Skip to main content
Allgate
Start free

LLM / IMAGE / VIDEO / AUDIO

Every model.One API.

Build with leading language models. Create images and videos. Connect speech workflows. One gateway, one balance and clear usage-based pricing — from your first experiment to your application.

A prompt. A new possibility.Explore the collection

Create the impossible.

Seedance 2.5 · AI-generated

Create a video

Current language models

GPT-6.1 Sol · Input $4 / 1M tokens

Connect this model
Start building Try the creative studio
  • OpenAI SDK compatible
  • Usage-based billing
  • No subscription
Language modelsCode, reason and build agentsImage generationCampaigns, portraits and designVideo generationFrom a scene to a moving storyAudio & speechSpeech synthesis and transcription
Browse models & pricing

Live model catalog

24 available now

Seedance 2.5 · 720p ByteDance GPT Image 2.5 Flare OpenAI GPT-6.1 Sol OpenAI Claude Opus 5.5 Anthropic Gemini 4 Argon Google DeepSeek V4.1 Flash 1017 DeepSeek Grok 4.7 xAI GLM-5.3 Z.AI Qwen3.8 Max Alibaba Kimi K3 Moonshot AI MiniMax-M3 MiniMax Browse the catalog

THE CREATIVE COLLECTION

One idea. A world of possibilities.

Images and films, unexpected worlds and everyday ideas. Find a spark, open the prompt, make something of your own.

Explore the creative studio

Selected AI-generated examples from GPT Image 2.5 Flare, Gemini 3.1 Flash Image and Seedance 2.5 through Letsllm. Video directions start a new text-to-video creation; live availability and results may differ. Some showcase films use 1080p. Available generation formats and prices are shown with each live model.

The Allgate index

Choose the model.
Know the cost.

Compare capabilities, check the unit price, then create or connect with your chosen model.

24available models

Explore the model reference
Showing 24 / 24 models Available models first · current versions lead

Google

Gemini 3.1 Flash Image

gemini-3.1-flash-image

Image

Released 2026-05-28

1K single-image generation with reported native token usage.

Input
$0.7693/ 1M tokens
Output
$92.3077/ 1M tokens
Available Create an image

OpenAI

GPT Image 2.5 Flare

gpt-image-2.5-flare

Image

Image generation with reported input/output token usage.

Input
$7.6924/ 1M tokens
Output
$46.1539/ 1M tokens
Available Create an image

DeepSeek

DeepSeek V4.1 Flash 1017

deepseek-flash

Chat

1,048,576 context

Released 2026-10-17

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

Input
$0.3/ 1M tokens
Output
$1.2/ 1M tokens
Available Connect API

Google

Gemini 4 Argon

gemini-4-argon

Chat

1,048,576 context

Released 2026-10-13

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

Input
$2/ 1M tokens
Output
$10/ 1M tokens
Available Connect API

Anthropic

Claude Haiku 5.5

claude-haiku-5-5

Chat

1,000,000 context

Released 2026-10-07

Fast Claude model for responsive assistance, classification, and lightweight agents

Input
$0.5/ 1M tokens
Output
$2.5/ 1M tokens
Available Connect API

OpenAI

GPT-6.1 Sol

gpt-6.1-sol

Chat

1,050,000 context

Released 2026-09-29

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

Input
$4/ 1M tokens
Output
$15/ 1M tokens
Available Connect API

OpenAI

GPT-6 Sol

gpt-6-sol

Chat

1,050,000 context

Released 2026-09-22

OpenAI model for complex coding and agentic workflows

Input
$4/ 1M tokens
Output
$15/ 1M tokens
Available Connect API

OpenAI

GPT-6 Luna

gpt-6-luna

Chat

1,050,000 context

Released 2026-09-22

OpenAI's most efficient model for focused, high-volume tasks

Input
$0.2/ 1M tokens
Output
$0.75/ 1M tokens
Available Connect API

Anthropic

Claude Opus 5.5

claude-opus-5-5

Chat

1,000,000 context

Released 2026-09-22

Claude model for long-running agentic coding and knowledge work

Input
$4/ 1M tokens
Output
$20/ 1M tokens
Available Connect API

xAI

Grok 4.7

grok-4.7

Chat

500,000 context

Released 2026-09-21

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

Input
$4/ 1M tokens
Output
$12/ 1M tokens
Available Connect API

OpenAI

GPT-6 Astra

gpt-6-astra

Chat

1,050,000 context

Released 2026-09-04

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

Input
$20/ 1M tokens
Output
$75/ 1M tokens
Available Connect API

Google

Gemini 3.8 Flash

gemini-3.8-flash

Chat

1,048,576 context

Released 2026-09-02

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

Input
$0.75/ 1M tokens
Output
$3.75/ 1M tokens
Available Connect API

Anthropic

Claude Fable 5.1

claude-fable-5-1

Chat

1,000,000 context

Released 2026-09-01

Claude model for demanding reasoning and long-horizon agentic work

Input
$10/ 1M tokens
Output
$50/ 1M tokens
Available Connect API

Z.AI

GLM-5.3

glm-5.3

Chat

1,000,000 context

Released 2026-08-14

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Input
$1.4/ 1M tokens
Output
$4.4/ 1M tokens
Available Connect API

DeepSeek

DeepSeek V4 Pro

deepseek-v4-pro

Chat

Released 2026-08-13

Input
$0.5/ 1M tokens
Output
$2/ 1M tokens
Available Connect API

Alibaba

Qwen3.8 Max

qwen3.8-max

Chat

1,000,000 context

Released 2026-08-03

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

Input
$2/ 1M tokens
Output
$6/ 1M tokens
Available Connect API

Moonshot AI

Kimi K3

kimi-k3

Chat

1,048,576 context

Released 2026-07-16

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Input
$3/ 1M tokens
Output
$15/ 1M tokens
Available Connect API

MiniMax

MiniMax-M3

MiniMax-M3

Chat

1,000,000 context

Released 2026-06-01

MiniMax multimodal model for long-context coding, perception, and agent planning

Input
$0.6/ 1M tokens
Output
$2.4/ 1M tokens
Available Connect API

OpenAI

GPT-5.5

gpt-5.5

Chat

Released 2026-04-23

Input
$2.5/ 1M tokens
Output
$15/ 1M tokens
Available Connect API

USD rates. Each model is billed in the unit shown.

Cost calculator

Estimate your monthly token bill.

Pick a model and your monthly token volume. Demo list prices; your invoice is authoritative.

Demo list prices; your invoice is authoritative

Estimated monthly cost

$0.54

Example call (1K input + 500 output) · $0.0009

Sign up to start
05 Developer experience

Change one line: base_url.

Your existing OpenAI SDK keeps working. Point it at Allgate and auth, routing, billing and logging happen automatically — or call the native protocols directly.

Your first API request

  1. 01 Choose a model from the live catalogue.
  2. 02 Create an API key and set your environment variables.
  3. 03 Send a request, then verify its usage and cost.

Base URL

https://api.allgate.ai/v1

Public production endpoint; call it directly with your API key.

  • OpenAI-compatible
  • SSE streaming
  • tool calls
  • multimodal input
  • OpenAI SDK compatible
  • All endpoints
  • 5-minute setup
Create an account and get a key
console · code
export ALLGATE_BASE_URL='https://api.allgate.ai/v1'
export ALLGATE_API_KEY='YOUR_ALLGATE_API_KEY'

curl --fail-with-body "$ALLGATE_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $ALLGATE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
  "model": "deepseek-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello, Allgate!"
    }
  ]
}'
ALLGATE GATEWAY · OPENAI COMPATIBLE Live

Compatible endpoints

  • POST /v1/chat/completions
  • POST /v1/messages
  • POST /v1/responses
  • POST /v1/embeddings
  • POST /v1/images/generations
  • POST /v1/audio/speech
  • POST /v1/audio/transcriptions
  • POST /v1/videos/generations
  • POST /v1/rerank
Pricing

Pay for usage. No subscription.

Pay by each model’s listed unit; chat separates input and output tokens. Recharge packages and bonuses follow the current configuration.

Live model prices (per 1M tokens)

01 DeepSeek V4.1 Flash 1017 input $0.30 / 1M output $1.20 / 1M
02 Gemini 4 Argon input $2.00 / 1M output $10.00 / 1M
03 Claude Haiku 5.5 input $0.50 / 1M output $2.50 / 1M
04 GPT-6.1 Sol input $4.00 / 1M output $15.00 / 1M
05 Claude Sonnet 5.5 input $3.00 / 1M output $15.00 / 1M
06 GPT-6 Sol input $4.00 / 1M output $15.00 / 1M
07 GPT-6 Luna input $0.20 / 1M output $0.75 / 1M
08 Claude Opus 5.5 input $4.00 / 1M output $20.00 / 1M
09 Grok 4.7 input $4.00 / 1M output $12.00 / 1M
010 GPT-6 Astra input $20.00 / 1M output $75.00 / 1M
011 Gemini 3.8 Flash input $0.75 / 1M output $3.75 / 1M
012 Claude Fable 5.1 input $10.00 / 1M output $50.00 / 1M
013 GLM-5.3 input $1.40 / 1M output $4.40 / 1M
014 DeepSeek V4 Pro input $0.50 / 1M output $2.00 / 1M
015 Qwen3.8 Max input $2.00 / 1M output $6.00 / 1M
016 Kimi K3 input $3.00 / 1M output $15.00 / 1M
017 MiniMax-M3 input $0.60 / 1M output $2.40 / 1M
018 Gemini 3.1 Flash Image input $0.7693 / 1M output $92.3077 / 1M
019 Gemini 3.5 Flash input $0.30 / 1M output $2.50 / 1M
020 GPT-5.5 input $2.50 / 1M output $15.00 / 1M
021 GPT Image 2.5 Flare input $7.6924 / 1M output $46.1539 / 1M

$10.00 in signup credit corresponds to about 50,000,000 input tokens at GPT-6 Luna’s input list price. Input-only estimate; output costs are additional.

Top-up tiers

Free accounts can use chat models only. $10 in cumulative paid top-ups qualifies for Tier 1 and other model categories, subject to live availability. Bonus credits do not raise your tier.

Starter

$10.00 one-time top-up

$10.00 credited after successful payment

Choose tier

Pro

Recommended
$100.00 one-time top-up

+$10.00 bonus

$110.00 credited after successful payment

Choose tier

Enterprise

$500.00 one-time top-up

+$100.00 bonus

$600.00 credited after successful payment

Choose tier

Prepaid credit is deducted for actual calls. Paid top-ups and bonuses are recorded separately.

Before you choose a model.

What is Allgate?
Allgate is a unified AI model gateway with one API key, prepaid credits and usage records. Connect language models or create with currently available image and video models. Check live supply before choosing audio or retrieval capabilities.
Which models can I use?
The public catalogue snapshot dated 2026-10-22 contains 24 model entries, with 24 currently callable. Each detail page shows the model ID, provider, capability, public billing unit and rate. Routing availability can change.
How do I choose between images, video, language and audio?
Use Studio to compare image and video generation models. Use the model catalogue for language models and public prices. The reference library also helps you discover audio, embedding and reranking models; reference inclusion does not promise an available route.

Catalogue snapshot: · Public model data · Models and prices · Image and video Studio · API reference

11 FAQ

Questions before you sign up.

Cannot find an answer? Sign in for the docs, or email us directly.

Models come from official or authorised providers. The gateway includes health checks and retries; routing and failover happen inside the gateway.

Input and output tokens are priced separately at public list prices. Every request traces its token count and cost, and failed retries are not double-billed.

Free accounts can use chat models only. $10 in cumulative paid top-ups qualifies for Tier 1 and other model categories, subject to live availability. Bonus credits do not raise your tier.

Top-up records and company settlement are supported; contact us for enterprise quotes and invoices.

Requests are forwarded only to the model provider you choose; API keys are encrypted at rest, and prompt/response bodies are not retained beyond what the provider requires.

New accounts have baseline rate limits that can be raised on request. Switching models is just a different model parameter — one key and one base_url work across the catalog.

Get started

Bring model capabilities into your project.

Choose a model, configure your project and verify your first API call. Pay for actual usage.

Connect your project Sign in

Pay as you go · Verify a real call in the workbench