budget on the most cost-efficient model for each step. Pay-as-you-go top-ups are optional, never automatic.
FAQ
What changes on DevPass on October 15, 2026?
For billing periods starting on or after October 15, usage drops from 3x to 2x the plan price ($58, $158 and $358 on Lite, Pro and Max), rolling daily caps of 8% to 10% apply, premium models get weekly caps, and API, automation and non-coding use is excluded.
Can I use DevPass for agents or automation?
Not after October 15: LLM Gateway's terms exclude API, automation and non-coding use on DevPass. Standard Compute plans allow agents and automations, with one monthly budget and no daily or weekly windows.
Is DevPass cheaper than Standard Compute?
On paper DevPass gives more usage per dollar: twice its price at list rates, against 5% to 14% more than the price on Standard Compute plans. Standard Compute starts lower ($19 against $29) and stretches its budget by routing routine steps to efficient models.
Does each work with Claude Code and Codex?
Yes. LLM Gateway documents both with its Anthropic and Responses endpoints. Standard Compute serves the Messages API for Claude Code and the Responses API for Codex.
Can a team share DevPass?
No, DevPass is a single-person plan. Standard Compute company and agency workspaces let an admin give each person or agent a key with its own plan.
Sources: DevPass terms (October 2026 plan changes) · DevPass · LLM Gateway pricing · LLM Gateway Claude Code guide