Per token
- Prices in the table above, billed to the millionth of a cent
- Prepaid balance, $5 to $2000 per top-up
- Balance never expires
USD per 1M tokens
Pricing
Each price is 2% of the vendor's official list price (struck through). Cached input is billed only when the provider reports a cache hit. Reasoning tokens count as output.
| Model | Input | Cached input | Output |
|---|---|---|---|
| DeepSeek V4.1 Flashdeepseek-v4.1-flash | $0.006$0.3 | $0.00012$0.006 | $0.024$1.2 |
| GLM-5.3 Flashglm-5.3-flash | $0.003$0.15 | $0.0006$0.03 | $0.01$0.5 |
List prices from DeepSeek and Z.ai, checked 2026-11-05. DeepSeek publishes peak and off-peak rates; we discount from the peak rate, so the price is the same at every hour.
Independent resellerNot affiliated with DeepSeek or Z.ai.
Two ways to pay
Plans
Pay as you go fits occasional or bursty use: you pay only for the tokens you send. Unlimited fits steady, heavy use such as long agent sessions: a flat price for 30 days with no per-token charge, priced by how many requests may run at the same time (slots). Paid up front in USDT or USDC.
$10/ 30 days
$5.00 per slot
- 2 requests running at the same time
- No per-token charge while it is active
- No auto-renewal: it ends after 30 days
$20/ 30 days
$4.00 per slot
- 5 requests running at the same time
- No per-token charge while it is active
- No auto-renewal: it ends after 30 days
$40/ 30 days
$4.00 per slot
- 10 requests running at the same time
- No per-token charge while it is active
- No auto-renewal: it ends after 30 days
More than 10 slots
$40 + $4 per slot above 10, up to 100
$80 / 30 days · $4.00 per slot
20 slots $80 · 50 slots $200 · 100 slots $400
Changing the slot count while a plan is active starts the new plan at once for 30 days, and the days you had not used yet are converted into extra days at the two plans' prices (12 unused days of a $10 plan become 3 extra days on a $40 plan). Paying for the same slot count again adds 30 days after your current end.
Limits
Apply to every plan
Every plan has the same request limits, pay as you go and the free trial included. Details and error codes are in the docs.
Input per request200,000tokens; more is rejected with HTTP 400
Output per request64,000tokens; a larger max_tokens is lowered to this
Unlimited slots2 to 100requests at once, as bought; one more gets HTTP 429, no queue
Rate limitStill onper key, on every plan; see the 429 error
Free trial
Try before you pay
New accounts get a free 1-hour trial with up to 1M tokens; the clock starts at your first API call.
Worked example
A long agent session
200 requests averaging 40k input tokens (75% cache hits) and 1.5k output tokens.
| Model | At list price | Here |
|---|---|---|
| DeepSeek V4.1 Flash | $0.9960 | $0.0199 |
| GLM-5.3 Flash | $0.6300 | $0.0126 |
Pay as you go
Top-ups
$5 to $2000 per payment, in USDT · Tron, USDC · Solana. Balance never expires. Each key is limited to 120 requests per minute by default; ask if you need more.