# OneAPI Indonesia > OneAPI is an API gateway that gives one API key access to models from Anthropic (Claude), OpenAI (GPT), Google (Gemini), DeepSeek, Moonshot (Kimi), and more through OpenAI-compatible and Anthropic-compatible endpoints. Usage is prepaid and billed per token. OneAPI keeps Zero Data Retention: prompts and completions are never stored, only request metadata. Website: https://oneapi.id/ Docs: https://oneapi.id/docs Support: support@oneapi.id X: https://x.com/oneapi_id | Telegram: https://t.me/oneapi_id | Threads: https://www.threads.com/@oneapi.id ## Quickstart 1. Create an account at https://oneapi.id/register and top up your balance. 2. Create an API key in the console at https://oneapi.id/api-keys. Keys start with `sk-` and are shown once. 3. Point any OpenAI- or Anthropic-compatible client at `https://api.oneapi.id/v1` and use a model id from the catalog. ```bash curl https://api.oneapi.id/v1/chat/completions \ -H "Authorization: Bearer $ONEAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "MODEL_ID", "messages": [{"role": "user", "content": "Hello"}]}' ``` OpenAI SDK (Python): ```python from openai import OpenAI client = OpenAI(base_url="https://api.oneapi.id/v1", api_key="sk-...") reply = client.chat.completions.create( model="MODEL_ID", messages=[{"role": "user", "content": "Hello"}], ) print(reply.choices[0].message.content) ``` Anthropic SDK (Python): ```python from anthropic import Anthropic client = Anthropic(base_url="https://api.oneapi.id", api_key="sk-...") reply = client.messages.create( model="MODEL_ID", max_tokens=1024, messages=[{"role": "user", "content": "Hello"}], ) print(reply.content[0].text) ``` ## Authentication | Format | Header | Fallback | | --- | --- | --- | | OpenAI (Chat Completions, Responses) | `Authorization: Bearer sk-...` | none | | Anthropic (Messages) | `x-api-key: sk-...` | `Authorization: Bearer sk-...` | Anthropic-format requests should also send `anthropic-version: 2023-06-01`. Each key can carry a USD spending quota (blank = unlimited per key), an optional daily, weekly, or monthly reset at 00:00 UTC, an expiry date, and a model allowlist. The account balance is always the final cap. Keep keys server-side; never ship them in client code. ## Endpoints | Method | Path | Format | | --- | --- | --- | | POST | `/v1/chat/completions` | OpenAI Chat Completions | | POST | `/v1/responses` | OpenAI Responses | | POST | `/v1/messages` | Anthropic Messages | | GET | `/v1/models` | Model list with vendor, context length, modalities and per-token prices | | GET | `/v1/me` | Balance, available credit and key limits | The gateway converts between the three request formats, so most models can be called from any of them. A feature the target model cannot express returns an `unsupported_conversion` or `unsupported_parameter` error. Change only the `model` string to switch provider. ### POST /v1/responses | Field | Type | Notes | | --- | --- | --- | | `model` | string | Required | | `input` | string or array | Required. Prompt text or structured input items | | `stream` | boolean | Server-Sent Events when true | | `max_output_tokens` | integer | Output cap | | `temperature` | number 0-2 | Sampling randomness | ### POST /v1/messages | Field | Type | Notes | | --- | --- | --- | | `model` | string | Required | | `max_tokens` | integer | Required | | `messages` | array | Anthropic message array | | `stream` | boolean | Server-Sent Events when true | ## Streaming Set `"stream": true`. `/v1/chat/completions` and `/v1/responses` stream OpenAI-style SSE events; `/v1/messages` streams Anthropic-style SSE events. Use `curl -N` to see events as they arrive. ## Errors OpenAI-format endpoints return `{"error": {"type", "code", "message", "param"}}`. The Anthropic-format endpoint returns `{"type": "error", "error": {"type", "message"}}`. | Status | Code | Meaning | What to do | | --- | --- | --- | --- | | 400 | `invalid_request` | Malformed body or unsupported parameter | Fix the request | | 401 | `unauthorized` | Missing, wrong, or expired key | Check the key and header | | 402 | `insufficient_credit` | Balance too low for this request | Top up | | 402 | `account_frozen` | Account suspended | Contact support | | 403 | `unknown_model` | Model not in this key's allowlist | Use an allowed model or edit the key | | 404 | `unknown_model` | Model id does not exist or is disabled | Check `GET /v1/models` | | 429 | `quota_exceeded` | Per-key quota used up for this period | Wait for `Retry-After` or raise the quota | | 429 | `rate_limit_exceeded` | Too many requests | Back off and retry | | 502/504 | `upstream_error`, `upstream_timeout` | Model provider failed or timed out | Retry with backoff | ## Rate limits Keys with a requests-per-minute limit get the current window on every response, including 429s: | Header | Example | Meaning | | --- | --- | --- | | `x-ratelimit-limit-requests` | `50` | Requests allowed per minute for this key | | `x-ratelimit-remaining-requests` | `47` | Requests left in the current window | | `x-ratelimit-reset-requests` | `12s` | Time until the window resets | A 429 also carries `Retry-After` in seconds. Slow down as `remaining` approaches 0 instead of retrying into a 429. Keys without an RPM limit get no `x-ratelimit-*` headers. ## Billing - Prepaid balance, charged per token (input, output, cache read, cache write) at the model's listed price. - No monthly minimum. Current prices: https://oneapi.id/models. Plans: https://oneapi.id/pricing. - Balance and usage history are in the console at https://oneapi.id/billing and https://oneapi.id/activity. ## Models - [Claude Fable 5.1](https://oneapi.id/models/claude-fable-5.1): model id `claude-fable-5.1`, $8.00 in / $40.00 out per 1M tokens, 1M context - [Claude Haiku 5.5](https://oneapi.id/models/claude-haiku-5.5): model id `claude-haiku-5.5`, $0.35 in / $1.75 out per 1M tokens, 1M context - [Claude Opus 5.5](https://oneapi.id/models/claude-opus-5.5): model id `claude-opus-5.5`, $2.80 in / $14.00 out per 1M tokens, 1M context - [Claude Sonnet 5.5](https://oneapi.id/models/claude-sonnet-5.5): model id `claude-sonnet-5.5`, $1.40 in / $7.00 out per 1M tokens, 1M context - [DeepSeek v4.1 Pro 0813](https://oneapi.id/models/deepseek-v4-pro-0813): model id `deepseek-v4-pro-0813`, $1.32 in / $3.96 out per 1M tokens, 1M context - [DeepSeek v4.1 Flash 1017](https://oneapi.id/models/deepseek-v4.1-flash): model id `deepseek-v4.1-flash`, $0.15 in / $1.20 out per 1M tokens, 1M context - [DeepSeek v4.1 Flash Uncensored](https://oneapi.id/models/deepseek-v4.1-flash-uncensored): model id `deepseek-v4.1-flash-uncensored`, $0.40 in / $1.20 out per 1M tokens, 1M context - [Drex Max](https://oneapi.id/models/drex-max): model id `drex-max`, $0.009 in / $0 out per 1M tokens, 262K context - [Gemini 3.8 Flash](https://oneapi.id/models/gemini-3.8-flash): model id `gemini-3.8-flash`, $0.53 in / $2.63 out per 1M tokens, 1M context - [Gemini 4 Argon](https://oneapi.id/models/gemini-4-argon): model id `gemini-4-argon`, $1.00 in / $5.00 out per 1M tokens, 1M context - [GLM 5.3](https://oneapi.id/models/glm-5.3): model id `glm-5.3`, $0.03 in / $3.84 out per 1M tokens, 1M context - [GLM 5.3 Flash](https://oneapi.id/models/glm-5.3-flash): model id `glm-5.3-flash`, $0.07 in / $0.25 out per 1M tokens, 1M context - [GLM 5.3 Flash Uncensored](https://oneapi.id/models/glm-5.3-flash-uncensored): model id `glm-5.3-flash-uncensored`, $0.25 in / $1.20 out per 1M tokens, 1M context - [GLM 5.3 Uncensored](https://oneapi.id/models/glm-5.3-uncensored): model id `glm-5.3-uncensored`, $0.78 in / $2.08 out per 1M tokens, 1M context - [GPT 5.6 Luna](https://oneapi.id/models/gpt-5.6-luna): model id `gpt-5.6-luna`, $0.14 in / $0.84 out per 1M tokens, 1M context - [GPT 5.6 Sol](https://oneapi.id/models/gpt-5.6-sol): model id `gpt-5.6-sol`, $1.40 in / $7.00 out per 1M tokens, 1M context - [GPT 5.6 Terra](https://oneapi.id/models/gpt-5.6-terra): model id `gpt-5.6-terra`, $1.40 in / $8.40 out per 1M tokens, 1M context - [GPT 6 Astra](https://oneapi.id/models/gpt-6-astra): model id `gpt-6-astra`, $7.00 in / $35.00 out per 1M tokens, 1M context - [GPT 6 Luna](https://oneapi.id/models/gpt-6-luna): model id `gpt-6-luna`, $0.07 in / $0.35 out per 1M tokens, 1M context - [GPT 6.1 Sol](https://oneapi.id/models/gpt-6.1-sol): model id `gpt-6.1-sol`, $1.40 in / $7.00 out per 1M tokens, 1M context - [GPT 6.1 Terra](https://oneapi.id/models/gpt-6.1-terra): model id `gpt-6.1-terra`, $0.50 in / $2.50 out per 1M tokens, 1M context - [Kimi K3](https://oneapi.id/models/kimi-k3): model id `kimi-k3`, $0.51 in / $10.80 out per 1M tokens, 1M context - [Kimi K3.1 Pro](https://oneapi.id/models/kimi-k3.1-pro): model id `kimi-k3.1-pro`, $1.60 in / $8.00 out per 1M tokens, 1M context - [MiMo v2.6 Flash](https://oneapi.id/models/mimo-v2.6-flash): model id `mimo-v2.6-flash`, $0.14 in / $0.28 out per 1M tokens, 1M context - [MiMo v2.6 Pro](https://oneapi.id/models/mimo-v2.6-pro): model id `mimo-v2.6-pro`, $0.43 in / $0.87 out per 1M tokens, 1M context - [MiniMax M3.1 Flash](https://oneapi.id/models/minimax-m3.1-flash): model id `minimax-m3.1-flash`, $0.15 in / $0.60 out per 1M tokens, 1M context - [Muse Spark 1.3](https://oneapi.id/models/muse-spark-1.3): model id `muse-spark-1.3`, $0.63 in / $2.13 out per 1M tokens, 1M context - [Solar Decide](https://oneapi.id/models/solar-decide): model id `solar-decide`, $0.001 in / $0 out per 1M tokens, 256K context ## Data retention - OneAPI does not store prompts, messages, files, images, tool calls, or model outputs in its database or logs. Content exists only in memory while a request is in flight. - Stored per request: key id, model, provider, protocol, token counts, charge, status, timestamps, latency. No content. - Content is forwarded to the model provider serving the request; the provider's own retention policy applies from that point. Avoid sending sensitive data to free or promotional models. - Details: https://oneapi.id/privacy ## About OneAPI is operated independently and is not affiliated with OpenRouter or any model provider.