×1
Eyeban Fast
Quick answers and light edits.
Input 9٬620 تومان Output 44٬200 تومان
Models
The right model for the job
Fast, Balanced, and Max sit on top of a live catalog of coding models. Prices below are Tomans per million tokens and follow the database — not a static page.
×2
Eyeban Balanced
Strong default for coding agents.
Input 9٬620 تومان Output 44٬200 تومان
×4
Eyeban Max
Highest capability for hard tasks.
Input 9٬620 تومان Output 44٬200 تومان
All models
Individual models available for coding in Eyeban. Input, output, and cache prices are per 1 million tokens. Changing a row in admin updates this table on the next page load.
No models match that filter.
Alibaba Cloud
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| Qwen3 32B qwen3-32b Parspack pricing: input 20,800 IRT / 1M tokens, output 72,800 IRT / 1M tokens. credit_multiplier=0.728 (blend 70/30 input/output, 1 credit≈… | 20٬800 تومان | 72٬800 تومان | — | — |
|
| Qwen3 Next 80B A3B Instruct qwen3-next-80b Parspack pricing: input 23,400 IRT / 1M tokens, output 286,000 IRT / 1M tokens. credit_multiplier=2.044 (blend 70/30 input/output, 1 credit… | 23٬400 تومان | 286٬000 تومان | — | — |
|
| Qwen3 Coder 480B A35B qwen3-coder-480b Parspack pricing: input 78,000 IRT / 1M tokens, output 260,000 IRT / 1M tokens. credit_multiplier=2.652 (blend 70/30 input/output, 1 credit… | 78٬000 تومان | 260٬000 تومان | — | 26٬000 تومان |
|
| Qwen 3.7 Plus qwen-3.7-plus Parspack pricing: input 104,000 IRT / 1M tokens, output 333,000 IRT / 1M tokens. credit_multiplier=3.454 (blend 70/30 input/output, 1 credi… | 104٬000 تومان | 333٬000 تومان | — | — |
|
| Qwen 3.6 Plus qwen-3.6-plus Parspack pricing: input 84,500 IRT / 1M tokens, output 507,000 IRT / 1M tokens. credit_multiplier=4.225 (blend 70/30 input/output, 1 credit… | 84٬500 تومان | 507٬000 تومان | 105٬625 تومان | — |
|
Anthropic
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| Claude Opus 4.7 claude-opus-4.7 Parspack pricing: input 1,300,000 IRT / 1M tokens, output 6,500,000 IRT / 1M tokens. credit_multiplier=57.2 (blend 70/30 input/output, 1 cr… | 1٬300٬000 تومان | 6٬500٬000 تومان | 1٬625٬000 تومان | 130٬000 تومان |
|
| Claude Opus 4.5 claude-opus-4.5 Parspack pricing: input 1,300,000 IRT / 1M tokens, output 6,500,000 IRT / 1M tokens. credit_multiplier=57.2 (blend 70/30 input/output, 1 cr… | 1٬300٬000 تومان | 6٬500٬000 تومان | 1٬625٬000 تومان | 130٬000 تومان |
|
| Anthropic: Claude Haiku 4.5 claude-haiku-4.5 Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and laten… | 260٬000 تومان | 1٬300٬000 تومان | 325٬000 تومان | 26٬000 تومان |
|
| Anthropic: Claude Sonnet 4.6 claude-sonnet-4.6 Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It e… | 780٬000 تومان | 3٬900٬000 تومان | 975٬000 تومان | 78٬000 تومان |
|
DeepSeek
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| DeepSeek V4 Pro deepseek-v4-pro Parspack pricing: input 113,100 IRT / 1M tokens, output 226,200 IRT / 1M tokens. credit_multiplier=2.941 (blend 70/30 input/output, 1 credi… | 113٬100 تومان | 226٬200 تومان | — | 35٬100 تومان |
|
| DeepSeek V4 Flash deepseek-v4-flash Parspack pricing: input 114,400 IRT / 1M tokens, output 343,200 IRT / 1M tokens. credit_multiplier=3.661 (blend 70/30 input/output, 1 credi… | 114٬400 تومان | 343٬200 تومان | — | 4٬448 تومان |
|
Eyeban
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| Composer 2.5 composer-2.5 Eyeban Composer via Cursor agent path | — | — | — | — |
|
| Composer 2 composer-2 Eyeban Composer via Cursor agent path | — | — | — | — |
|
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash gemini-2.5-flash Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scien… | 78٬000 تومان | 650٬000 تومان | 21٬667 تومان | 7٬800 تومان |
|
| gemma-3n-e4b-it gemma-3n-e4b-it gemma-3n-e4b-it via ParsPack. | — | — | — | — |
|
| Google: Gemma 3 27B gemma-3-27b-it Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understa… | 20٬800 تومان | 117٬000 تومان | — | 10٬400 تومان |
|
| Google: Gemma 3 12B gemma-3-12b-it Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understa… | 13٬000 تومان | 39٬000 تومان | — | — |
|
| Google: Gemini 3.1 Flash Lite Preview gemini-3.1-flash-lite-preview Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite o… | 65٬000 تومان | 390٬000 تومان | 21٬667 تومان | 6٬500 تومان |
|
| Google: Gemma 4 26B A4B gemma-4-26b-a4b-it Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B a… | 23٬400 تومان | 78٬000 تومان | — | 13٬000 تومان |
|
| Google: Gemma 4 31B gemma-4-31b-it Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K to… | 23٬400 تومان | 88٬400 تومان | — | 13٬000 تومان |
|
| Google: Gemini 3.1 Pro Preview Custom Tools gemini-3.1-pro-preview-customtools Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general… | 520٬000 تومان | 3٬120٬000 تومان | 97٬500 تومان | 52٬000 تومان |
|
| Google: Gemini 3.1 Pro Preview gemini-3.1-pro-preview Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliabi… | 520٬000 تومان | 3٬120٬000 تومان | 97٬500 تومان | 52٬000 تومان |
|
| Google: Gemini 3 Flash Preview gemini-3-flash-preview Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. I… | 130٬000 تومان | 780٬000 تومان | 21٬667 تومان | 13٬000 تومان |
|
Meta Llama
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| Meta: Llama 3.3 70B Instruct llama-3.3-70b-instruct The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out)… | 26٬000 تومان | 83٬200 تومان | — | — |
|
Minimax
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| MiniMax: MiniMax M3 minimax-m3 MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context wi… | 78٬000 تومان | 312٬000 تومان | — | 15٬600 تومان |
|
| MiniMax: MiniMax M2.7 minimax-m2.7 MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built t… | 78٬000 تومان | 312٬000 تومان | — | 15٬600 تومان |
|
Mistral AI
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| Mistral: Mistral Nemo mistral-nemo A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting… | 4٬940 تومان | 7٬800 تومان | — | — |
|
Moonshot
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| kimi 2.5 kimi-2.5 Moonshot Kimi K2.5 | 117٬000 تومان | 585٬000 تومان | — | 18٬200 تومان |
|
| MoonshotAI: Kimi K2.7 Code kimi-k2.7-code MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliab… | 184٬600 تومان | 910٬000 تومان | — | 39٬000 تومان |
|
| moonshot-v1-128k moonshot-v1-128k moonshot-v1-128k via ParsPack. | — | — | — | — |
|
| moonshot-v1-8k-vision-preview moonshot-v1-8k-vision-preview moonshot-v1-8k-vision-preview via ParsPack. | — | — | — | — |
|
| moonshot-v1-8k moonshot-v1-8k moonshot-v1-8k via ParsPack. | — | — | — | — |
|
| moonshot-v1-32k-vision-preview moonshot-v1-32k-vision-preview moonshot-v1-32k-vision-preview via ParsPack. | — | — | — | — |
|
| moonshot-v1-32k moonshot-v1-32k moonshot-v1-32k via ParsPack. | — | — | — | — |
|
| moonshot-v1-128k-vision-preview moonshot-v1-128k-vision-preview moonshot-v1-128k-vision-preview via ParsPack. | — | — | — | — |
|
| MoonshotAI: Kimi K2.6 kimi-k2.6 Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-ag… | 247٬000 تومان | 1٬040٬000 تومان | — | 41٬600 تومان |
|
Nex-AGI
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| nex-n2-pro nex-n2-pro nex-n2-pro via ParsPack. | — | — | — | — |
|
Nousresearch
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| Nous: Hermes 3 405B Instruct hermes-3-llama-3.1-405b Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplay… | 260٬000 تومان | 260٬000 تومان | — | — |
|
NVIDIA
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| nemotron-3-ultra-preview nemotron-3-ultra-preview nemotron-3-ultra-preview via ParsPack. | — | — | — | — |
|
| nemotron-3-nano-omni-30b-a3b-reasoning nemotron-3-nano-omni-30b-a3b-reasoning nemotron-3-nano-omni-30b-a3b-reasoning via ParsPack. | — | — | — | — |
|
| NVIDIA: Nemotron 3 Nano 30B A3B nemotron-3-nano-30b-a3b NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specializ… | 13٬000 تومان | 52٬000 تومان | — | 7٬800 تومان |
|
| nemotron-nano-9b-v2 nemotron-nano-9b-v2 nemotron-nano-9b-v2 via ParsPack. | — | — | — | — |
|
| NVIDIA: Nemotron 3 Ultra nemotron-3-ultra-550b-a55b NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (Mo… | 156٬000 تومان | 624٬000 تومان | — | 31٬200 تومان |
|
| nemotron-nano-12b-v2-vl nemotron-nano-12b-v2-vl nemotron-nano-12b-v2-vl via ParsPack. | — | — | — | — |
|
| NVIDIA: Nemotron 3 Super nemotron-3-super-120b-a12b NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accura… | 20٬800 تومان | 117٬000 تومان | — | — |
|
openai
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| nemotron3(free) nemotron3 NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (Mo… | 0 تومان | 0 تومان | 0 تومان | 0 تومان |
|
OpenAI
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| GPT OSS 120B gpt-oss-120b Open-weight GPT OSS 120B via ParsPack | 9٬620 تومان | 44٬200 تومان | — | — |
|
| OpenAI: GPT-5.5 Pro gpt-5.5-pro GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M… | 7٬800٬000 تومان | 46٬800٬000 تومان | — | — |
|
| OpenAI: GPT-5.5 gpt-5.5 GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliabi… | 1٬300٬000 تومان | 7٬800٬000 تومان | — | 130٬000 تومان |
|
| OpenAI: GPT-5.3-Codex gpt-5.3-codex GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with… | 455٬000 تومان | 3٬640٬000 تومان | — | 45٬500 تومان |
|
| OpenAI: GPT-4o (2024-11-20) gpt-4o-2024-11-20 The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve … | 650٬000 تومان | 2٬600٬000 تومان | — | 325٬000 تومان |
|
| OpenAI: GPT-4 gpt-4 OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than … | 7٬800٬000 تومان | 15٬600٬000 تومان | — | — |
|
| OpenAI: o3 o3 o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It al… | 520٬000 تومان | 2٬080٬000 تومان | — | 130٬000 تومان |
|
| OpenAI: o1-pro o1-pro The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model… | 39٬000٬000 تومان | 156٬000٬000 تومان | — | — |
|
| OpenAI: GPT-5 gpt-5 GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for com… | 325٬000 تومان | 2٬600٬000 تومان | — | 32٬500 تومان |
|
| OpenAI: GPT-4o-mini gpt-4o-mini GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As… | 39٬000 تومان | 156٬000 تومان | — | 19٬500 تومان |
|
| OpenAI: gpt-oss-20b gpt-oss-20b gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) archi… | 7٬800 تومان | 33٬800 تومان | — | 7٬800 تومان |
|
| OpenAI: GPT-5.2 Pro gpt-5.2-pro GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It … | 5٬460٬000 تومان | 43٬680٬000 تومان | — | — |
|
| OpenAI: GPT-5 Pro gpt-5-pro GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for… | 3٬900٬000 تومان | 31٬200٬000 تومان | — | — |
|
| OpenAI: GPT-5 Mini gpt-5-mini GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and… | 65٬000 تومان | 520٬000 تومان | — | 6٬500 تومان |
|
| OpenAI: GPT-4.1 Mini gpt-4.1-mini GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 mi… | 104٬000 تومان | 416٬000 تومان | — | 26٬000 تومان |
|
| OpenAI: o4 Mini o4-mini OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimod… | 286٬000 تومان | 1٬144٬000 تومان | — | 71٬500 تومان |
|
| OpenAI: GPT-4.1 Nano gpt-4.1-nano For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performanc… | 26٬000 تومان | 104٬000 تومان | — | 6٬500 تومان |
|
| OpenAI: o3 Mini o3-mini OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and c… | 286٬000 تومان | 1٬144٬000 تومان | — | 143٬000 تومان |
|
| OpenAI: o1 o1 The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is tra… | 3٬900٬000 تومان | 15٬600٬000 تومان | — | 1٬950٬000 تومان |
|
| OpenAI: GPT-4o-mini (2024-07-18) gpt-4o-mini-2024-07-18 GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As… | 39٬000 تومان | 156٬000 تومان | — | 19٬500 تومان |
|
| OpenAI: GPT-4 Turbo gpt-4-turbo The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to De… | 2٬600٬000 تومان | 7٬800٬000 تومان | — | — |
|
| OpenAI: GPT-3.5 Turbo gpt-3.5-turbo GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional… | 130٬000 تومان | 390٬000 تومان | — | — |
|
Poolside
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| laguna-m.1 laguna-m.1 laguna-m.1 via ParsPack. | — | — | — | — |
|
| laguna-xs.2 laguna-xs.2 laguna-xs.2 via ParsPack. | — | — | — | — |
|
Z.Ai
| Model | Input | Output | Cache write | Cache read | Plans |
|---|---|---|---|---|---|
| GLM 5.2 100 for light program and websites | 177٬632 تومان | 558٬272 تومان | — | 32٬989 تومان | — |
| Z.ai: GLM 5.1 glm-5.1 GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous mod… | 251٬160 تومان | 789٬360 تومان | — | 46٬644 تومان |
|
Keys
Default cloud keys stay on api.eyeban.ir. Optional BYOK keeps your provider key in the desktop secure store and proxies it on each Agent turn. You sign in with your Eyeban account.
Plans and quota
Quota lives on the dashboard. Free is limited for evaluation. Pricing has the amounts. New catalog models are on Pro, Pro+, and Ultra unless an operator assigns them otherwise.