One wallet. Better coding usage.
Multiplier shown vs. Claude Opus / Sonnet official API rates
Top up Hypereal Credits once. The credits work across Hypereal, and your selected top-up amount can reduce token charges on Claude Opus, Claude Sonnet, GPT-5.5, and Gemini 3.5 coding models.
Top up when you want. Stop when you want. There is no monthly plan to maintain.
Connect Claude Code, Codex CLI, Cursor, Cline, Aider, Continue.dev, OpenCode, or your own app.
You see usage as tokens and credits, not a fuzzy monthly request pool.
Claude Opus 4.7 is priced 32% below official API rates, and Claude Sonnet is 77% below official API rates on this plan.
How is one wallet charged?
Every API uses Hypereal Credits. Coding multipliers apply only to the listed coding models.
Claude, GPT, and Gemini coding models spend the same Hypereal Credits wallet. Your selected top-up amount can reduce charges on these coding models.
Video, image, audio, 3D, GPU, training, and other model APIs use the prices shown on their product pages.
Top up Hypereal Credits
Each pack adds face-value credits to one wallet. The amount you top up determines the coding-model usage multiplier.
Top-ups add face-value Hypereal Credits. Coding multipliers are a coding-model feature shown for this plan.
Coding models with usage multipliers
Call the model ID you want. Billing applies the coding multiplier only to these listed models.
Exact token pricing
The plan is simple: every request is billed by input and output tokens.
| Model | Hypereal $ / MTok (in / out) | Official API rate | Below 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% |
Per 1M tokens. Input and output are metered separately, so heavy users can forecast spend clearly.
Use it where you already code
Drop Hypereal into tools that speak OpenAI-compatible or Anthropic-compatible APIs.
Any tool that speaks OpenAI or Anthropic APIs works. Set the base URL to hypereal.cloud and paste your key. Setup snippets below.
Hypereal supports cache_control caching and Hypereal Cache. Hypereal Cache is on by default and can reduce token use when agents resend repository context. Set hypereal.cache to "auto", or omit it for the same default.
Claude Code
The official Anthropic Claude Code CLI talks to /v1/messages. Point it at Hypereal, default to Sonnet, and keep prompt caching on.
# 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
OpenAI Codex CLI uses /v1/chat/completions. Set OPENAI_BASE_URL to Hypereal and pin 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
Cursor accepts OpenAI-compatible endpoints. Override the OpenAI host in 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
OpenCode, Cline, and Aider can use Anthropic-compatible API settings or 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
Hermes Agent works with any OpenAI-compatible endpoint. Configure once and run.
# 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
For agents and scripts: call /v1/messages directly with your 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"}
}'