The platformto build
One API.
Every Model.
Claude, GPT-5, Gemini, DeepSeek, Qwen, Sora, Veo, Fish Audio — text, image, video, and audio. One key. One bill.
Anthropic
3 models| Model | Input / MTok | Output / MTok | Savings |
|---|---|---|---|
Claude Opus 4.6Most Intelligent claude-opus-4-6 | $3.00 | $15.00 | −80% |
Claude Sonnet 4.6Best Balance claude-sonnet-4-6 | $1.80 | $9.00 | −40% |
Claude Haiku 4.5Fastest claude-haiku-4-5 | $0.60 | $3.00 | −25% |
OpenAI
11 models| Model | Input / MTok | Output / MTok | Savings |
|---|---|---|---|
GPT-5 gpt-5 | $0.76 | $6.00 | −40% |
GPT-5.1 gpt-5.1 | $0.76 | $6.00 | −40% |
GPT-5.2 gpt-5.2 | $1.06 | $8.40 | −30% |
GPT-5 Codex gpt-5-codex | $0.76 | $6.00 | −40% |
GPT-5 Codex MiniUltra Cheap gpt-5-codex-mini | $0.14 | $1.20 | −35% |
GPT-5.1 Codex gpt-5.1-codex | $0.76 | $6.00 | −40% |
GPT-5.1 Codex Mini gpt-5.1-codex-mini | $0.14 | $1.20 | −35% |
GPT-5.1 Codex Max gpt-5.1-codex-max | $0.76 | $6.00 | −40% |
GPT-5.2 Codex gpt-5.2-codex | $1.06 | $8.40 | −30% |
GPT-5.3 Codex gpt-5.3-codex | $1.06 | $8.40 | −30% |
GPT-5.3 Codex Spark gpt-5.3-codex-spark | $1.06 | $8.40 | −30% |
Google Gemini
14 models| Model | Input / MTok | Output / MTok | Savings |
|---|---|---|---|
Gemini 3 ProFlagship gemini-3-pro-official | $3.20 | $19.20 | −30% |
Gemini 3 Pro Preview gemini-3-pro-preview-official | $3.20 | $19.20 | −30% |
Gemini 3 Flash gemini-3-flash-official | $0.80 | $4.80 | −35% |
Gemini 3 Flash Preview gemini-3-flash-preview-official | $0.80 | $4.80 | −35% |
Gemini 3.1 ProFree Tier gemini-3.1-pro | $0.05 | $0.30 | FREE |
Gemini 3.1 Pro Preview gemini-3.1-pro-preview-official | $3.20 | $19.20 | −30% |
Gemini 3.1 Fast gemini-3.1-fast | $1.00 | $6.00 | −40% |
Gemini 3.1 Thinking gemini-3.1-thinking | $1.00 | $6.00 | −40% |
Gemini 3.1 Flash Lite gemini-3.1-flash-lite-preview-official | $0.40 | $2.40 | −30% |
Gemini 2.5 Pro gemini-2.5-pro-official | $2.00 | $16.00 | −35% |
Gemini 2.5 Flash gemini-2.5-flash-official | $0.48 | $4.00 | −35% |
Gemini 2.5 Flash Lite gemini-2.5-flash-lite-official | $0.16 | $0.64 | −50% |
Gemini 2.0 Flash gemini-2.0-flash-official | $0.24 | $0.96 | −50% |
Gemini 2.0 Flash LiteCheapest gemini-2.0-flash-lite-official | $0.12 | $0.48 | −50% |
DeepSeek / Qwen / GLM / Kimi
8 models| Model | Input / MTok | Output / MTok | Savings |
|---|---|---|---|
DeepSeek V3.2Popular deepseek-v3.2 | $0.80 | $3.20 | −30% |
Qwen 3.5 Plus qwen3.5-plus | $0.80 | $4.80 | −45% |
Qwen 3.5 Flash qwen3.5-flash | $0.24 | $2.40 | −30% |
Qwen 3 Max qwen3-max | $1.40 | $5.60 | −30% |
GLM-5 glm-5 | $0.80 | $3.60 | −45% |
Kimi K2.5 kimi-k2.5 | $0.80 | $4.20 | −45% |
MiniMax M2.5 MiniMax-M2.5 | $0.42 | $1.68 | −40% |
Nano Banana 2Free Tier nano-banana-2 | $0.05 | $0.30 | FREE |
All prices per million tokens (LLM) or per generation/request (Image/Video/Audio). 100 credits = $1 USD.
New models added weekly. One API key for everything.
Drop-in replacement.
Zero config.
1# Set your Neolab API key2export NEOLAB_API_KEY=rk_your_key_here34# That's it. You're ready to use5# 80+ models from 7+ providers.
Every AI coding tool.
Unified.
One Neolab API key works across all five tools. Full API call logs, real-time cost and usage dashboards, and per-model performance analytics.
OpenClaw
The fastest-growing AI agent. Configure Neolab as your provider — Claude Sonnet/Opus, Codex, and Gemini 3.0 Pro through one interface.
Models: Claude, GPT-5, Gemini, DeepSeek, Qwen + 60 more
~/.openclaw/openclaw.json
{
"models": {
"providers": {
"neolab-claude": {
"baseUrl": "https://api.neolab.build/v1",
"apiKey": "rk_YOUR_KEY",
"api": "anthropic-messages",
"models": [
{ "id": "claude-opus-4-6" },
{ "id": "claude-sonnet-4-6" }
]
},
"neolab-codex": {
"baseUrl": "https://api.neolab.build/v1/codex",
"apiKey": "rk_YOUR_KEY",
"api": "openai-responses"
},
"neolab-gemini": {
"baseUrl": "https://api.neolab.build/v1/gemini",
"apiKey": "rk_YOUR_KEY",
"api": "openai-completions"
}
}
}
}Claude Code
Drop-in proxy for Claude Code. Same CLI, same models — pay only for what you use.
export ANTHROPIC_BASE_URL=https://api.neolab.build/v1Models: Opus 4.6, Sonnet 4.6, Haiku 4.5
OpenCode
Multi-provider coding agent. Configure once — access all models through one config file.
~/.config/opencode/opencode.jsonModels: Claude, GPT-5, Gemini, DeepSeek, Qwen + 60 more
Codex CLI
Route Codex CLI through Neolab. All GPT-5.x Codex models at a fraction of the cost.
export OPENAI_BASE_URL=https://api.neolab.build/v1/codexModels: GPT-5 / 5.1 / 5.2 / 5.3 Codex
Gemini CLI
Full Gemini CLI compatibility. Massive context windows, lower cost.
export GEMINI_API_BASE_URL=https://api.neolab.build/v1/geminiModels: Gemini 3.1 / 3.0 / 2.5 Pro, Flash, Thinking
Built by devs.
For devs.
OpenAI-compatible API — use any existing SDK. Just change the base URL and API key. Works with Python, TypeScript, Go, and more.
OpenAI-compatible
Drop-in replacement for any OpenAI SDK.
All providers, one key
Claude, GPT, Gemini, DeepSeek — one endpoint.
Streaming support
Full SSE streaming for all models.
Credit-based billing
100 credits = $1 USD. Pay only for usage.
from openai import OpenAI
client = OpenAI(
api_key="rk_your_key",
base_url="https://api.neolab.build/v1"
)
response = client.chat.completions.create(
model="claude-opus-4-6",
messages=[{"role": "user",
"content": "Hello!"}]
)
print(response.choices[0].message.content)Global by
default.
Deploy once, run everywhere. Our edge network spans 17 data centers across 6 continents, delivering sub-50ms latency to 99% of the world.
Latency measured from nearest edge node
Performance you
can measure.
Trust is
non-negotiable.
Enterprise-grade security isn't optional. It's built into every layer of our platform, from infrastructure to application.
SOC 2 Type II
Independently audited security controls with continuous monitoring.
End-to-end encryption
AES-256 encryption for data at rest and TLS 1.3 in transit.
Zero-trust architecture
Every request is authenticated and authorized. No exceptions.
GDPR & HIPAA
Full compliance with data protection and healthcare regulations.
“We consolidated five AI providers into one Neolab API key. Our monthly AI spend dropped 60% and our integration code went from 2,000 lines to 200.”
David Park
CTO, Lumino AI
60% cost savings
Trusted by forward-thinking teams
Ready to
ship faster?
Claude Code, OpenCode, Codex CLI, Gemini CLI, and OpenClaw — all live. Drop in your API key and start coding in seconds.
No credit card required — 100 credits = $1 USD