Cocolada
v0.1 · public beta

One key.
Every open model.

OpenAI-compatible gateway routing your requests to the cheapest available provider across Novita, Together, Gonka, and more. Pay only for what you use.

190+ models4 providersSSE streamingUSDC top-up
curl · openai-sdk
# OpenAI Python SDK with one line changed
from openai import OpenAI

client = OpenAI(
    api_key="sk-live-...",
    base_url="https://api.cocolada.xyz/v1",
)

r = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Hi"}],
)
print(r.choices[0].message.content)
Why Cocolada

Built for engineers who refuse to babysit provider dashboards.

01

Provider-agnostic

Drop-in OpenAI SDK. Send to llama-3.3-70b — we route through Novita, fail over to Together. You change nothing.

02

Transparent margins

Catalog shows the upstream price alongside our 15% markup. No hidden fees, no per-minute rates, no credit-pack gimmicks.

03

Crypto-native billing

Top up with USDC on Base or Solana. No card walls, no KYC for prepaid usage. Move money in 30 seconds.

04

Streaming & tool calls

Native SSE for streaming, structured outputs, function calling. The full OpenAI API surface, mirror-matched.

05

Quota controls

Three-tier rate limiting per IP, key, and account. Scoped sub-keys for delegation. Sleep through abuse spikes.

06

Open-source provers

Roadmap: Gonka (verifiable inference) and Cocoon (TEE-confidential). Provable inference when you need an audit trail.

Catalog

Frontier open weights.

Every model below is served by at least one provider. Same alias, automatic failover, single bill.

See all 190 models →
ModelContextInput / 1MOutput / 1M
Llama 3.3 70B
meta-llama/Llama-3.3-70B-Instruct
131k$0.135$0.400
DeepSeek V3.2
deepseek/deepseek-v3.2
128k$0.269$0.400
Qwen 2.5 72B
Qwen/Qwen2.5-72B-Instruct
32k$0.300$0.300
Mixtral 8x22B
mistralai/Mixtral-8x22B-Instruct
64k$0.880$0.880
MiniMax M3
minimax/minimax-m3
1M$0.300$1.200
Pricing

Pay per token.
That's it.

No subscriptions, no minimum spend. Top up credits when you need them — we add 15% over the upstream rate. The full breakdown is in your dashboard.

Hobby

$0
Pay-as-you-go
  • No upfront cost
  • 60 requests/min per key
  • $0.01 minimum top-up
  • Access to all 190 models
Get started
Most common

Developer

$10
One-time top-up
  • Everything in Hobby
  • Priority routing
  • Provider failover
  • ~50M tokens of Qwen2.5 7B
Start with $10

Team

Custom
Enterprise
  • Volume discounts (-5%)
  • Sub-keys with scopes
  • Dedicated support
  • Audit logs export
Contact sales