Bumili ng coding credits. Gamitin kahit saan.
One-time credits para sa Claude Opus, Claude Sonnet, GPT-5.5, at Gemini 3.5. Ikonekta sa Claude Code, Codex, Cursor, Cline, Aider, o sa sarili mong API calls. Walang subscription. Walang malabong buwanang limit. Eksaktong token billing.
Mag-top up kung kailan mo gusto. Itigil kung kailan mo gusto. Walang buwanang plan na kailangang panatilihin.
Ikonekta ang Claude Code, Codex CLI, Cursor, Cline, Aider, Continue.dev, OpenCode, o ang sarili mong app.
Makikita mo ang paggamit bilang tokens at credits, hindi bilang malabong buwanang request pool.
Ang Claude Opus ay naka-presyo nang 32% mas mababa kaysa official API rates, at ang Claude Sonnet ay 77% mas mababa kaysa official API rates sa plan na ito.
Aling balanse ang sisingilin?
Gamitin ang parehong API key. Ang model na tatawagin mo ang magpapasya kung aling credit pool ang gagamitin.
Claude Opus 4.7, Sonnet 4.6, GPT-5.5, Gemini 3.5 Thinking, at Gemini 3.5 Fast ay unang gumagamit ng Coding Credits, pagkatapos ay lilipat sa General Credits kung maubos ang Coding Credits.
Ang larawan, video, audio, 3D, at lahat ng iba pang LLMs ay gumagamit lang ng General Credits. Nakareserba ang Coding Credits para sa coding workloads.
Pumili ng one-time pack
Walang subscription at walang monthly reset. Mag-e-expire ang credits 365 araw pagkatapos ng pagbili.
Nakareserba ang Coding Credits para sa mga coding model na ipinapakita sa ibaba. Ang video, larawan, audio, 3D, at iba pang LLMs ay gumagamit ng General Credits.
Nakareserba para sa mga coding model na ito
Tawagin ang model ID na gusto mo. Pinananatiling hiwalay ng billing ang Coding Credits mula sa General Credits.
Eksaktong token pricing
Simple ang plan: bawat request ay sinisingil batay sa input at output tokens.
| Model | Hypereal $ / MTok (in / out) | Official API rate | Mas mababa kaysa official |
|---|---|---|---|
Claude Opus 4.7 / 4.6 | $3.40 / $16.96 | $5.00 / $25.00 | −32% |
Claude Sonnet 4.6 | $0.68 / $3.40 | $3.00 / $15.00 | −77% |
GPT-5.5 | $0.42 / $2.52 | $1.20 / $7.20 | −65% |
Gemini 3.5 Thinking | $0.90 / $5.40 | $1.50 / $9.00 | −40% |
Gemini 3.5 Fast | $0.90 / $5.40 | $1.50 / $9.00 | −40% |
Bawat 1M tokens. Ang input at output ay hiwalay na sinusukat, kaya malinaw na maipaplanong ng mga heavy user ang gastos.
Gamitin kung saan ka na nagko-code
I-drop ang Hypereal sa mga tool na gumagamit ng OpenAI-compatible o Anthropic-compatible APIs.
Gumagana ang anumang tool na gumagamit ng OpenAI o Anthropic APIs. Itakda ang base URL sa hypereal.cloud at ilagay ang iyong key. Nasa ibaba ang setup snippets.
Sinusuportahan ng Hypereal ang cache_control caching at Hypereal Cache. Naka-on ang Hypereal Cache bilang default at puwedeng magpababa ng token use kapag muling ipinapadala ng agents ang repository context. Itakda ang hypereal.cache sa "auto", o i-omit ito para sa parehong default.
Claude Code
Ang official Anthropic Claude Code CLI ay nakikipag-usap sa /v1/messages. I-point ito sa Hypereal, gawing default ang Sonnet, at panatilihing naka-on ang prompt caching.
# 1. Get your API key
# https://hypereal.cloud/manage-api-keys
# 2. Point Claude Code at Hypereal (Anthropic-compatible endpoint).
# NOTE: do NOT include /v1 — the Anthropic SDK appends /v1/messages
# itself. Setting the URL to .../v1 produces /v1/v1/messages → 404.
export ANTHROPIC_BASE_URL="https://api.hypereal.cloud"
export ANTHROPIC_API_KEY="ck_..." # your Hypereal key
# 3. Default to Sonnet 4.6 for daily coding agents.
# Switch to claude-opus-4-7 only for the hardest refactors.
export ANTHROPIC_MODEL="claude-sonnet-4-6"
# 4. Run
claude
# Hypereal Cache is enabled by default.
# Use hypereal.cache="auto" to be explicit, or omit it.OpenAI Codex CLI
Gumagamit ang OpenAI Codex CLI ng /v1/chat/completions. Itakda ang OPENAI_BASE_URL sa Hypereal at i-pin ang GPT-5.5.
export OPENAI_BASE_URL="https://hypereal.cloud/v1"
export OPENAI_API_KEY="ck_..."
export OPENAI_MODEL="gpt-5.5"
codex --provider openaiCursor
Tinatanggap ng Cursor ang OpenAI-compatible endpoints. I-override ang OpenAI host sa Settings -> Models.
# Cursor → Settings → Models → "Add OpenAI-compatible"
# Base URL: https://hypereal.cloud/v1
# API Key: ck_...
# Model: gemini-3.5-thinking (or gpt-5.4 / claude-sonnet-4-6)
#
# Enable "Override OpenAI" in the same panel so Cursor routes
# completions through Hypereal instead of api.openai.com.
#
# Note: Cursor BYOK currently rejects gpt-5.5
# (https://forum.cursor.com/t/gpt-5-5-byok-not-working/160004/15).
# Use the LiteLLM workaround if you need gpt-5.5 in Cursor:
# pip install "litellm[proxy]"
# OPENAI_API_BASE=https://api.hypereal.cloud/v1 \
# OPENAI_API_KEY=ck_... \
# python -m litellm.proxy.proxy_cli --model gpt-5.5
# Then point Cursor at http://localhost:4000/v1 instead.OpenCode / Cline / Aider
Maaaring gumamit ang OpenCode, Cline, at Aider ng Anthropic-compatible API settings o environment variables.
# OpenCode / Cline (VS Code) — Anthropic-compatible.
# Cline appends /v1/messages itself, so omit /v1 here.
{
"anthropic.baseURL": "https://api.hypereal.cloud",
"anthropic.apiKey": "ck_...",
"anthropic.model": "claude-sonnet-4-6"
}
# Aider uses the Anthropic SDK underneath — same rule:
# do NOT add /v1 to ANTHROPIC_API_BASE.
export ANTHROPIC_API_BASE="https://api.hypereal.cloud"
export ANTHROPIC_API_KEY="ck_..."
aider --model anthropic/claude-sonnet-4-6Hermes Agent
Gumagana ang Hermes Agent sa anumang OpenAI-compatible endpoint. I-configure nang isang beses at patakbuhin.
# Hermes Agent supports OpenAI-compatible endpoints out of the box.
hermes config set provider openai-compatible
hermes config set base_url https://hypereal.cloud/v1
hermes config set api_key ck_...
hermes config set model gemini-3.5-fast
hermes run "Refactor auth.ts to use jose"Raw curl
Para sa agents at scripts: direktang tawagin ang /v1/messages gamit ang iyong API key.
curl https://hypereal.cloud/v1/messages \
-H "x-api-key: ck_..." \
-H "content-type: application/json" \
-H "anthropic-version: 2023-06-01" \
-d '{
"model": "claude-sonnet-4-6",
"max_tokens": 1024,
"system": [{
"type": "text",
"text": "You are a senior TypeScript refactoring assistant.",
"cache_control": {"type": "ephemeral"}
}],
"messages": [{"role": "user", "content": "Write a Python quicksort."}],
"hypereal": {"cache": "auto"}
}'