CoderPlanCoderPlan
HomePricingLotteryAbout
Limited-time: free trial credit for new accounts

Membership-level pricing,no membership required

CoderPlan is the pay-as-you-go API layer for Claude Code, Cursor, Codex CLI, and Gemini CLI. Same models, cache-optimized rates, credit that never expires — built for vibe coding, not for quota windows.

Start free trialSee models & prices

Credit never expires. Every call logs model, tokens, cache savings, and cost.

api-previewSetup guide

model: claude-sonnet

Input 34K · Cache read 94K · Output 4.2K

Cost $6.20 · Estimated savings $12.40

Usage credit $93.80 · Request succeeded

All major models

Claude, GPT, and Gemini behind one endpoint

Dual-protocol

Works with OpenAI- and Anthropic-compatible clients

New models, fast

Major model launches land here quickly

Credit never expires

Top up as you go; idle time costs nothing

High cache hits

Repeated context bills at cache-read prices

Same models, lower prices

The same models as the official APIs, billed by real usage — no subscriptions, no usage windows. Start on free trial credit and run an actual task before you pay.

Membership vs pay-as-you-go

Keep the membership-level price, drop the membership

Same models and similar per-call cost — without the fixed monthly commitment.

Monthly membershipCoderPlan pay-as-you-go
BillingFixed monthly fee, charged whether you code or notTop up credit as needed; credit never expires
Usage capQuota windows and throttling when you hit limitsNo monthly quota — spend at your own pace
Idle monthsQuiet months still burn the full feeZero cost when you don't call
Tool coverageBest inside official apps and web clientsBuilt for Claude Code, Cursor, Codex CLI, Gemini CLI via API
Spend visibilityA flat fee with little per-call detailModel, tokens, cache savings, and cost logged per request
OverageSlow down or upgrade the planKeep going — credit simply decrements

Loved by developers

Developers who switched to pay-as-you-go

Real workflows, real bills.

DKDaniel K.·Pro throttled me mid-refactor one time too many. never againPSPriya S.·90K context on my monorepo used to scare me. cache hits made it pocket changeOFOmar F.·i read the per-call logs like bank statements. every token accountedMTMarco T.·freelance = sprint weeks then dead weeks. my bill finally matchesCBChris B.·dropped my $100/mo plan. last month's real usage: $41HYHana Y.·daily driver is the cheap model, opus only when truly stuck. the logs taught meDKDaniel K.·Pro throttled me mid-refactor one time too many. never againPSPriya S.·90K context on my monorepo used to scare me. cache hits made it pocket changeOFOmar F.·i read the per-call logs like bank statements. every token accountedMTMarco T.·freelance = sprint weeks then dead weeks. my bill finally matchesCBChris B.·dropped my $100/mo plan. last month's real usage: $41HYHana Y.·daily driver is the cheap model, opus only when truly stuck. the logs taught me
ARAlex R.·my agent burned 200K tokens chasing a flaky test — cost $0.61. fine.LWLena W.·didn't write code for 3 weeks. paid $0. my old sub charged me anywayJPJonas P.·2am debugging, no "quota resets in 3 hours". just kept goingSMSofia M.·sent my boss the per-request cost breakdown. budget approved same dayNSNate S.·quota resets always hit right when i entered flow. not anymoreVZVictor Z.·team of 4, no seat licenses to argue about. everyone has their own keyARAlex R.·my agent burned 200K tokens chasing a flaky test — cost $0.61. fine.LWLena W.·didn't write code for 3 weeks. paid $0. my old sub charged me anywayJPJonas P.·2am debugging, no "quota resets in 3 hours". just kept goingSMSofia M.·sent my boss the per-request cost breakdown. budget approved same dayNSNate S.·quota resets always hit right when i entered flow. not anymoreVZVictor Z.·team of 4, no seat licenses to argue about. everyone has their own key
YHYuki H.·student here: trial credit → course project → one $50 top-up. no subscription anxietyKMKenji M.·one key for claude code AND codex cli. finally stopped juggling dashboardsTLTina L.·same prompt side by side, official vs this. same output, lower bill. soldRDRafael D.·the cache savings counter is my new dopamineFGFelix G.·cursor + this endpoint = poor man's unlimited planPMPaul M.·refunded unused credit once just to test them. money came back, then i topped up for realYHYuki H.·student here: trial credit → course project → one $50 top-up. no subscription anxietyKMKenji M.·one key for claude code AND codex cli. finally stopped juggling dashboardsTLTina L.·same prompt side by side, official vs this. same output, lower bill. soldRDRafael D.·the cache savings counter is my new dopamineFGFelix G.·cursor + this endpoint = poor man's unlimited planPMPaul M.·refunded unused credit once just to test them. money came back, then i topped up for real

API cache optimization

High cache hits do the heavy lifting

Agentic tools resend your project context and system prompts every turn. Cache hits bill that repeated context at a fraction of the price — that is where the savings come from.

Cache miss92% full-price range
Input 128KCache read 0Output 4.2KCost $18.60
Cache hit38% full-price range
Input 34KCache read 94KOutput 4.2KCost $6.20Estimated savings $12.40

Example based on common long-context tasks. Actual usage changes with model and task content.

Trackable spend

Every call leaves a receipt

Model, tokens, cache reads, status, credit delta — logged per request. Run a small task, read the receipt, then decide which models earn your budget.

Model and unit price
Input / output usage
Cache-read amount
Per-call cost
Usage credit change
Call time and result

Quick start

Plug in your stack in minutes

Sign up, grab an API Key, point your tool at one endpoint — run your first real task tonight.

1

Claim trial credit

Sign up, grab an API Key. Trial credit covers one real task end to end.

2

Point your tool at us

One BASE_URL, one API Key. Claude Code, Cursor, Codex CLI, Gemini CLI — pick your weapon.

3

Pay per call

Credit burns only when tokens flow. Model, tokens, cache savings, cost — logged per request.

Claude Code

Long-context refactors and multi-step agent tasks.

Configure ANTHROPIC_BASE_URL and API Key.

Cursor

Route your daily editor workflow through one endpoint.

Configure Base URL, API Key, and model name.

Codex CLI

One API Key for model calls inside project tasks.

Configure API endpoint and model per project.

Gemini CLI

Google models with pay-as-you-go billing and full logs.

Configure the Gemini model and CoderPlan API Key.

FAQ

Have another question? Contact our support team anytime.

Yes — the same models, served through direct connections to the official providers. What makes it cheap is scale: the more traffic we serve, the more repeated context hits the cache, and cached tokens bill at a fraction of the standard rate. That is a cost structure, not a compromise. Run a real task on trial credit and diff the output against the official API yourself.

Start vibe coding today

Claim trial credit, point Claude Code or Codex CLI at our endpoint, and ship something tonight.

Start free trialView quick setup
CoderPlanCoderPlan

An AI coding service platform for developers, making common tools easier to connect and manage.

[email protected]

Product

  • Pricing
  • Sign up

Docs

  • Quickstart
  • API Key setup

Supported services

  • Claude Code
  • OpenAI Codex / GPT
  • Gemini

About

  • About
  • Contact us
  • Service Status

© 2026 CoderPlan. All rights reserved.

Privacy Policy|Terms of Service|Refund Policy
Checking...We only process service access and usage records; we do not store your code content or conversation bodies.

Same models, lower prices

The same models as the official APIs, billed by real usage — no subscriptions, no usage windows. Start on free trial credit and run an actual task before you pay.

Direct provider connections and volume-scale cache hits keep costs low, so prices can stay as low as ~4% of official list.

Prices sync with official pricing in real time; the console shows the actual amount charged.

OpenAI
GPT-5.6 SolOpenAI
Save ~95%
Input price$0.25 / 1M
Output price$1.50 / 1M
Cache read$0.03 / 1M
Ratio 0.35xOnline
OpenAI
GPT-5.6 TerraOpenAI
Save ~96%
Input price$0.10 / 1M
Output price$0.60 / 1M
Cache read$0.01 / 1M
Ratio 0.35xOnline
Claude
Claude Opus 5Anthropic
—
Input price$0.36 / 1M
Output price$1.79 / 1M
Cache read$0.04 / 1M
Ratio 0.5xOnline
Claude
Claude Sonnet 5Anthropic
—
Input price$0.14 / 1M
Output price$0.71 / 1M
Cache read$0.01 / 1M
Ratio 0.5xOnline
Gemini
Gemini 3.1 Pro PreviewGoogle
Save ~90%
Input price$0.26 / 1M
Output price$1.54 / 1M
Cache read$0.03 / 1M
Ratio 0.9xOnline
ModelInput priceOutput priceCache readvs. official pricingRatioStatus
OpenAI
GPT2 models
OpenAI
GPT-5.6 SolOpenAI
$0.25 / 1M$1.50 / 1M$0.03 / 1MSave ~95%0.35xOnline
OpenAI
GPT-5.6 TerraOpenAI
$0.10 / 1M$0.60 / 1M$0.01 / 1MSave ~96%0.35xOnline
Claude
Claude2 models
Claude
Claude Opus 5Anthropic
$0.36 / 1M$1.79 / 1M$0.04 / 1M—0.5xOnline
Claude
Claude Sonnet 5Anthropic
$0.14 / 1M$0.71 / 1M$0.01 / 1M—0.5xOnline
Gemini
Gemini1 models
Gemini
Gemini 3.1 Pro PreviewGoogle
$0.26 / 1M$1.54 / 1M$0.03 / 1MSave ~90%0.9xOnline

Unit: USD/1M tokens

Ratio is the multiplier of the billing group serving the model: you pay the model's USD list price × the ratio. The vs-official column already factors in the top-up conversion.

View all 38 model prices

Choose a top-up tier

Top up what you need, when you need it. Every $1 of credit spends like $1 on the official APIs, and credit never expires.

Trial

Kick the tires on your own codebase

$7.14You pay (estimated at current rate)Get 50 USD of API credit≈ 150M tokens≈ 1,260 typical requests
Most popular

Daily development

Ship a small project end to end

$21.43You pay (estimated at current rate)Get 150 USD of API credit≈ 450M tokens≈ 3,780 typical requests

Power user

A full week of heavy agent sessions

$50.00You pay (estimated at current rate)Get 350 USD of API credit≈ 1.05B tokens≈ 8,820 typical requests

Professional

Heavy monthly usage and team collaboration

$100.00You pay (estimated at current rate)Get 700 USD of API credit≈ 2.1B tokens≈ 17,640 typical requests

New here? Start on the free trial credit: connect your tool, run a real task, and top up when the results convince you.

Token and request estimates are based on GPT-5.6 Sol's current platform pricing and recent real Codex usage (about 93.5% cache hits); actual mileage varies with model choice and usage pattern.

Top-ups are processed by Stripe with international cards. International invoices are available; Chinese fapiao is not supported.