Selora unifies every Claude, GPT, Kimi and GLM model behind a single key. Scoped access, rolling budgets, and transparent usage for the agents you actually ship.
Free 14-day trial · Telegram-verified · no card required
1import OpenAI from 'openai';23const selora = new OpenAI({4 baseURL: 'https://api.selora.lol/v1',5 apiKey: process.env.SELORA_KEY // 1 key routes to all models6});78const completion = await selora.chat.completions.create({9 model: 'claude-opus-5-5',10 messages: [{ role: 'user', content: 'Execute agent planning loop' }],11 stream: true,12});{ "model": "claude-opus-5-5", "tokens": 1420, "charge": "$0.0142" }Every Claude, GPT, Kimi, and GLM model available under your single API key with automatic failover and immutable per-request accounting.
claude-fable-5-1
claude-fable-5
claude-opus-5
claude-sonnet-5
claude-opus-4-8
claude-opus-4-7
claude-opus-4-6
claude-haiku-4-5
kimi-k3
gpt-5-6-sol
gpt-5-6-luna
gpt-6-astra
claude-opus-5-5
glm-5.3
glm-5.3-flash
Run flagship multi-step reasoning, autonomous agent loops, and deep code synthesis through Selora with pooled upstream resilience and automated rolling budget protection — $2.00 in, $10.00 out per million tokens.
A complex agent planning loop executed and settled on one transparent ledger.
Why Selora
Gateway infrastructure that treats cost and reliability as first-class product features — not painful afterthoughts.
Claude · GPT · Kimi · GLM — 15 models, one key.
Replace fragmented vendor keys with a unified high-security Selora credential. Rotate, revoke, and scope access per autonomous agent without touching production code.
cha_live_8f2a9c4b7e12...c41bDual continuous spend caps. Exhausted windows pause inference until reset — zero surprise overages.
Multiple hot upstream provider routes per model. When an upstream provider returns 503 or degrades, Selora immediately switches channels with 0ms rerouting delay.
Transparent per-token rates settled on one ledger across every tier.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Claude Opus 5.5 | $2.00 | $10.00 |
| GPT-6 Astra | $2.00 | $10.00 |
| Kimi K3 | $3.00 | $15.00 |
| GLM 5.3 Flash | $0.30 | $0.60 |
Real-time tokens, request frequency, and latency metrics tracked at microsecond resolution.
Every single inference request leaves an immutable, cryptographically verifiable ledger entry. Zero discrepancies between upstream provider invoices and customer billing.
How it works
From zero to multi-model agent fleet in less than two minutes. No migrations, no breaking changes.
Point your code at https://api.selora.lol/v1. 100% drop-in replacement for the Anthropic & OpenAI SDKs you already use.
Generate granular keys per autonomous agent, background worker, or CI pipeline with model scope and rate limits.
Predictable rolling 4-hour and weekly spend windows. Zero surprise overages — your agents stay capped and safe.
Predictable Pricing
Monthly memberships with continuous spend headroom. Zero surprise overages, no billing spikes, and instant access to all frontier models.
Free 14-day launchpad into the gateway.
For solo developers & background agents.
The sweet spot for production agent teams.
Autonomous agent swarms & heavy workloads.
Adjust the slider to discover the optimal plan and projected savings for your workload.
One key, one ledger, one bill. Start with the free Telegram-verified trial — the whole gateway is ready to probe in minutes.