Inference API

One API. Frontier + open-source models. Zero friction.

Name: BLACKBOX AI Inference API
Author: BLACKBOX AI

Access every major AI model through a single unified endpoint. Drop-in OpenAI-compatible, so your existing code works instantly — just swap the base URL.

Get API Key Search Models

Models

Frontier and Open-Source Models.

Inputs	Context	Max Out	Input $/M	Output $/M	Think	Data	Tags	Provider
ImgTxt	1M	128K	$5	$25		No train	FilesReasoningToolsVision	TextAnthropic
ImgTxt	1M	128K	$3	$15		No train	FilesReasoningToolsVision	TextAnthropic
AudFileImgTxtVid	1.0M	65.5K	$1.25	$10		No train	ReasoningTools	TextGoogle
Txt	204.8K	131K	$0.30	$1.20		Check	CacheReasoningTools	TextMinimax
ImgTxt	256K	256K	$0.50	$2.80		Check	CacheReasoningToolsVision	TextMoonshot
ImgTxt	400K	128K	$1.75	$14		No train	FilesCacheReasoningToolsVision	TextOpenAI
Txt	41.0K	16.4K	$0.10	$0.30		Opt-out	ReasoningTools	TextAlibaba
Txt	160K	32.8K	$0.07	$0.27		Opt-out	ReasoningTools	TextAlibaba
Txt	256K	65.5K	$1.20	$6		Opt-out	CacheReasoningTools	TextAlibaba
ImgTxt	1M	64K	$0.40	$2.40		Opt-out	FilesReasoningToolsVision	TextAlibaba
ImgTxt	262.1K	262.1K	$0.30	$2.90		Opt-out	FilesReasoningToolsVision	TextAlibaba
Txt	262.1K	66.5K	$0.40	$1.60	—	Opt-out	Tools	TextAlibaba
Txt	256K	256K	$0.50	$1.20		Opt-out	ReasoningTools	TextAlibaba
Txt	1M	65.5K	$1	$5	—	Opt-out	Tools	TextAlibaba
Txt	32.8K	32.8K	$0.01	<$0.01	—	Opt-out	—	EmbeddingAlibaba
Txt	32.8K	32.8K	$0.02	<$0.01	—	Opt-out	—	EmbeddingAlibaba
Txt	32.8K	32.8K	$0.05	<$0.01	—	Opt-out	—	EmbeddingAlibaba
Txt	262.1K	65.5K	$0.84	$3.38	—	Opt-out	—	TextAlibaba
Txt	262.1K	32.8K	$1.20	$6	—	Opt-out	CacheTools	TextAlibaba
Txt	262.1K	32.8K	$0.09	$1.10	—	Opt-out	—	TextAlibaba
Txt	65.5K	65.5K	$0.15	$1.50	—	Opt-out	—	TextAlibaba
ImgTxt	256K	256K	$0.22	$0.88	—	Opt-out	FilesCacheVision	TextAlibaba
ImgTxt	256K	256K	$0.22	$0.88		Opt-out	ReasoningToolsVision	TextAlibaba
Txt	41.0K	16.4K	$0.06	$0.24		Opt-out	ReasoningTools	TextAlibaba
Txt	41.0K	16.4K	$0.07	$0.46	—	Opt-out	Tools	TextAlibaba

1–25 of 215

...

See it in action

What makes it powerful.

api.blackbox.ai

# Chat completion — OpenAI-compatible

$ curl https://api.blackbox.ai/chat/completions \

-H "Authorization: Bearer $BLACKBOX_API_KEY" \

-H "Content-Type: application/json" \

-d '{

"model": "gpt-4",

"messages": [{"role":"user","content":"Explain BLACKBOX AI in one sentence"}],

"stream": false

HTTP/1.1 200 OK

{

"id": "chatcmpl-9f2a3b...",

"model": "gpt-4",

"choices": [{

"message": {

"role": "assistant",

"content": "BLACKBOX AI is an enterprise platform

providing frontier and open-source AI models through a single

OpenAI-compatible API for inference, code

generation, and multi-agent orchestration."

"finish_reason": "stop"

}],

"usage": { "prompt_tokens": 14, "completion_tokens": 38 }

}

Universal model access

Route requests to frontier and open-source models like Claude, GPT, Gemini, Grok, Llama, Mistral, DeepSeek, and Qwen through one API key. No separate accounts, no per-provider SDKs.

Automatic fallback routing ensures uptime even when individual providers experience outages. Smart load balancing distributes requests for optimal latency.

api.blackbox.ai — model routing

# Route to any model through one API key

→ "gpt-4" routed to OpenAI

→ "claude-sonnet" routed to Anthropic

→ "gemini-3" routed to Google

→ "grok-4" routed to xAI

→ "llama-3" routed to Meta

→ "mistral-large" routed to Mistral

Frontier + open-source models • 1 API key • automatic fallback

OpenAI-compatible endpoints

Use /v1/chat/completions, /v1/embeddings, and /v1/images/generations with the same request format you already know. Migrate in under 5 minutes.

Full streaming support, function calling, JSON mode, and vision inputs across all compatible models. Response format matches OpenAI spec exactly.

migration — 2 minutes

# Before (OpenAI SDK)

baseURL: "https://api.openai.com/v1"

apiKey: process.env.OPENAI_API_KEY

# After (Blackbox — same SDK)

baseURL: "https://api.blackbox.ai"

apiKey: process.env.BLACKBOX_API_KEY

✓ Same request format • same response shape

✓ Streaming, function calling, JSON mode

Enterprise-grade infrastructure

99.9% uptime SLA, sub-200ms median latency, and usage-based billing with no per-seat costs. Scale from prototype to production without renegotiating contracts.

SOC 2 compliant infrastructure with data residency options. Rate limits scale automatically with your plan. Real-time usage dashboards and cost alerts.

infrastructure — dashboard

Uptime

99.99%

30-day rolling

Latency p50

89ms

↓ 12ms

Requests

2.8M

+18% MoM

Model Access

Frontier + OSS

Claude • GPT • Llama • Mistral

FAQ

Common Questions.

IS THE API OPENAI-COMPATIBLE?

Yes. Use the same SDK and request format you already know — just swap the base URL and API key. Supports /v1/chat/completions, /v1/embeddings, and /v1/images/generations with full streaming, function calling, JSON mode, and vision inputs.

WHAT MODELS ARE AVAILABLE?

The API includes frontier and open-source models such as Claude Opus-4.6, GPT-5.2, Gemini-3, Grok-4, Llama 4, Mistral, DeepSeek, and Qwen from leading providers. New models are added continuously as they launch.

HOW IS PRICING STRUCTURED?

Pay per token with no per-seat fees. The free tier includes access to the Grok Code Fast Model. Pro starts at $10/mo with $30 in credits, Pro Plus at $20/mo with $50 in credits, and Pro Max at $40/mo with $100 in credits. Enterprise volume discounts are available.

DO YOU SUPPORT STREAMING?

Yes. Full SSE streaming support is available across all chat completion models. Response format matches the OpenAI spec exactly, so existing streaming implementations work without modification.

WHAT SECURITY CERTIFICATIONS DO YOU HAVE?

Infrastructure is SOC 2 compliant with TLS 1.3 encryption in transit and AES-256 at rest. Enterprise plans add end-to-end encryption with zero-knowledge architecture, RBAC with SSO (Okta, Azure AD, Google Workspace), and comprehensive audit logging.

WHAT IS THE API UPTIME GUARANTEE?

The API provides a 99.9% uptime SLA with sub-200ms median latency. Automatic fallback routing ensures availability even when individual providers experience outages, and smart load balancing optimizes for the lowest latency.

CAN I USE THE API WITH EXISTING OPENAI SDKS?

Yes. The API is fully compatible with the official OpenAI Python and Node.js SDKs, as well as LangChain, LlamaIndex, and other popular frameworks. Migration takes under 5 minutes — just change the base URL.

Start with BLACKBOX

Join 30M+ developers building with BLACKBOX AI.

Get Access Read Docs