0%gateway fees
- Pay the model rate, with nothing added on top.
- No seats, no monthly minimum, no commitment.
- Top up any amount and spend it on any model.
Spending a lot every month?Ask about volume discounts
Pay for tokens. That's the whole bill.
The rate beside each model is the whole price — there is no gateway fee on top of it. Pay as you go for what you send, or take a flat monthly Token Plan — the models, the keys, and the API are the same either way.
Two ways to pay
Both draw on the same catalogue and the same API. They differ only in how you put money in.
Token Plans: 3× the usage you pay for
Token Plans · Solo
3×You pay
$20
You get
$60
$40 of extra usage every month, at no extra cost.
- Pro · pay $100 a month
- get $300 of usage
- Max · pay $200 a month
- get $600 of usage
Image generation included, at the same 3× usage
- No hourly limits
- No daily limits
- No weekly limits
Volume discounts
Sending serious volume? Pay less per token.
0% gateway fees is where pay as you go starts, not where it ends. If your team spends steadily every month, tell us roughly how much and we will put together a discount on the models you use most.
- Lower rates on the models you send the most traffic to
- Applied to your workspace, so every project and key gets them
- Still no seats, no fees, and no lock-in
Talk to us about volume pricing
Or email us at support@inferray.com
No hourly, daily, or weekly limits
Plenty of token plans hand out what you paid for in rations — a window every few hours, a cap per day, a ceiling per week. Ours don't. Your whole month is there from day one.
Usage rationed into windows
- Usage resets every few hours
- A daily cap on top of that
- A weekly ceiling on top of both
- Hit one mid-task and you wait
One monthly allowance, on your schedule
- No hourly limits
- No daily limits
- No weekly limits
- Spend the month in a day, or across thirty
Referrals stretch it even further
Join with a friend's code and every plan carries 20% more usage for your first 3 months. Share your own code and earn 20% of what the people you bring pay.
Join with a referral code
3.6×You pay
$20
You get
$72
$60+ $12 · +20% referral bonus
- Pro · pay $100 a month
- $300$360
- Max · pay $200 a month
- $600$720
20% extra credit on every Token Plan you buy in your first 3 months. Add the code when you sign up.
Earn 20% of every plan your referrals buy
Paid on each person's Token Plan for their first 3 months, for as many people as you bring.
5 friends on Solo
$20 a month to you
That's what your own Solo plan costs.
Every model, every price
Text models are priced per 1M tokens. Image models are priced the way their provider bills them — per generated image, per request, or per token — so each row shows its own unit. What you see is what you pay, with no gateway fee on top.
Anthropic
12 models| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| Claude Fable 5.1claude-fable-5-1 | 1M | $10 | $0.25 | $50 |
| Claude Opus 5.5claude-opus-5-5 | 1M | $4 | $0.20 | $20 |
| Claude Fable 5claude-fable-5 | 1M | $10 | $1 | $50 |
| Claude Opus 5claude-opus-5 | 1M | $5 | $0.50 | $25 |
| Claude Opus 4.8claude-opus-4-8 | 1M | $5 | $0.50 | $25 |
| Claude Opus 4.7claude-opus-4-7 | 1M | $5 | $0.50 | $25 |
| Claude Opus 4.6claude-opus-4-6 | 1M | $5 | $0.50 | $25 |
| Claude Sonnet 5.5claude-sonnet-5-5 | 1M | $2 | $0.10 | $10 |
| Claude Sonnet 5claude-sonnet-5 | 1M | $2 | $0.20 | $10 |
| Claude Sonnet 4.6claude-sonnet-4-6 | 1M | $3 | $0.30 | $15 |
| Claude Haiku 5.5claude-haiku-5-5 | 1M | $0.10 | $0.01 | $0.50 |
| Claude Haiku 4.5claude-haiku-4-5 | 200K | $1 | $0.10 | $5 |
OpenAI
14 models| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| GPT-6 Astragpt-6-astra | 1.1M | $10 | $1 | $50 |
| GPT-6.1 Solgpt-6.1-sol | 1.1M | $2 | $0.10 | $10 |
| GPT-6.1 Terragpt-6.1-terra | 1.1M | $1 | $0.05 | $5 |
| GPT-6 Solgpt-6-sol | 1.1M | $2 | $0.20 | $10 |
| GPT-6 Lunagpt-6-luna | 1.1M | $0.10 | $0.01 | $0.50 |
| GPT-5.6 Solgpt-5.6-sol | 1.1M | $4 | $0.40 | $20 |
| GPT-5.6 Terragpt-5.6-terra | 1.1M | $2 | $0.20 | $12 |
| GPT-5.6 Lunagpt-5.6-luna | 1.1M | $0.20 | $0.02 | $1.20 |
| GPT-5.5gpt-5.5 | 1.1M | $5 | $0.50 | $30 |
| GPT-5.4gpt-5.4 | 1.1M | $2.50 | $0.25 | $15 |
| GPT-5.2gpt-5.2 | 400K | $1.75 | $0.17 | $14 |
| GPT Image 2.5 Sunburstgpt-image-2.5-sunburst | — | $30 / 1M image tokens | ||
| GPT Image 2.5 Flaregpt-image-2.5-flare | — | $30 / 1M image tokens | ||
| GPT Image 2gpt-image-2 | — | $30 / 1M image tokens | ||
| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| Gemini 3 Pro Image (Preview)gemini-3-pro-image-preview | — | $0.13–$0.24 / image | ||
| Gemini 3 Pro Imagegemini-3-pro-image | — | $0.13–$0.24 / image | ||
| Gemini 3.1 Flash Imagegemini-3.1-flash-image | — | $0.045–$0.15 / image | ||
| Gemini 3.1 Flash Lite Imagegemini-3.1-flash-lite-image | — | $0.034 / image | ||
| Gemini Nano Banana 2.1gemini-nano-banana-2.1 | — | $0.034–$0.076 / image | ||
| Gemini 2.5 Flash Imagegemini-2.5-flash-image | — | $0.039 / image | ||
| Gemini 4 Argongemini-4-argon | 1.0M | $4 | $0.20 | $20 |
| Gemini 3.8 Flashgemini-3.8-flash | 1.0M | $0.75 | $0.07 | $3.75 |
| Gemini 3.5 Flashgemini-3.5-flash | 1.0M | $1.50 | $0.15 | $9 |
| Gemini 3.5 Flash Litegemini-3.5-flash-lite | 1.0M | $0.30 | $0.03 | $2.50 |
| Gemini 3.1 Flash Litegemini-3.1-flash-lite | 1.0M | $0.25 | $0.03 | $1.50 |
| Gemini 3.1 Pro (Preview)gemini-3.1-pro-preview | 1.0M | $2 | $0.20 | $12 |
| Gemini 2.5 Progemini-2.5-pro | 1.0M | $1.25 | $0.13 | $10 |
DeepSeek
1 model| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| DeepSeek V4.1 Flashdeepseek-v4.1-flash | 1.1M | $0.15 | $0.00 | $0.60 |
Z.ai
2 models| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| GLM-5.3glm-5.3 | 1M | $1.40 | $0.26 | $4.40 |
| GLM-5.2glm-5.2 | 1M | $1.40 | $0.26 | $4.40 |
Moonshot AI
2 models| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| Kimi K3kimi-k3 | 1.0M | $3 | $0.30 | $15 |
| Kimi K2.6kimi-k2.6 | 262K | $0.95 | $0.16 | $4 |
Alibaba
1 model| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| Qwen3.8 Maxqwen3.8-max | 984K | $2 | $0.25 | $6 |
MiniMax
1 model| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| MiniMax M3minimax-m3 | 512K | $0.60 | $0.12 | $2.40 |
ByteDance
1 model| Model | Context | Input | Cached input | Output |
|---|---|---|---|---|
| Seedance 2.0 Miniseedance-2-0-mini | — | $0.0378–$0.0756 / second | ||
Four things you never get charged for
- No seats
- Invite the whole team. You pay for tokens, not headcount.
- No commitment
- Pay as you go and nothing renews. Top up when you want to, or take a Token Plan if a flat monthly price suits you better.
- No minimum
- Spend $5 this month and $5,000 the next. There is no minimum to meet before the rates apply.
- No gateway fee
- Nothing is added on top of the model rate, whether you send one request or a million.
Questions worth answering
- Pay as you go or a Token Plan?
- Pay as you go if your usage is uneven or occasional — you only ever pay for what you send. Take a plan once you are spending steadily every month, because the credit it buys works out cheaper than topping up the same amount. Plans cover the text models and image generation, both at 3× usage.
- Is it the same model I'd get direct?
- Yes. Same model, same version, same answers. The only thing that changes is what it costs you.
- Do you charge gateway fees?
- No. You pay the rate shown for the model you called, and nothing is added on top of it. Seats, projects, and API keys are free, and there's no tier to reach before that applies.
- Do you offer volume discounts?
- Yes. If you spend steadily every month, contact us with your expected usage and the models you rely on, and we will offer a discount that applies to your whole workspace on top of 0% gateway fees.
- Why is cached input cheaper?
- Providers price input they have already seen well below fresh input, and that price is passed straight through. Workloads that reuse a long system prompt or a big document pay noticeably less than the input column suggests.
- Does a Token Plan have hourly, daily, or weekly limits?
- No. Your whole month's credit is available from the day your plan starts. Spend it in one afternoon or spread it across the month — nothing locks you out for a few hours or until next week.
- What happens when my balance runs out?
- Requests stop rather than silently overspending. Turn on auto top-up in the console and your balance refills before that happens.
- Do I get an invoice?
- Every top-up produces a receipt, and the console breaks spend down by project, key, and model so you can see where it went.
Start with no gateway fees
Create a key, top up, and your very next request is billed at the rate on this page.