CATALOGUE

Every model, and what it costs

Four vendors behind one OpenAI-compatible endpoint, reachable from an Iranian network without a VPN. Prices are live Toman rates read from the same table the biller uses.

How to call it How pricing works

[01]THE CATALOGUE

Models by vendor

Rates are per 1,000 tokens in Toman. A blank price means the model is in the catalogue but has no priced row yet, so it is not callable — that is a state worth seeing rather than one worth hiding.

OpenAI

Model	Type	Context	In / 1K	Out / 1K
gpt-5.5GPT-5	Reasoning	400K	1,372	8,230
gpt-5.2GPT-5	Reasoning	400K	480	3,840
gpt-5GPT-5	Reasoning	200K	343	2,743
gpt-5-miniGPT-5	Reasoning	200K	69	549
gpt-5-nanoGPT-5	Chat	200K	14	110
gpt-4.1GPT-4.1	Chat	1,000K	549	2,195
gpt-4.1-miniGPT-4.1	Chat	1,000K	110	439
gpt-4.1-nanoGPT-4.1	Chat	1,000K	27	110
gpt-4oGPT-4o	Chat	128K	686	2,743
gpt-4o-miniGPT-4o	Chat	128K	41	165
o1o-series	Reasoning	200K	4,115	16,459
o3o-series	Reasoning	200K	549	2,195
o3-minio-series	Reasoning	128K	302	1,207
o4-minio-series	Reasoning	200K	302	1,207
gpt-4-turboGPT-4	Chat	128K	2,743	8,230
gpt-3.5-turboGPT-3.5	Chat	16K	137	411
text-embedding-3-largeEmbeddings	Embedding	8.192K	36	—
text-embedding-3-smallEmbeddings	Embedding	8.192K	5.49	—

Anthropic

Model	Type	Context	In / 1K	Out / 1K
claude-fable-5Claude Fable	Reasoning	200K	2,743	13,716
claude-opus-5Claude Opus	Reasoning	200K	1,372	6,858
claude-opus-4-8Claude Opus	Reasoning	200K	1,372	6,858
claude-sonnet-5Claude Sonnet	Reasoning	200K	549	2,743
claude-opus-4-7Claude Opus	Reasoning	200K	1,372	6,858
claude-sonnet-4-6Claude Sonnet	Chat	200K	823	4,115
claude-haiku-4-5Claude Haiku	Chat	200K	274	1,372
claude-3-5-sonnetClaude 3.5	Chat	200K	823	4,115
claude-3-5-haikuClaude 3.5	Chat	200K	274	1,372

Google

Model	Type	Context	In / 1K	Out / 1K
gemini-3.1-pro-previewGemini 3	Reasoning	1,000K	549	3,292
gemini-3.5-flashGemini 3	Chat	1,000K	411	2,469
gemini-3.1-flash-liteGemini 3	Chat	1,000K	69	411
gemini-2.5-proGemini 2.5	Reasoning	1,000K	343	2,743
gemini-2.5-flashGemini 2.5	Chat	1,000K	82	686
gemini-2.5-flash-liteGemini 2.5	Chat	1,000K	27	110

DeepSeek

Model	Type	Context	In / 1K	Out / 1K
deepseek-chatDeepSeek	Chat	64K	77	115
deepseek-reasonerDeepSeek	Reasoning	64K	77	115

Priced, not yet documented

Callable today; the catalogue entry has not caught up. The id is what you put in the request body.

gpt-6-astra2,743 T / 1K in
gpt-5.61,097 T / 1K in
gpt-5.6-luna55 T / 1K in
gpt-5.6-sol1,097 T / 1K in
gpt-5.6-terra549 T / 1K in
gpt-5.5-pro8,230 T / 1K in
gpt-5.4686 T / 1K in
gpt-5.4-mini206 T / 1K in
gpt-5.4-nano55 T / 1K in
gpt-5.4-pro8,230 T / 1K in
gpt-5.3-chat-latest480 T / 1K in
gpt-5.3-codex480 T / 1K in
gpt-5.2-chat-latest480 T / 1K in
gpt-5.2-codex480 T / 1K in
gpt-5.2-pro5,761 T / 1K in
gpt-5.1343 T / 1K in
gpt-5.1-chat-latest343 T / 1K in
gpt-5.1-codex343 T / 1K in
gpt-5.1-codex-max343 T / 1K in
gpt-5.1-codex-mini69 T / 1K in
gpt-5-chat343 T / 1K in
gpt-5-chat-latest343 T / 1K in
gpt-5-codex343 T / 1K in
gpt-5-pro4,115 T / 1K in
gpt-5-search-api343 T / 1K in
gpt-4-06138,230 T / 1K in
gpt-48,230 T / 1K in
gpt-4o-mini-search-preview41 T / 1K in
gpt-4o-search-preview686 T / 1K in
o1-pro41,148 T / 1K in
chat-latest1,372 T / 1K in
claude-fable-5-12,743 T / 1K in
claude-opus-4-61,372 T / 1K in
claude-opus-4-51,372 T / 1K in
claude-sonnet-4-5823 T / 1K in
gemma-4-31b-it27 T / 1K in
gemma-4-26b-a4b-it27 T / 1K in
gemini-3.8-flash206 T / 1K in
gemini-3.7-flash206 T / 1K in
gemini-3.6-flash206 T / 1K in
gemini-3.5-flash-lite82 T / 1K in
gemini-3.1-flash-lite-preview69 T / 1K in
gemini-3.1-pro-preview-customtools549 T / 1K in
gemini-3-flash-preview137 T / 1K in
gemini-2.0-flash41 T / 1K in
gemini-2.0-flash-lite21 T / 1K in
gemini-2.0-flash-lite-00121 T / 1K in
gemini-omni-1.1-flash411 T / 1K in
gemini-flash-latest206 T / 1K in
gemini-flash-lite-latest82 T / 1K in
gemini-omni-flash-preview411 T / 1K in
gemini-pro-latest549 T / 1K in
deepseek-v4-flash82 T / 1K in
deepseek-v4-flash-vision-exp121 T / 1K in
deepseek-v4-pro362 T / 1K in
deepseek-v3.277 T / 1K in
deepseek-v374 T / 1K in
deepseek-coder38 T / 1K in
deepseek-flash82 T / 1K in

[02]HOW TO CALL

One endpoint, one key

Base URL: https://1xai.ir/v1
Auth: Authorization: Bearer 1xai-…
Model selection: The `model` field in the request body
Streaming: Supported on every chat and reasoning model
Billing: Per token, in Toman, from your wallet

The full route list, error shapes and the Anthropic-native passthrough are on the endpoint page.

[03]DEEPER

Per-model write-ups

Each model has a longer analysis — what it is good at, where it falls down, and which one to reach for instead. Those are written in Persian and live at 1xai.ir/models (Persian). The structured facts above are the same in both languages.

FAQ · IN ENGLISH

Do I need a different key or base URL per provider?

No. One key and one base URL reach all four. You select the vendor by the model name in the request body — 1xAi resolves gpt-*, claude-*, gemini-* and deepseek-* to the right upstream. That is the whole point of an OpenAI-compatible endpoint: your existing client library keeps working and only the model string changes.

Are these prices final?

They are the customer-facing Toman rate, which is the upstream list price plus twenty percent, converted at the current FX rate. This table is rendered from the same table the biller reads, so what you see here is what a call costs. It moves when the FX rate moves.

What happens when a model is retired upstream?

It disappears from this table, because the table is the live catalogue rather than a document someone remembers to edit. Dated snapshot ids (gpt-4o-2024-08-06) are priced as their family, so pinning a snapshot never produces an unpriced call.

Is there an English description of each model?

Not yet — the per-model write-ups are Persian. The structured facts here (context window, endpoints, streaming, family) are the same in either language, and the vendors' own model cards cover the rest better than a translation would.