LLM API pricing, billed per token

Each model has its own input and output token rates, billed in USD credit. The request log records the exact credit deducted per call.

$1 of sign-up credit ≈ 10M input tokens on openai/gpt-6-luna, the lowest-priced model in the catalog at $0.10 per 1M tokens in credit. Every $1 you top up becomes $10 in credit ≈ 100M input tokens on that same model.

Top-up to credit conversion at 1 : 10, with the top-up bonus
You pay	Credit received	Bonus	Total credit
$5	$50	—	$50
$10	$100	+$10	$110
$50	$500	+$50	$550
$100	$1,000	+$100	$1,100

A top-up is not a plan tier — the conversion rate has no amount threshold, so any top-up converts at the same rate. A top-up of $10 or more additionally receives a bonus; see the terms above. Fixed 30-day plans are separate from top-ups: a plan gives you a fixed credit pool valid for 30 days, with no auto-renewal.

Billing: Credit is deducted per token of usage. No calls, no charges.
Minimum spend: None. An idle account costs nothing either.
New users: $1 credit on sign-up, no card required.
Credit exhausted: The API returns 403 (insufficient_user_quota). Top up at https://y-api.bestvirtualgoods.com/app/billing — it recovers immediately, and keys stay valid.

Fixed plans

Or buy a fixed 30-day plan

A plan is the other way to pay: one payment buys a fixed credit pool that lasts 30 days, with no auto-renewal. Credit from a top-up never expires; plan credit does — whatever is unused when the 30 days end is gone.

Two ways to pay

Pay as you go

$1 = $10

Top up any amount, spend it whenever. No expiry, no minimum, billed per token at each model’s rate.

Top up

Fixed 30-day plan

From $5

One payment, a fixed credit pool for 30 days. Cheaper per dollar of credit than a top-up at the same amount.

See the plans

Plans

Standard

$60 credit· Valid for 30 days from activation

$12 of credit per $1 paid
One-time payment, no auto-renewal
Unused credit expires with the plan

Pro

$20

$250 credit· Valid for 30 days from activation

$12.5 of credit per $1 paid
One-time payment, no auto-renewal
Unused credit expires with the plan

Max

$50

$630 credit· Valid for 30 days from activation

$12.6 of credit per $1 paid
One-time payment, no auto-renewal
Unused credit expires with the plan

Can I buy a second plan?: One plan at a time. Once the current one expires you can buy again.
What happens to unused credit?: Plan credit expires with the plan. Top-up credit never expires, so the two are kept separate.
Does it renew automatically?: No. A plan is a one-time payment for 30 days; nothing is charged when it ends.

What a dollar buys

Every model, priced in what you actually pay

The rates on the models page are in USD credit. Divide by the 1:10 top-up rate and you get the cash column below — the dollars that leave your card per 1M input tokens. The third column is the same figure read the other way round: how many input tokens one dollar buys.

Cash price, tokens per dollar, and the multiple against each vendor's own published price, for all 48 models
Model ID	You pay / 1M input	$1 buys	vs vendor official
Vendor: DeepSeek
deepseek/deepseek-v4-flash	Free — no credit deducted		$0.22^{1,2,3off-peak rate; a cheaper cache-hit tier also exists; historical official price for this version; current rolling-model pricing may differ}
deepseek/deepseek-v4-pro	$0.05	20M	13.2×$0.66^{1,2off-peak rate; a cheaper cache-hit tier also exists}
deepseek/deepseek-v4.1-flash	$0.015	66.7M	10×$0.15^{1,2off-peak rate; a cheaper cache-hit tier also exists}
deepseek/deepseek-v4-flash-0731	$0.015	66.7M	14.7×$0.22^{1,2,3off-peak rate; a cheaper cache-hit tier also exists; historical official price for this version; current rolling-model pricing may differ}
Vendor: Qwen
qwen/qwen3.8-max	$0.20	5M	8.25×$1.65^{6cheapest of its six regional price tables}
qwen/qwen3.8-flash	$0.02	50M	5.65×$0.113^{6cheapest of its six regional price tables}
Vendor: MiniMax
minimax/minimax-m2.7	Free — no credit deducted		$0.30^{2a cheaper cache-hit tier also exists}
minimax/minimax-m3	$0.03	33.3M	10×$0.30^{2,7a cheaper cache-hit tier also exists; cheapest input-length tier; a longer prompt costs more per token}
minimax/minimax-m3.1-flash-preview	$0.03	33.3M	5×$0.15^{2,4a cheaper cache-hit tier also exists; listed under a different name}
minimax/minimax-m3.1-flash	$0.015	66.7M	Official price unverified
Vendor: Z.ai
z-ai/glm-5.1	$0.14	7.14M	10×$1.40^{2a cheaper cache-hit tier also exists}
z-ai/glm-5.2	$0.14	7.14M	10×$1.40^{2a cheaper cache-hit tier also exists}
z-ai/glm-5.3	$0.14	7.14M	10×$1.40^{2a cheaper cache-hit tier also exists}
z-ai/glm-5.3-flash	$0.015	66.7M	10×$0.15^{2a cheaper cache-hit tier also exists}
Vendor: Moonshot AI
moonshotai/kimi-k3	$0.30	3.33M	10×$3.00^{2a cheaper cache-hit tier also exists}
moonshotai/kimi-k2.6	$0.095	10.5M	10×$0.95^{2a cheaper cache-hit tier also exists}
Vendor: Anthropic
anthropic/claude-opus-4.6	$0.50	2M	10×$5.00^{2a cheaper cache-hit tier also exists}
anthropic/claude-opus-4.7	$0.50	2M	10×$5.00^{2a cheaper cache-hit tier also exists}
anthropic/claude-opus-5	$0.50	2M	10×$5.00^{2a cheaper cache-hit tier also exists}
anthropic/claude-opus-5.5	$0.40	2.5M	10×$4.00^{2a cheaper cache-hit tier also exists}
anthropic/claude-sonnet-5	$0.20	5M	10×$2.00^{2a cheaper cache-hit tier also exists}
anthropic/claude-haiku-4.5	$0.10	10M	10×$1.00^{2a cheaper cache-hit tier also exists}
anthropic/claude-haiku-5.5	$0.015	66.7M	6.67×$0.10^{2,7a cheaper cache-hit tier also exists; cheapest input-length tier; a longer prompt costs more per token}
Vendor: Google
google/gemini-4-argon	$0.40	2.5M	10×$4.00^{2a cheaper cache-hit tier also exists}
google/gemini-3.1-pro-preview	$0.20	5M	10×$2.00^{2,7a cheaper cache-hit tier also exists; cheapest input-length tier; a longer prompt costs more per token}
google/gemini-3.5-flash	$0.20	5M	Not on the vendor’s rate card
google/gemini-3.7-flash	$0.15	6.67M	Not on the vendor’s rate card
google/gemini-3.8-flash	$0.15	6.67M	10×$1.50^{2a cheaper cache-hit tier also exists}
google/gemini-3.1-flash-lite	$0.025	40M	10×$0.25^{2,5a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ}
Vendor: OpenAI
openai/gpt-5.5-pro	$3.00	333K	10×$30.00^{5,7standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-6-astra	$1.00	1M	10×$10.00^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-5.5	$0.50	2M	10×$5.00^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-5.6-sol	$0.50	2M	10×$5.00^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-5.4	$0.25	4M	10×$2.50^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-5.6-terra	$0.20	5M	10×$2.00^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-6-sol	$0.20	5M	10×$2.00^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-6.1-sol	$0.20	5M	10×$2.00^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-5.4-mini	$0.08	12.5M	9.38×$0.75^{2,5a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ}
openai/gpt-5.6-luna	$0.03	33.3M	6.67×$0.20^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
openai/gpt-6-luna	$0.01	100M	10×$0.10^{2,5,7a cheaper cache-hit tier also exists; standard tier; priority and flex tiers differ; cheapest input-length tier; a longer prompt costs more per token}
Vendor: xAI
x-ai/grok-4.6	$0.40	2.5M	5×$2.00^{2,7a cheaper cache-hit tier also exists; cheapest input-length tier; a longer prompt costs more per token}
x-ai/grok-4.7	$0.20	5M	10×$2.00^{2,7a cheaper cache-hit tier also exists; cheapest input-length tier; a longer prompt costs more per token}
Vendor: Other
tencent/hy3	Free — no credit deducted		$0.20
xiaomi/mimo-v2.5	Free — no credit deducted		$0.14^{2a cheaper cache-hit tier also exists}
tencent/hy4-preview	$0.10	10M	12×$1.20
xiaomi/mimo-v2.6-pro	$0.05	20M	8.7×$0.435^{2a cheaper cache-hit tier also exists}
stepfun/step-3.7-flash	$0.02	50M	11×$0.22
xiaomi/mimo-v2.6-flash	$0.018	55.6M	8.89×$0.16

Vendor official prices verified 2026-09-18. Sources are listed on the price comparison page.

1off-peak rate
2a cheaper cache-hit tier also exists
3historical official price for this version; current rolling-model pricing may differ
4listed under a different name
5standard tier; priority and flex tiers differ
6cheapest of its six regional price tables
7cheapest input-length tier; a longer prompt costs more per token

The cash column is the credit rate divided by 10, the top-up rate.
"vs vendor official" compares against the model vendor's own published list price, taking their cheapest published tier — DeepSeek's off-peak rate, Alibaba's cheapest region and shortest input tier, and cache-miss pricing throughout. Aggregator prices are not used here; they are on the comparison page.
OpenAI uses Standard processing with up to 272K input tokens; GPT-5.6 Sol uses its current promotional rate.
Not every model has a comparable figure. 2 of the 44 are not on their vendor's own rate card. For 1 of the 44 we have not verified a price on the vendor's own page. A blank cell means we found no source we could cite, not that the model is cheap.
Free models are listed too, and carry no multiple: their cash price is $0, so there is no ratio to compute. The figure in that column is the vendor's own list price.
Free status is set by our upstream provider and can be withdrawn — when it is, these calls start billing at the listed rate and your code does not change. The models page always shows the current state.
Vendor APIs bill cached input far below their cache-miss rate, and we have no equivalent tier. On workloads that hit the cache constantly, the vendor can be cheaper than us — the comparison page has the numbers.

See the full market comparison Put your own volume through the calculator OpenRouter alternative: Y-API vs OpenRouter →

Up front

"$1 becomes $10" is credit, not a discount coupon

You pay $1 and your account gains $10 in credit. Credit burns at each model's multiplier, which varies widely — so it is not "official pricing at 10% off". Treat the actual deductions in the request log as the real cost.

Invitations

Bring someone with you and you both get credit

Every account has an invitation link in the console. When someone signs up through it and makes their first API call, you and they each receive $1 in credit, once. Sign-up credit still applies on top, so an invited account ends up with $2 in credit — about 20M input tokens on openai/gpt-6-luna — without adding a card.

Your invitation link

Start now

Start for free Read the guide first