OpenAI
GPT-6.1 Sol
cx/gpt-6.1-solContext window500,000tokens
Maximum output128,000tokens
Input types
TextImage
AI API. Pay in Rupiah.
Pick a model.
Connect.
Start coding.
Use GPT, Claude, Gemini, and DeepSeek in your app or coding agent. Choose Coding Plan or top up PAYG credit with QRIS.
No credit card Start with an empty balance
api.sekaigateway.xyz/v1Live
model"cx/gpt-5.6-sol"
providers.json
{
"providers": [
"OpenAI",
"Anthropic",
"MiniMax",
"Xiaomi",
"DeepSeek",
"Z.ai",
"Moonshot AI",
"Qwen",
"Google"
]
}OpenAI API formatUse your SEKAI API key and base URL
Access models from these providers
OpenAIAnthropicGoogleDeepSeekQwen
Plans & programs
Code every day?
There's a plan for that.
Choose Coding Plan for coding models. Check referral commissions and Bansos quota requirements too.
Basic, Pro & MAX
Coding Plan
Choose a plan with usage budgets for each 5-hour, weekly, and monthly window. Track your remaining budget in the dashboard.
Usage windows
- 5 hours
- 7 days
- 30 days
5% commission
Referral
Invite friends and earn 5% commission on their deposits and plan purchases, plus a Basic Coding Plan after 20 qualified referrals.
Daily quota
Bansos AI
Use the shared quota without spending your balance. Requires Discord verification and at least IDR10,000 in combined balance; access depends on remaining daily quota.
SekaiGateway Helper
Set up your coding agent from the terminal.
Run the helper to connect Claude Code, Codex, or OpenCode. Choose your agent and model, then enter your SEKAI API key.
Claude CodeCodexOpenCodeHermesOpenClawCline
Terminal
Run it, choose your coding agent, then paste your API key when prompted.
$ npx @sekaigateway/helperModel catalog
Check the models.
Compare the specs.
Compare context windows, input types, and rates for each model.
18 of 18 models
Anthropic
Claude Haiku 5.5
cc/claude-haiku-5-5Context window1Mtokens
Maximum output128,000tokens
Input types
TextImage
MiniMax
MiniMax M3
minimax/minimax-m3Context window1Mtokens
Maximum output262,144tokens
Input types
TextImageVideo
Xiaomi
MiMo V2.6 Flash
xiaomi/mimo-v2.6-flashContext window1Mtokens
Maximum output131,072tokens
Input types
TextImageAudioVideo
Xiaomi
MiMo V2.6 Pro
xiaomi/mimo-v2.6-proContext window1Mtokens
Maximum output131,072tokens
Input types
TextImageAudioVideo
OpenAI
GPT-5.6 Sol
cx/gpt-5.6-solContext window1.05Mtokens
Maximum output128,000tokens
Input types
TextImage
OpenAI
GPT-5.6 Terra
cx/gpt-5.6-terraContext window1.05Mtokens
Maximum output128,000tokens
Input types
TextImage
DeepSeek
DeepSeek V4 Pro
ds/deepseek-v4-proContext window1Mtokens
Maximum output393,216tokens
Input types
Text
OpenAI
GPT-6 Astra
cx/gpt-6-astraContext window1.05Mtokens
Maximum output128,000tokens
Input types
TextImage
DeepSeek
DeepSeek V4 Flash
ds/deepseek-v4-flashContext window1Mtokens
Maximum output393,216tokens
Input types
Text
DeepSeek
DeepSeek V4.1 Flash
ds/deepseek-v4.1-flashContext window1Mtokens
Maximum output393,216tokens
Input types
TextImage
DeepSeek
DeepSeek-V4.1-Flash-1017
ds/deepseek-v4.1-flash-1017Context window1Mtokens
Maximum output393,216tokens
Input types
TextImage
Z.ai
GLM-5.3 Flash
z-ai/glm-5.3-flashContext window1Mtokens
Maximum output128,000tokens
Input types
TextImage
Z.ai
GLM-5.3
z-ai/glm-5.3Context window1Mtokens
Maximum output128,000tokens
Input types
Text
Anthropic
Claude Opus 5
cc/claude-opus-5Context window1Mtokens
Maximum output128,000tokens
Input types
TextImage
Moonshot AI
Kimi K3
moonshot/kimi-k3Context window1.05Mtokens
Maximum output943,718tokens
Input types
TextImageVideo
Qwen
Qwen3.8 Max
qwen/qwen3.8-maxContext window1Mtokens
Maximum output131,072tokens
Input types
TextImage
Google
Gemini 3.8 Flash
gemini/gemini-3.8-flash-highContext window1Mtokens
Maximum output65,536tokens
Input types
TextImage
Context and input specs follow model provider specifications.
See full pricingStart using SEKAI
Create a key. Top up.
Send a request.
For PAYG, get an API key and credit, then connect your app to the SEKAI endpoint.
Create an API key
Create a key in the dashboard. Use a model ID from the catalog according to your plan access or PAYG credit.
Top up with QRIS
PAYG charges are based on input and output tokens. Check model rates before sending a request.
Connect your app
Set the base URL, SEKAI API key, and model ID in the OpenAI SDK. Find request examples in the docs.
Pay As You Go
Top up.
Pay per token.
PAYG credit does not expire. Charges follow the input and output rates of the model you use.
Coding Plan for a monthly budget, or top up PAYG and pay per token.
Start using SEKAI
Get your API key.
Send your first request.
Create an account, choose Coding Plan or top up PAYG credit, then follow the setup guide.
Create a free account