What it costs
API usage is the provider's own USD list price for the model you called, plus a flat 20% markup, converted to Iranian Toman and deducted from your wallet. That is the whole rule, on every model and every endpoint. Chat plans are separate and optional; nothing about the API requires a subscription.
List price, plus twenty percent
There is no gateway rate card to learn. Whatever OpenAI, Anthropic, Google or DeepSeek charges for the model you called is multiplied by 1.2 and converted to Toman. Both inputs are public (the provider's published price, and the token counts returned in the response), so you can check any line on your bill yourself.
# what you are billed for one call cost_usd = provider_list_price(model, prompt_tokens, completion_tokens) billed_usd = cost_usd * 1.20 # flat 20%, every model, every endpoint billed_toman = to_toman(billed_usd) # deducted from your wallet balance # the token counts in that formula are the ones the API hands back resp = client.chat.completions.create(...) resp.usage.prompt_tokens, resp.usage.completion_tokens
Live per-model rates in Toman are on the pricing page and the models page; both read from the same table the biller uses, as does the rate table below. To size a workload before running it, the cost calculator and token counter take a prompt and a model and return the Toman figure.
Every model, per 1,000 tokens
Toman, input and output priced separately, read live from the same table the biller charges against — so these are the numbers your wallet will actually be debited by, not a transcription of them. Rates move when a provider changes its list price or when the daily USD rate is refreshed. Reasoning models also spend hidden "thinking" tokens before answering; those are billed as output.
Reasoning models
For work that needs to think — complex code, long analysis, multi-step agents.
| Model | Provider | Input · Toman / 1K | Output · Toman / 1K |
|---|---|---|---|
| gpt-5.5 | OpenAI | 1,405 | 8,431 |
| gpt-5.5-pro | OpenAI | 8,431 | 50,587 |
| gpt-5.4-pro | OpenAI | 8,431 | 50,587 |
| gpt-5.3-codex | OpenAI | 492 | 3,935 |
| gpt-5.2 | OpenAI | 492 | 3,935 |
| gpt-5.2-codex | OpenAI | 492 | 3,935 |
| gpt-5.2-pro | OpenAI | 5,902 | 47,215 |
| gpt-5.1-codex | OpenAI | 351 | 2,810 |
| gpt-5.1-codex-max | OpenAI | 351 | 2,810 |
| gpt-5.1-codex-mini | OpenAI | 70 | 562 |
| gpt-5 | OpenAI | 351 | 2,810 |
| gpt-5-codex | OpenAI | 351 | 2,810 |
| gpt-5-mini | OpenAI | 70 | 562 |
| gpt-5-pro | OpenAI | 4,216 | 33,725 |
| o4-mini | OpenAI | 309 | 1,237 |
| o3 | OpenAI | 562 | 2,248 |
| o3-mini | OpenAI | 309 | 1,237 |
| o1 | OpenAI | 4,216 | 16,862 |
| o1-pro | OpenAI | 42,156 | 168,624 |
| claude-fable-5-1 | Anthropic | 2,810 | 14,052 |
| claude-fable-5 | Anthropic | 2,810 | 14,052 |
| claude-opus-5 | Anthropic | 1,405 | 7,026 |
| claude-sonnet-5 | Anthropic | 562 | 2,810 |
| claude-opus-4-8 | Anthropic | 1,405 | 7,026 |
| claude-opus-4-7 | Anthropic | 1,405 | 7,026 |
| claude-opus-4-6 | Anthropic | 1,405 | 7,026 |
| claude-opus-4-5 | Anthropic | 1,405 | 7,026 |
| gemini-3.1-pro-preview | 562 | 3,372 | |
| gemini-3.1-pro-preview-customtools | 562 | 3,372 | |
| gemini-2.5-pro | 351 | 2,810 | |
| gemini-pro-latest | 351 | 2,810 | |
| deepseek-v4-pro | DeepSeek | 371 | 1,113 |
| deepseek-reasoner | DeepSeek | 79 | 118 |
Model: gpt-5.5
- Provider
- OpenAI
- Input · Toman / 1K
- 1,405
- Output · Toman / 1K
- 8,431
Model: gpt-5.5-pro
- Provider
- OpenAI
- Input · Toman / 1K
- 8,431
- Output · Toman / 1K
- 50,587
Model: gpt-5.4-pro
- Provider
- OpenAI
- Input · Toman / 1K
- 8,431
- Output · Toman / 1K
- 50,587
Model: gpt-5.3-codex
- Provider
- OpenAI
- Input · Toman / 1K
- 492
- Output · Toman / 1K
- 3,935
Model: gpt-5.2
- Provider
- OpenAI
- Input · Toman / 1K
- 492
- Output · Toman / 1K
- 3,935
Model: gpt-5.2-codex
- Provider
- OpenAI
- Input · Toman / 1K
- 492
- Output · Toman / 1K
- 3,935
Model: gpt-5.2-pro
- Provider
- OpenAI
- Input · Toman / 1K
- 5,902
- Output · Toman / 1K
- 47,215
Model: gpt-5.1-codex
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
25 more models
Model: gpt-5.1-codex-max
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-5.1-codex-mini
- Provider
- OpenAI
- Input · Toman / 1K
- 70
- Output · Toman / 1K
- 562
Model: gpt-5
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-5-codex
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-5-mini
- Provider
- OpenAI
- Input · Toman / 1K
- 70
- Output · Toman / 1K
- 562
Model: gpt-5-pro
- Provider
- OpenAI
- Input · Toman / 1K
- 4,216
- Output · Toman / 1K
- 33,725
Model: o4-mini
- Provider
- OpenAI
- Input · Toman / 1K
- 309
- Output · Toman / 1K
- 1,237
Model: o3
- Provider
- OpenAI
- Input · Toman / 1K
- 562
- Output · Toman / 1K
- 2,248
Model: o3-mini
- Provider
- OpenAI
- Input · Toman / 1K
- 309
- Output · Toman / 1K
- 1,237
Model: o1
- Provider
- OpenAI
- Input · Toman / 1K
- 4,216
- Output · Toman / 1K
- 16,862
Model: o1-pro
- Provider
- OpenAI
- Input · Toman / 1K
- 42,156
- Output · Toman / 1K
- 168,624
Model: claude-fable-5-1
- Provider
- Anthropic
- Input · Toman / 1K
- 2,810
- Output · Toman / 1K
- 14,052
Model: claude-fable-5
- Provider
- Anthropic
- Input · Toman / 1K
- 2,810
- Output · Toman / 1K
- 14,052
Model: claude-opus-5
- Provider
- Anthropic
- Input · Toman / 1K
- 1,405
- Output · Toman / 1K
- 7,026
Model: claude-sonnet-5
- Provider
- Anthropic
- Input · Toman / 1K
- 562
- Output · Toman / 1K
- 2,810
Model: claude-opus-4-8
- Provider
- Anthropic
- Input · Toman / 1K
- 1,405
- Output · Toman / 1K
- 7,026
Model: claude-opus-4-7
- Provider
- Anthropic
- Input · Toman / 1K
- 1,405
- Output · Toman / 1K
- 7,026
Model: claude-opus-4-6
- Provider
- Anthropic
- Input · Toman / 1K
- 1,405
- Output · Toman / 1K
- 7,026
Model: claude-opus-4-5
- Provider
- Anthropic
- Input · Toman / 1K
- 1,405
- Output · Toman / 1K
- 7,026
Model: gemini-3.1-pro-preview
- Provider
- Input · Toman / 1K
- 562
- Output · Toman / 1K
- 3,372
Model: gemini-3.1-pro-preview-customtools
- Provider
- Input · Toman / 1K
- 562
- Output · Toman / 1K
- 3,372
Model: gemini-2.5-pro
- Provider
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gemini-pro-latest
- Provider
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: deepseek-v4-pro
- Provider
- DeepSeek
- Input · Toman / 1K
- 371
- Output · Toman / 1K
- 1,113
Model: deepseek-reasoner
- Provider
- DeepSeek
- Input · Toman / 1K
- 79
- Output · Toman / 1K
- 118
Chat models
General-purpose conversation, drafting, summarising and extraction.
| Model | Provider | Input · Toman / 1K | Output · Toman / 1K |
|---|---|---|---|
| gpt-6-astra | OpenAI | 2,810 | 14,052 |
| gpt-5.6 | OpenAI | 1,124 | 5,621 |
| gpt-5.6-luna | OpenAI | 56 | 337 |
| gpt-5.6-sol | OpenAI | 1,124 | 5,621 |
| gpt-5.6-terra | OpenAI | 562 | 3,372 |
| gpt-5.4 | OpenAI | 703 | 4,216 |
| gpt-5.4-mini | OpenAI | 211 | 1,265 |
| gpt-5.4-nano | OpenAI | 56 | 351 |
| gpt-5.3-chat-latest | OpenAI | 492 | 3,935 |
| gpt-5.2-chat-latest | OpenAI | 492 | 3,935 |
| gpt-5.1 | OpenAI | 351 | 2,810 |
| gpt-5.1-chat-latest | OpenAI | 351 | 2,810 |
| gpt-5-chat | OpenAI | 351 | 2,810 |
| gpt-5-chat-latest | OpenAI | 351 | 2,810 |
| gpt-5-nano | OpenAI | 14 | 112 |
| gpt-5-search-api | OpenAI | 351 | 2,810 |
| gpt-4-0613 | OpenAI | 8,431 | 16,862 |
| gpt-4.1 | OpenAI | 562 | 2,248 |
| gpt-4.1-mini | OpenAI | 112 | 450 |
| gpt-4.1-nano | OpenAI | 28 | 112 |
| gpt-4 | OpenAI | 8,431 | 16,862 |
| gpt-4-turbo | OpenAI | 2,810 | 8,431 |
| gpt-4o | OpenAI | 703 | 2,810 |
| gpt-4o-mini | OpenAI | 42 | 169 |
| gpt-4o-mini-search-preview | OpenAI | 42 | 169 |
| gpt-4o-search-preview | OpenAI | 703 | 2,810 |
| gpt-3.5-turbo | OpenAI | 141 | 422 |
| chat-latest | OpenAI | 1,405 | 8,431 |
| claude-sonnet-4-6 | Anthropic | 843 | 4,216 |
| claude-haiku-4-5 | Anthropic | 281 | 1,405 |
| claude-sonnet-4-5 | Anthropic | 843 | 4,216 |
| claude-3-5-haiku | Anthropic | 281 | 1,405 |
| claude-3-5-sonnet | Anthropic | 843 | 4,216 |
| gemma-4-31b-it | 28 | 112 | |
| gemma-4-26b-a4b-it | 28 | 112 | |
| gemini-3.8-flash | 211 | 1,054 | |
| gemini-3.7-flash | 211 | 1,054 | |
| gemini-3.6-flash | 211 | 1,054 | |
| gemini-3.5-flash | 422 | 2,529 | |
| gemini-3.5-flash-lite | 84 | 703 | |
| gemini-3.1-flash-lite | 70 | 422 | |
| gemini-3.1-flash-lite-preview | 70 | 422 | |
| gemini-3-flash-preview | 141 | 843 | |
| gemini-2.5-flash | 84 | 703 | |
| gemini-2.5-flash-lite | 28 | 112 | |
| gemini-omni-1.1-flash | 422 | 2,529 | |
| gemini-flash-latest | 84 | 703 | |
| gemini-flash-lite-latest | 28 | 112 | |
| gemini-omni-flash-preview | 422 | 2,529 | |
| deepseek-v4-flash | DeepSeek | 124 | 371 |
| deepseek-v4-flash-vision-exp | DeepSeek | 124 | 371 |
| deepseek-chat | DeepSeek | 79 | 118 |
| deepseek-coder | DeepSeek | 39 | 79 |
| deepseek-flash | DeepSeek | 84 | 337 |
Model: gpt-6-astra
- Provider
- OpenAI
- Input · Toman / 1K
- 2,810
- Output · Toman / 1K
- 14,052
Model: gpt-5.6
- Provider
- OpenAI
- Input · Toman / 1K
- 1,124
- Output · Toman / 1K
- 5,621
Model: gpt-5.6-luna
- Provider
- OpenAI
- Input · Toman / 1K
- 56
- Output · Toman / 1K
- 337
Model: gpt-5.6-sol
- Provider
- OpenAI
- Input · Toman / 1K
- 1,124
- Output · Toman / 1K
- 5,621
Model: gpt-5.6-terra
- Provider
- OpenAI
- Input · Toman / 1K
- 562
- Output · Toman / 1K
- 3,372
Model: gpt-5.4
- Provider
- OpenAI
- Input · Toman / 1K
- 703
- Output · Toman / 1K
- 4,216
Model: gpt-5.4-mini
- Provider
- OpenAI
- Input · Toman / 1K
- 211
- Output · Toman / 1K
- 1,265
Model: gpt-5.4-nano
- Provider
- OpenAI
- Input · Toman / 1K
- 56
- Output · Toman / 1K
- 351
46 more models
Model: gpt-5.3-chat-latest
- Provider
- OpenAI
- Input · Toman / 1K
- 492
- Output · Toman / 1K
- 3,935
Model: gpt-5.2-chat-latest
- Provider
- OpenAI
- Input · Toman / 1K
- 492
- Output · Toman / 1K
- 3,935
Model: gpt-5.1
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-5.1-chat-latest
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-5-chat
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-5-chat-latest
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-5-nano
- Provider
- OpenAI
- Input · Toman / 1K
- 14
- Output · Toman / 1K
- 112
Model: gpt-5-search-api
- Provider
- OpenAI
- Input · Toman / 1K
- 351
- Output · Toman / 1K
- 2,810
Model: gpt-4-0613
- Provider
- OpenAI
- Input · Toman / 1K
- 8,431
- Output · Toman / 1K
- 16,862
Model: gpt-4.1
- Provider
- OpenAI
- Input · Toman / 1K
- 562
- Output · Toman / 1K
- 2,248
Model: gpt-4.1-mini
- Provider
- OpenAI
- Input · Toman / 1K
- 112
- Output · Toman / 1K
- 450
Model: gpt-4.1-nano
- Provider
- OpenAI
- Input · Toman / 1K
- 28
- Output · Toman / 1K
- 112
Model: gpt-4
- Provider
- OpenAI
- Input · Toman / 1K
- 8,431
- Output · Toman / 1K
- 16,862
Model: gpt-4-turbo
- Provider
- OpenAI
- Input · Toman / 1K
- 2,810
- Output · Toman / 1K
- 8,431
Model: gpt-4o
- Provider
- OpenAI
- Input · Toman / 1K
- 703
- Output · Toman / 1K
- 2,810
Model: gpt-4o-mini
- Provider
- OpenAI
- Input · Toman / 1K
- 42
- Output · Toman / 1K
- 169
Model: gpt-4o-mini-search-preview
- Provider
- OpenAI
- Input · Toman / 1K
- 42
- Output · Toman / 1K
- 169
Model: gpt-4o-search-preview
- Provider
- OpenAI
- Input · Toman / 1K
- 703
- Output · Toman / 1K
- 2,810
Model: gpt-3.5-turbo
- Provider
- OpenAI
- Input · Toman / 1K
- 141
- Output · Toman / 1K
- 422
Model: chat-latest
- Provider
- OpenAI
- Input · Toman / 1K
- 1,405
- Output · Toman / 1K
- 8,431
Model: claude-sonnet-4-6
- Provider
- Anthropic
- Input · Toman / 1K
- 843
- Output · Toman / 1K
- 4,216
Model: claude-haiku-4-5
- Provider
- Anthropic
- Input · Toman / 1K
- 281
- Output · Toman / 1K
- 1,405
Model: claude-sonnet-4-5
- Provider
- Anthropic
- Input · Toman / 1K
- 843
- Output · Toman / 1K
- 4,216
Model: claude-3-5-haiku
- Provider
- Anthropic
- Input · Toman / 1K
- 281
- Output · Toman / 1K
- 1,405
Model: claude-3-5-sonnet
- Provider
- Anthropic
- Input · Toman / 1K
- 843
- Output · Toman / 1K
- 4,216
Model: gemma-4-31b-it
- Provider
- Input · Toman / 1K
- 28
- Output · Toman / 1K
- 112
Model: gemma-4-26b-a4b-it
- Provider
- Input · Toman / 1K
- 28
- Output · Toman / 1K
- 112
Model: gemini-3.8-flash
- Provider
- Input · Toman / 1K
- 211
- Output · Toman / 1K
- 1,054
Model: gemini-3.7-flash
- Provider
- Input · Toman / 1K
- 211
- Output · Toman / 1K
- 1,054
Model: gemini-3.6-flash
- Provider
- Input · Toman / 1K
- 211
- Output · Toman / 1K
- 1,054
Model: gemini-3.5-flash
- Provider
- Input · Toman / 1K
- 422
- Output · Toman / 1K
- 2,529
Model: gemini-3.5-flash-lite
- Provider
- Input · Toman / 1K
- 84
- Output · Toman / 1K
- 703
Model: gemini-3.1-flash-lite
- Provider
- Input · Toman / 1K
- 70
- Output · Toman / 1K
- 422
Model: gemini-3.1-flash-lite-preview
- Provider
- Input · Toman / 1K
- 70
- Output · Toman / 1K
- 422
Model: gemini-3-flash-preview
- Provider
- Input · Toman / 1K
- 141
- Output · Toman / 1K
- 843
Model: gemini-2.5-flash
- Provider
- Input · Toman / 1K
- 84
- Output · Toman / 1K
- 703
Model: gemini-2.5-flash-lite
- Provider
- Input · Toman / 1K
- 28
- Output · Toman / 1K
- 112
Model: gemini-omni-1.1-flash
- Provider
- Input · Toman / 1K
- 422
- Output · Toman / 1K
- 2,529
Model: gemini-flash-latest
- Provider
- Input · Toman / 1K
- 84
- Output · Toman / 1K
- 703
Model: gemini-flash-lite-latest
- Provider
- Input · Toman / 1K
- 28
- Output · Toman / 1K
- 112
Model: gemini-omni-flash-preview
- Provider
- Input · Toman / 1K
- 422
- Output · Toman / 1K
- 2,529
Model: deepseek-v4-flash
- Provider
- DeepSeek
- Input · Toman / 1K
- 124
- Output · Toman / 1K
- 371
Model: deepseek-v4-flash-vision-exp
- Provider
- DeepSeek
- Input · Toman / 1K
- 124
- Output · Toman / 1K
- 371
Model: deepseek-chat
- Provider
- DeepSeek
- Input · Toman / 1K
- 79
- Output · Toman / 1K
- 118
Model: deepseek-coder
- Provider
- DeepSeek
- Input · Toman / 1K
- 39
- Output · Toman / 1K
- 79
Model: deepseek-flash
- Provider
- DeepSeek
- Input · Toman / 1K
- 84
- Output · Toman / 1K
- 337
Embedding models
Turn text into vectors for semantic search, RAG and clustering. Output is a vector, not text, so only the input side is charged.
| Model | Provider | Input · Toman / 1K |
|---|---|---|
| text-embedding-3-large | OpenAI | 37 |
| text-embedding-3-small | OpenAI | 6 |
Model: text-embedding-3-large
- Provider
- OpenAI
- Input · Toman / 1K
- 37
Model: text-embedding-3-small
- Provider
- OpenAI
- Input · Toman / 1K
- 6
Wallet for the API, plans for chat
- API · pay as you go
- Deducted per call from wallet credit at list price plus 20%. No plan required, no monthly minimum, no expiry on credit you bought.
- Chat · free
- A 100,000-Toman allowance every 30 days, auto-renewing, with a 40,000-Toman weekly cap, on gpt-4o-mini, claude-haiku-4-5 and gemini-2.5-flash.
- Chat · Base
- 500,000 Toman per month.
- Chat · Pro
- 2,000,000 Toman per month.
- Chat · Max
- 10,000,000 Toman per month.
- Top-ups
- Zarinpal, minimum 100,000 Toman. A local card is all that is needed at any point in the flow.
Per-plan allowances, weekly caps and model ranges are listed on the plans page. The hosted chat is a web app that installs as a PWA on phone or desktop; there is no native app and 1xAi is not in any app store.
What you get before paying anything
- [01]
The free chat plan. 100,000 Toman of chat allowance every 30 days, renewing automatically, capped at 40,000 Toman per week, on the three fast models. Signing up needs an email — no phone number and no foreign card.
- [02]
The signup gift wheel. One server-drawn spin per new account, worth from 100,000 to 1,000,000 Toman in wallet credit. It never expires, and it can be spent on API calls as well as chat, which makes it the straightforward way to benchmark the endpoint against your own workload before paying for anything.
What this pricing does not promise
Provider list prices are the providers' to change, and so is the Toman conversion; the 20% rule is what stays fixed. Credit bought with money does not expire, but plan allowances are periodic by definition: they reset rather than accumulate. And a gateway cannot promise a provider's behaviour: model availability and usage policy remain theirs.
1xAi is an independent gateway. It is not affiliated with, endorsed by, or a reseller for OpenAI, Anthropic, Google or DeepSeek. Requests are relayed to those providers' official APIs, so each provider's own usage policies apply to what their models will and will not do, and their model availability is theirs to change. Current reachability is published on the status page.
How much does the 1xAi API cost?
Every model is billed at the provider's own USD list price plus a flat 20% markup, converted to Iranian Toman and deducted from your wallet as you use it. The markup is the same 20% on every model and every endpoint: there is no per-seat licence, no monthly minimum and no separate rate card for the gateway.
Do I need a subscription to use the API?
No. API access is pay-as-you-go from wallet credit. The monthly plans are chat plans for the hosted web app; if you only want API calls, top up the wallet and start.
What are the chat plans?
Four tiers. Free: a 100,000-Toman chat allowance every 30 days, renewing automatically, with a 40,000-Toman weekly cap, on gpt-4o-mini, claude-haiku-4-5 and gemini-2.5-flash. Base at 500,000 Toman/month, Pro at 2,000,000 Toman/month and Max at 10,000,000 Toman/month, each with a larger allowance and a wider model range; the per-plan details are on the plans page.
How do I top up from Iran?
Through Zarinpal, a local Iranian payment gateway, with a minimum top-up of 100,000 Toman. No international card, PayPal account or foreign intermediary is involved.
Is there any free credit?
Yes, two kinds. The free chat plan gives 100,000 Toman of chat allowance every 30 days on the fast models. Separately, each new account gets one server-drawn spin of a gift wheel worth 100,000 to 1,000,000 Toman in wallet credit; that credit never expires and can be spent on API usage as well as chat.
Why is the markup 20% rather than a fixed monthly fee?
Because it makes the bill auditable. Your cost for a call is the upstream list price times 1.2, so you can reproduce it from the provider's own published rate card and the token counts the API returns. A flat fee would hide which model and which prompt actually spent the money.
- API documentation
Quickstart, auth, native Anthropic/Gemini routes, streaming, Toman billing and account endpoints.
- Terms of Service
Billing, refunds, availability, liability and termination.
- Privacy Policy
What we collect, what never leaves, and what the model provider receives.
- Contact
Business enquiries, large top-ups, and anything the docs did not answer.
- Models and prices
Every callable model with live Toman rates, context windows and endpoints.
- Overview
What 1xAi is, who it is for, and what it costs — the English entry point.
- ChatGPT API from Iran
Whether the OpenAI API can be called from an Iranian network, and how.
- Claude API from Iran
Anthropic's Messages API from Iran, including the native passthrough route.
- OpenAI-compatible endpoint
The base URL, the auth header, every supported route, streaming and errors.
- Service status
Live per-provider reachability measured from inside Iran, plus the raw dataset.