Compare DeepSeek Coding Plan, Max, and Pro Max for everyday coding, larger projects, and agent workflows.
Pre-generated private keys are sold from available inventory. After verified payment, your key is assigned and activated on the server; its service period starts at activation.
DeepSeek Coding Plan
1 month
$19.90/month
Renews every month
7 keys available
Models from
DeepSeekFlash
50M / 5 hours · 400M / 7 daysplan tokens
DeepSeek Flash
Works with leading coding tools
Use the exact gateway model IDs in the setup guides
OpenAI Chat Completions, Responses, and Anthropic-compatible APIs
Both payment options share this tier’s key inventory. Taxes, if applicable, appear at checkout.
Prices are in USD. Both payment options draw from the same key inventory for each tier. A pre-generated key is assigned after verified payment; its service period starts when the server activates it. Billing & API keys.
Which Coding Plan fits your work?
DeepSeek Coding Plan
Start here if you mainly need the listed DeepSeek Flash route. Check the DeepSeek catalog before comparing its plan-token allowance.
Multi-Model Coding Plan
Consider this family if you need to switch between the listed models. They share one points allowance, with a different rate for each model. Check models and points rates.
Check fit before paying
You need a compatible coding tool and configuration. These plans provide API access; they do not include an IDE subscription or a ready-to-use chat app. For required search, images or native agent features, confirm support first. For project-specific data requirements, review API data handling.
Compare tiers against your usage
Estimating for DeepSeek Coding Plan. Enter millions of plan tokens (M), not requests, coding hours or lines of code. Use a measured week or your own forecast, including a buffer you choose.
Use this plan’s usage units from Billing & API keys. Confirm the delivered route’s conversion before treating raw model tokens as plan tokens.
Both limits must fit; do not add the windows together. This is a planning estimate, not a live account or stock check. Actual fixed-window timing, usage spikes, rate and concurrency limits still apply.
No tier selected. Enter both estimates to compare. If you do not know your usage, measure a representative workflow before choosing a tier.
DeepSeek Coding Plan · listed prices in USD before any applicable tax
Subscription renews monthly until canceled. Pay once provides one month without automatic renewal. The comparison does not select a payment option or start checkout.
Check that the models, allowance and setup match your workflow. SaveMyToken provides this API access service.
Who it suits
Developers who mainly want DeepSeek Flash for coding and agent tasks in a compatible tool.
What you receive
An assigned API key, service URL, model IDs and usage view in Billing & API keys. API access starts at server activation.
How usage counts
Standard and Max have 5-hour and 7-day limits. Pro Max has a 7-day limit without a 5-hour quota cap. Input and output tokens both count toward the allowance. Unused allowance does not roll over; rate and concurrency limits also apply.
Check your tool
Follow the setup guide for your agent and version. API access is separate from an IDE subscription. Check image support, tool calls and any native features you need.
API data handling
Content your tool includes in a request passes through SaveMyToken and the upstream inference service. Usage records are separate from request content. Review the data-handling policy for your project’s requirements.
Choose how to pay
Subscription renews monthly until canceled. Pay once provides one month without automatic renewal. Check the selected price and any tax before paying.
Cancellation and help
Cancel future renewal in Billing & API keys. Cancellation is separate from a refund request. For delivery or billing problems, contact support with your order number.
The setup templates start with DeepSeek Flash. Add other delivered routes only after confirming their exact IDs and capabilities.
Model catalog — exact request IDs
Model / request ID
Input
Points rate
Reasoning
DeepSeek Flashdeepseek-flash
Text only
1×
Off / Low / High / Max
AGENT SETUP
Connect your coding tool
DeepSeek Coding Plan setup: install, add your delivered connection, declare models, choose effort and verify a file-reading task. Each guide includes configuration downloads and desktop notes.
Choose a tier with available keys and a payment option, then complete checkout. After verified payment, a stocked key is assigned and activated on the server. Find the key, API URL, access period and usage in Billing & keys. Monthly and one-time offers share the same inventory for each tier.
What is the difference between Pay once and Subscription?
All plans provide 1 month of access per paid period. Pay once does not renew automatically. Subscription renews every month. A renewal period is separate from the 5-hour and 7-day allowance windows.
When does my access start?
After verified payment, your assigned key is activated on the server and its API access period begins. Pre-generating a key does not start access; waiting to make your first API request does not delay activation. Subscription charges follow the payment provider's billing schedule. Check Billing & API keys for your access dates and subscription details.
How do the allowance windows work?
Standard and Max have both a 5-hour and 7-day allowance. Pro Max has no 5-hour quota cap, but its weekly, rate and concurrency limits still apply. Plan tokens are the allowance unit; confirm the delivered route's conversion before comparing raw tokens.
When do limits reset? Does renewing reset them?
Fixed allowance windows start when your assigned key is activated on the server. Renewals preserve your key and window schedule; unused allowance does not roll over. Pro Max has no 5-hour quota cap.
How do I cancel or request a refund?
Open Billing & API keys → Manage subscriptions to cancel future renewal. A canceling subscription retains access until its paid period ends. For a refund request or a delivery problem, contact contact@savemytoken.com with your order number. A full refund revokes that purchase's API access.
Where do my prompts and code go?
Content included by your coding tool is processed by the SaveMyToken gateway and the upstream inference service for the requested route. The billing usage ledger records identifiers and usage rather than the prompt or response text. Your tool, operational logs and the upstream service have separate data-handling rules. Review our API data-handling details and contact us if your project has specific retention, training-use or region requirements.
Can I use one configuration for every agent?
Each agent has its own schema, credentials and model picker. Start with its guide below. Codex uses Responses, Claude Code uses Messages, and the other examples use Chat Completions. Desktop applications may need separate credentials or a compatibility endpoint.
Why do some configuration values contain null?
In a Pi or OpenClaw thinkingLevelMap, null disables an unsupported choice. It is not an effort sent to the model. Defaults must select a supported value. An Off control sends none where the gateway supports it; omitting a parameter can leave reasoning on.
Does a gateway model include every native agent feature?
Model access does not by itself include native web search, image support or every provider-specific tool. Confirm those features on the delivered route. The setup guides include a separate file-reading check and instructions for diagnosing tool failures.
DeepSeekFlash