Save up to 88% on AI model APIs
GPT, Claude, Gemini, image and video models in one OpenAI-compatible API. One key, one wallet.
- Top up from $10
- Pay per call
- No subscription
- Claude prompt caching — repeated context up to 10× cheaper
50+ models, one key
Pass model: "smart" and each task goes to the right model on its own.
- Easy work — translation, cleanups, extraction — goes to fast, cheap models
- Hard work — code, analysis, long-form — automatically gets the top tier
- Transparent: the response reports the actual model, tier and signals
Live catalog rates
Every model in the API with live prices in US dollars. Compare with the vendors' official rates for the same unit.
Showing 10 of 87 models
| Model | Price | Unit | Discount | Model page |
|---|---|---|---|---|
GPT-5.6 Luna gpt-5.6-luna · OpenAI | Official price: | per 1M tokensofficial: 3:1 blend · $0.20 in / $1.20 out | -88% | |
Claude Opus 4.7 claude-opus-4.7 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $5 in / $25 out | -85% | |
Claude Opus 5 claude-opus-5 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $5 in / $25 out | -78% | |
Claude Sonnet 4.6 claude-sonnet-4.6 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $3 in / $15 out | -78% | |
Nano Banana Pro gemini-image-pro · Google | Official price: | per imageofficial: $0.134 · 1K/2K | -78% | |
Claude Sonnet 5 claude-sonnet-5 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $2 in / $10 out | -78% | |
Claude Opus 5.5 claude-opus-5.5 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $4 in / $20 out | -78% | |
Claude Sonnet 5.5 claude-sonnet-5.5 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $2 in / $10 out | -78% | |
Claude Fable 5.1 claude-fable-5.1 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $10 in / $50 out | -78% | |
Claude Opus 4.6 claude-opus-4.6 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $5 in / $25 out | -78% | |
Claude Opus 4.8 claude-opus-4.8 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $5 in / $25 out | -78% | |
Claude Fable 5.2 claude-fable-5.2 · Anthropic | Official price: | per 1M tokensofficial: 3:1 blend · $8 in / $40 out | -78% | |
GPT-6 Sol gpt-6-sol · OpenAI | Official price: | per 1M tokensofficial: 3:1 blend · $2 in / $10 out | -75% | |
GPT-6.1 Sol gpt-6.1-sol · OpenAI | Official price: | per 1M tokensofficial: 3:1 blend · $2 in / $10 out | -75% | |
Nano Banana gemini-image · Google | Official price: | per imageofficial: $0.039 · 1024×1024 | -70% | |
Wan 2.7 text-to-video wan/2-7-text-to-video · Alibaba | Official price: | per clipofficial: $0.10/s × 5 s · 720P | -68% | |
Wan 2.7 image-to-video wan/2-7-image-to-video · Alibaba | Official price: | per clipofficial: $0.10/s × 5 s · 720P | -68% | |
GPT-6 Luna gpt-6-luna · OpenAI | Official price: | per 1M tokensofficial: 3:1 blend · $0.10 in / $0.50 out | -64% | |
Nano Banana 2 gemini-image-2 · Google | Official price: | per imageofficial: $0.067 · 1K | -60% | |
Nano Banana 2 Lite nano-banana-2-lite · Google | Official price: | per imageofficial: $0.0336 · 1K | -60% | |
MiniMax 3 Hailuo minimax-3-hailuo · MiniMax | Official price: | per clipofficial: $0.08/s × 5 s · 768P | -58% | |
Veo 3.1 Quality veo-3.1-quality · Google | Official price: | per clip720p — $0.863 · 1080p — $0.881 · 4k — $1.29official: $0.40/s × 5 s · 1080p | -55% | |
Kling V3 Pro kling-v3-pro · Kuaishou | Official price: | per second of videoofficial: $0.168/s · 1080P · with audio | -36% | |
GPT-5.6 Terra gpt-5.6-terra · OpenAI | Official price: | per 1M tokensofficial: 3:1 blend · $2 in / $12 out | -33% | |
GPT-5.6 Sol gpt-5.6-sol · OpenAI | Official price: | per 1M tokensofficial: 3:1 blend · $4 in / $20 out | -24% | |
Nano Banana Pro VIP nano-banana-pro-vip · Google | Official price: | per imageofficial: $0.134 · 1K/2K | -20% | |
Kling V3 kling-v3 · Kuaishou | Official price: | per second of videoofficial: $0.126/s · 720P · with audio | -16% | |
GPT-5.5 gpt-5.5 · OpenAI | Official price: | per 1M tokensofficial: 3:1 blend · $5 in / $30 out | -6% | |
Wan 2.7 text-to-video wan-3.0 · Alibaba | Official price: | per second of video480p — $0.0482 · 720p — $0.0948 · 1080p — $0.19official: $0.10/s · 720P | -5% | |
Kling V2.6 kling-v2.6 · Kuaishou | Official price: | per second of videoofficial: $0.168/s · 1080P | -5% | |
Perplexity Sonar sonar · Perplexity | input $0.60 / output $0.60 | per 1M tokens | — | |
Grok 4.7 grok-4.7 · xAI | input $0.72 / output $2.16 | per 1M tokens | — | |
GLM 5.3 glm-5.3 · Z.ai | input $0.84 / output $2.64 | per 1M tokens | — | |
Kimi K2.7 Code kimi-k2.7-code · Moonshot AI | input $0.798 / output $3.36 | per 1M tokens | — | |
DeepSeek V4 Pro deepseek-v4-pro · DeepSeek | input $1.44 / output $2.88 | per 1M tokens | — | |
Qwen 3.8 Max qwen3.8-max · Alibaba | input $2.04 / output $6.12 | per 1M tokens | — | |
GPT Image 2 gpt-image-2 · OpenAI | $0.0265 | per image | — | |
Seedream 5.0 Lite seedream-5.0-lite · ByteDance | $0.042 | per image | — | |
Seedance 2.0 Fast seedance-2.0-fast · ByteDance | from $0.0653 | per second of video480p — $0.0653 · 720p — $0.145 | — | |
Veo 3.1 Fast veo-3.1-fast · Google | from $0.558 | per clip720p — $0.558 · 4k — $1.15 | — | |
ElevenLabs v3 eleven_v3 · ElevenLabs | $0.107 | per 1K characters | — | |
Qwen 3.8 Flash qwen3.8-flash · Alibaba | input $0.153 / output $0.479 | per 1M tokens | — | |
Grok 4.7 X Search grok-4.7-x-search · xAI | input $0.72 / output $2.16 | per 1M tokens | — | |
GLM 5.2 glm-5.2 · Z.ai | input $0.84 / output $2.64 | per 1M tokens | — | |
Perplexity Sonar Pro sonar-pro · Perplexity | input $0.72 / output $3.36 | per 1M tokens | — | |
GPT Image 2.5 gpt-image-2.5 · OpenAI | $0.0265 | per image | — | |
Seedream 5.0 Pro seedream-5.0-pro · ByteDance | $0.108 | per image | — | |
Seedance 2.0 seedance-2.0 · ByteDance | from $0.0816 | per second of video480p — $0.0816 · 720p — $0.181 · 1080p — $0.449 · 4k — $0.933 | — | |
ElevenLabs Multilingual v2 eleven_multilingual_v2 · ElevenLabs | $0.107 | per 1K characters | — | |
Perplexity Sonar Reasoning Pro sonar-reasoning-pro · Perplexity | input $0.60 / output $1.92 | per 1M tokens | — | |
GPT Image 2 VIP gpt-image-2-vip · OpenAI | $0.0398 | per image | — | |
Seedance 2.0 Pro seedance-2.0-pro · ByteDance | from $0.0816 | per second of video480p — $0.0816 · 720p — $0.181 · 1080p — $0.449 | — | |
Veo 3.1 Lite veo-3.1-lite · Google | from $0.265 | per clip720p — $0.265 · 4k — $1.02 | — | |
ElevenLabs v4 Turbo eleven_v4_turbo · ElevenLabs | $0.0533 | per 1K characters | — | |
Seedance 2.5 seedance-2.5 · ByteDance | from $0.125 | per second of video480p — $0.125 · 720p — $0.277 · 1080p — $0.682 | — | |
Kling O3 kling-o3 · Kuaishou | $0.146 | per second of video | — | |
Veo 3 Fast veo-3-fast · Google | $0.465 | per clip | — | |
ElevenLabs Turbo 2.5 eleven_turbo_v2_5 · ElevenLabs | $0.0533 | per 1K characters | — | |
Seedance 2.0 Mini seedance-2.0-mini · ByteDance | from $0.0816 | per second of video480p — $0.0816 · 720p — $0.181 | — | |
Kling O3 Pro kling-o3-pro · Kuaishou | $0.186 | per second of video | — | |
Veo 3 Quality veo-3-quality · Google | $0.863 | per clip | — | |
Kling V2.5 Standard kling-v2.5-standard · Kuaishou | $0.0929 | per second of video | — | |
Veo Extend veo-extend · Google | $0.465 | per clip | — | |
Kling V2.5 Pro kling-v2.5-pro · Kuaishou | $0.0929 | per second of video | — | |
GPT-6.1 Terra gpt-6.1-terra · OpenAI | input $0.135 / output $0.675 | per 1M tokens | — | |
GPT Image 2.6 gpt-image-2.6 · OpenAI | $0.0265 | per image | — | |
Nano Banana 2.1 nano-banana-2.1 · Google | $0.0265 | per image | — | |
GPT Image 2.6 Flare gpt-image-2.6-flare · OpenAI | $0.0465 | per image | — | |
Seedream 5.5 seedream-5.5 · ByteDance | $0.0531 | per image | — | |
GPT Image 2.6 Sunburst gpt-image-2.6-sunburst · OpenAI | $0.0557 | per image | — | |
Midjourney V8 Relax midjourney-v8-relax · Midjourney | $0.0692 | per image | — | |
Midjourney V8 Fast midjourney-v8-fast · Midjourney | $0.0856 | per image | — | |
Midjourney V8 Turbo midjourney-v8-turbo · Midjourney | $0.154 | per image | — | |
MiniMax H3 minimax-h3 · MiniMax | from $0.0615 | per second of video768p — $0.0615 · 2k — $0.0999 | — | |
Wan 3.0 Prime wan-3.0-prime · Alibaba | from $0.0722 | per second of video480p — $0.0722 · 720p — $0.147 · 1080p — $0.292 | — | |
Kling V2.6 Motion 720p kling-v2.6-motion-720p · Kuaishou | $0.0929 | per second of video | — | |
Kling O1 kling-o1 · Kuaishou | $0.106 | per second of video | — | |
Seedance 2.5 Flash seedance-2.5-flash · ByteDance | from $0.125 | per second of video480p — $0.125 · 720p — $0.277 | — | |
Kling V4 Flash kling-v4-flash · Kuaishou | from $0.128 | per second of video720p — $0.128 | — | |
Kling V4 kling-v4 · Kuaishou | from $0.181 | per second of video720p — $0.181 · 1080p — $0.271 | — | |
Kling V4 Omni kling-v4-omni · Kuaishou | from $0.181 | per second of video720p — $0.181 · 1080p — $0.271 | — | |
Seedance 2.0 Eco seedance-2.0-eco · ByteDance | from $0.181 | per second of video720p — $0.181 · 1080p — $0.449 · 4k — $0.933 | — | |
Kling V2.6 Motion 1080p kling-v2.6-motion-1080p · Kuaishou | $0.186 | per second of video | — | |
Seedance 2.5 Eco seedance-2.5-eco · ByteDance | from $0.277 | per second of video720p — $0.277 · 1080p — $0.682 | — | |
Kling V2.1 Master kling-v2.1-master · Kuaishou | $0.305 | per second of video | — | |
Gemini Omni Flash Video gemini-omni-flash-video · Google | $0.66 | per clip | — | |
Gemini Omni Flash Video Edit gemini-omni-flash-video-edit · Google | $1.76 | per clip | — |
Zerocoder prices are the live GET /v1/models price list; text models have two prices per 1M tokens — input and output (output costs more). Discount — vs the vendor's official price for the same unit (second of video, clip, image, 1M tokens), checked 4 October 2026; all prices are in US dollars (Zerocoder prices converted at the internal rate), and for text the discount compares both prices blended 3 : 1 (input : output). Sources and assumptions are on the model pages: Nano Banana API · Claude API · Kling API · Wan API · ChatGPT API · MiniMax Hailuo API · Veo API
Why overpay vendors?
The same Claude, GPT and Gemini through one key — below the vendors' official list prices; the saving per model is computed on the right from the live price list. Wallet billing, pay only for the calls you actually make.
Need volume pricing for a team? Talk to us
Powered by the best AI models
87 models in one API: 29 for text, 18 for images, 36 for video and 4 for speech. The full machine-readable list is GET /v1/models.
Models via the API
Every family has its own page: current ids, prices per second, image or 1M tokens (input and output), code samples and limits. Text, images and video behind one key.
Text
/v1/messagesClaude models via the Anthropic-compatible /v1/messages and the OpenAI format
GPT models from flagships to light ones via the OpenAI-compatible chat/completions
DeepSeek V4 Pro: reasoning, maths and code via the OpenAI-compatible API
Alibaba Qwen 3.8: the Max flagship and fast Flash, function calling
xAI Grok 4.7: lively dialogue and creative copy, streaming
Sonar, Sonar Pro and Reasoning Pro: answers with live web search and sources
Kimi K2.7 Code: a model for programming and coding agents
GLM 5.3 and 5.2: general models for text, code and agents
Images
/v1/images/generationsGemini images: generation and photo edits with up to 4 references
GPT Image 2: accurate in-image text and careful edits
ByteDance Seedream 5.0: detailed photos and illustrations, Lite and Pro
Video
/v1/videosText- and image-to-video with audio, 4–10 seconds, priced by resolution
Cinematic video, motion control and image-to-video
Google Veo 3 and 3.1: clips with native audio and speech
Hailuo 3: fast clips from text and photos
Alibaba Wan 2.7: text- and image-to-video, one price per 4–10 s clip
How much does smart routing save?
The router sends easy work to cheap models and hard work to the top tier. Set the sliders to your workload profile:
- Get a keyone click in the API dashboard
- Top up the walletpay as you go, no subscription
- Make the callevery call shows in your history
Change two values. Reach every model.
Swap the base URL and the API key — your requests, streaming and response handling stay exactly as they are.
Base URLhttps://zerocoder.com /api/v1Anthropic SDK — https://zerocoder.com, without /v1
// Only the base URL and the key changeimport OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://zerocoder.com/api/v1", apiKey: process.env.ZEROCODER_API_KEY,}); const res = await client.chat.completions.create({ model: "smart", // or any id from GET /v1/models messages: [{ role: "user", content: "Hello!" }],});// base URL without /v1 — the Anthropic SDK adds itimport Anthropic from "@anthropic-ai/sdk"; const client = new Anthropic({ baseURL: "https://zerocoder.com/api", apiKey: process.env.ZEROCODER_API_KEY,}); const msg = await client.messages.create({ model: "smart", max_tokens: 1024, messages: [{ role: "user", content: "Hello!" }],});# Quick check from the terminalcurl https://zerocoder.com/api/v1/chat/completions \ -H "Authorization: Bearer $ZEROCODER_API_KEY" \ -H "content-type: application/json" \ -d '{"model": "smart", "messages": [{"role": "user", "content": "Hello!"}]}' # Wallet balance and priced model listcurl https://zerocoder.com/api/v1/balance \ -H "Authorization: Bearer $ZEROCODER_API_KEY"curl https://zerocoder.com/api/v1/models \ -H "Authorization: Bearer $ZEROCODER_API_KEY"Anthropic list price; bars and discount compare both prices blended 3 : 1 (input : output); checked 4 October 2026
We plug into your stack
We'll wire the API into your business
Don't want to build it yourself — the Zerocoder team designs and ships a solution on our API for your workflows.
Chatbots & assistants
Customer support, lead qualification, internal copilots — in Telegram, WhatsApp and on your site.
Content on autopilot
Product descriptions, articles, images and social video — generated on schedule straight into your CMS.
CRM & process automation
Ticket triage, call summaries, scoring — wired into Bitrix24, amoCRM, spreadsheets and internal systems.
Products already run on the API
100+ companies use the Zerocoder API — from bots and internal assistants to products that raised over $100M combined. A few examples:

Cybersecurity, USA: text models score inquiries and prepare summaries for buyer-vendor matching.

EdTech platform: a tutor-matching assistant and study-material generation through the text API.

PropTech marketplace in Dubai and Kazakhstan: venue descriptions and smart routing of text workloads.

Logistics: shipment-request parsing and automatic customer replies through the API.
“Zerocoder is a reliable service. Great to get a working MVP in under 2 weeks and $2000.”
“George and his team of experts easily solve problems at the intersection of no-code and code.”
“This team helped many startups save time and resources with AI and no-code development. Our platform now has a flawless design!”
FAQ
Do you store my prompts and generated files?
We don't store the text of your requests or responses — billing keeps only the model, volume and amount charged. Images and videos generated via the API stay available by link for 30 days and are then deleted automatically, so save them on your side. Requests themselves are processed by the model providers under their own policies.
How is this cheaper than the official APIs?
We aggregate traffic across many customers and buy capacity in bulk, so per-call prices are usually well below direct provider rates — compare the economics block above with the official price lists.
What is smart routing?
Pass model: "smart" and the built-in router scores each request's complexity (length, code, reasoning, math, format) and picks the right tier. You're billed at the routed model's price, and the response reports which model ran.
Which SDKs does it work with?
The endpoint is compatible with the Anthropic Messages API — the official Anthropic SDK and any HTTP client work as-is. Images use the OpenAI Images format. Examples are in the docs.
Which models are available?
50+ models: text — GPT, Claude (Opus/Sonnet/Fable), Gemini; images — Nano Banana, GPT Image, Seedream; video — Kling, Veo, Seedance, Minimax, Wan. The full priced list is GET /v1/models.
Is there a subscription or minimum commitment?
No subscription — a prepaid wallet and per-call billing. Top up once and pay only for what you use; auto top-up is available.
Do failed calls get charged?
No. If the upstream fails after our fallbacks, the charge is refunded automatically and the response says so.
Plug the API in within minutes
A key in one click, your first call five minutes later.
Zerocoder API gives you 50+ AI models behind one key and one wallet: text (ChatGPT, Claude, Gemini), images (Nano Banana, GPT Image) and video (Kling, Veo, Seedance). Bulk contracts keep per-call prices below official rates — up to 88%, and the built-in smart routing assigns every request to the right tier — easy calls go to fast, inexpensive models while hard ones get the top tier, so your integration never overpays. See also the API documentation and our business solutions.



