Utvecklarplattform

Ett API.
Alla AI-funktioner.

Sluta jonglera SDK:er. Få tillgång till 100+ AI-modeller, bildgenerering, videoskapande, röstsyntes, agenter, arbetsytor och mer — allt genom en enda API-nyckel.

1from openai import OpenAI
2 
3client = OpenAI(
4 base_url="https://kunya.ai/api/v1",
5 api_key="kunya_sk_..."
6)
7 
8response = client.chat.completions.create(
9 model="claude-4-sonnet",
10 messages=[{"role": "user",
11 "content": "Explain quantum computing"}],
12 stream=True
13)
Response — 200 OKlatency: 142ms · tokens: 847
{"id": "chatcmpl-9x2k...",
"model": "claude-4-sonnet",
"choices": [{ ... }]
}
Vad du kan bygga

Varje AI-domän. En endpoint.

Från chattavslutningar till fullständig helpdesk-automatisering.

Chattavslutningar

OpenAI-kompatibel. Streaming eller batch. 100+ modeller.

Bildgenerering

FLUX, DALL-E 3, Stable Diffusion.

Videogenerering

Sora, Veo, Kling, MiniMax och Runway.

Ljud & röst

Text-till-tal, tal-till-text, röstkloning, musik.

AI-agenter

19 agentmallar. Autonom uppgiftsexekvering.

Arbetsytor

Programmatiska dokument, databaser och whiteboards.

Blogg & SEO

AI-drivet blogg-CMS.

Helpdesk

100+ endpoints. Ärenden, kunder, hjälpcenter.

CRM

Kontakter, företag, affärer, pipelines.

Game Studio

Three.js, Unity och Blender-integration.

Skrivstudio

Långformat med varumärkesröst.

Språkinlärning

Grammatik, CEFR, ordförråd, uttal.

Utvecklarupplevelse

Byggt för utvecklare.

Förstklassiga verktyg så du spenderar tid på att bygga.

OpenAPI 3.1-spec

Schema med kostnadsuppskattningar och streamingflaggor.

OpenAI-kompatibel

Byt bas-URL och API-nyckel — din befintliga SDK-kod fungerar.

Strukturerade fel

Felkatalog med HTTP-koder och retry-vägledning.

Transparenta gränser

Gränser i svarsheaders.

Scopade nycklar

Skapa nycklar med detaljerade behörigheter.

LLM-optimerade docs

/llms-full.txt för AI-kodningsassistenter.

Your API Key
kunya_sk_••••••••••••••••••••••••
Scoped
No expiry
1,000 req/min
100+ modeller

Alla stora labb. En API-nyckel.

Ingen leverantörsinlåsning. Byt modell med en parameter.

OpenAI

GPT-4oGPT-4 Turboo1o3-miniDALL-E 3WhisperTTS

Anthropic

Claude 4 OpusClaude 4 SonnetClaude 3.5 Haiku

Google

Gemini 2.5 ProGemini 2.0 FlashImagen 3VeoLyria

Meta

Llama 4 MaverickLlama 4 ScoutLlama 3.3 70B

Mistral

Mistral LargePixtral LargeCodestral

Others

DeepSeek R1GrokFLUXKlingSoraSunoMiniMax

Varför Kunya API istället för direkta leverantörs-API:er?

Capability
Direct Provider APIs
Kunya API
100+ models from one endpoint
Single API key for everything
OpenAI SDK compatible
Chat completions
Image generation (multi-provider)
Video generation
Voice cloning & TTS
AI agents with memory & tools
Workspace/database API
Blog CMS API
Support helpdesk API (100+ endpoints)
CRM & outreach automation
Unified billing & usage tracking
Scoped keys with fine-grained permissions
OpenAPI 3.1 spec with cost extensions
Webhook notifications

One Integration, Not Twelve

With direct provider APIs, you need separate accounts, keys, SDKs, error handling, and billing for OpenAI, Anthropic, Google, Stability, Runway, and more. Kunya gives you one key, one SDK, one bill, and one error format for all of them.

Switch Models in One Line

Testing Claude vs GPT-4o vs Gemini? Change the model parameter. No SDK swap, no auth change, no endpoint rewrite. A/B test models in production without touching infrastructure.

Beyond Chat Completions

OpenAI gives you chat and images. Kunya gives you chat, images, video, audio, voice, music, agents, workspaces, blog CMS, CRM, support desk, game studio, and language tools — all from the same API key.

Enterprise-Ready Security

Scoped API keys let you grant chat-only or images-only access without exposing your full account. Per-key spend limits, real-time usage tracking, and webhook alerts give you production-grade control.

Vanliga frågor

Is the Kunya API compatible with the OpenAI SDK?

Yes. Kunya's chat completions endpoint is fully OpenAI-compatible. Point your existing OpenAI Python or Node.js SDK at https://kunya.ai/api/v1 and change your API key — your code works immediately with 100+ models from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, and more.

How many models are available?

Over 100 models from every major AI lab: OpenAI (GPT-4o, o1, DALL-E 3), Anthropic (Claude 4), Google (Gemini 2.5, Imagen 3, Veo), Meta (Llama 4), Mistral, DeepSeek, xAI (Grok), and many more. New models are added within days of release.

How are API calls priced?

Pay-per-use based on the model you select. Each model has a transparent per-token (for text) or per-unit (for images, audio, video) price listed in our model catalog. Credits are deducted in real-time and you can set spend limits per key.

Can I use the API for production applications?

Absolutely. The API is designed for production use with enterprise-grade rate limits, 99.9% uptime SLA on paid plans, structured error handling, webhook notifications, and scoped API keys for secure multi-tenant deployments.

Do you support streaming responses?

Yes. Chat completions, writing generation, and agent responses all support server-sent events (SSE) streaming. Set stream: true in your request and receive tokens as they're generated with sub-100ms first-token latency.

Is there an OpenAPI specification?

Yes. A full OpenAPI 3.1 spec is available at /api/v1/openapi with custom extensions for cost estimates (x-cost-estimate), streaming support (x-streaming), and call types (x-call-type). Import it into Postman, use it to auto-generate SDKs, or feed it to AI coding assistants.

What's the difference between the API and the dashboard?

The dashboard (app.kunya.ai) is the GUI for all Kunya features — chat, image generation, workspaces, etc. The API (/api/v1/) gives you programmatic access to the same capabilities so you can build them into your own products. Both use the same underlying infrastructure.

Börja bygga. Leverera snabbare.

Gratis nivå utan kreditkort. Få din API-nyckel på 30 sekunder.