Pricing

No hidden fees. Scale as you grow.

One API. 400+ Models.
Access more, spend less.

Free

Getting started

$0

/ mo

Perfect for testing and learning

ANY Tokens:

50K / day

Users:

Unlimited

Core features:

All 400+ models

AnyAPI SDK

AnyCLI

AnyChat

Plan Highlights:

No credit card required

Community support

Limited API calls

Pay-as-you-go

Flexible usage

From

$100

usage-based

Only pay for what you use

ANY Tokens:

500 M+

Users:

Unlimited

Core features:

All 400+ models

AnyAPI SDK

AnyCLI

AnyChat

All features included →

Plan Highlights:

No monthly commitment

Scale as needed

Standard support

Usage-based billing

Developer

Side projects & MVPs

Ideal for small projects and personal apps

$39

/ mo

ANY Tokens:

200 M

Unused tokens roll over monthly

Users:

Unlimited

Core features:

All 400+ models

AnyAPI SDK

AnyCLI

AnyChat

All features included →

Plan Highlights:

Standard support

Shared infrastructure

Basic analytics

Pro

Growing teams & startups

Scales with growing projects and teams

$189

/ mo

ANY Tokens:

1 B

Unused tokens roll over monthly

Users:

Unlimited

Core features:

All 400+ models

AnyAPI SDK

AnyCLI

AnyChat

All features included →

Plan Highlights:

Priority support

Team collaboration

Advanced analytics

99.9% SLA

Most popular

Enterprise

Large teams & production apps

Designed for high-traffic applications

$559

/ mo

ANY Tokens:

3 B

Unused tokens roll over monthly

Users:

Unlimited

Core features:

All 400+ models

AnyAPI SDK

AnyCLI

AnyChat

All features included →

Plan Highlights:

Priority support

Custom integrations

Advanced logging

99.9% SLA

Dedicated instance

* All plans are priced before taxes. Any applicable taxes and local fees will be added based on your country of residence.

Trusted by 2,000+ developers and teams worldwide

Join the growing community building with AnyAPI

Custom

Volume discount

ANY Solution

Tailored for your unique needs. Get custom pricing, dedicated support, and enterprise-grade features built specifically for your business.

Turnkey AI Infrastructure

We design, deploy, and operate your AI stack — ready for production from day one.

Retrieval-Augmented Generation (RAG)

Ground AI responses in your proprietary data for higher accuracy and trust.

Model Context Protocol (MCP)

Advanced context handling for seamless, multi-model integrations.

Private Cloud Deployment

Fully isolated AI environment deployed in your private cloud or on-prem.

Available on all paid plans

Everything you need to ship AI

One powerful toolkit that handles everything.

Core Platform

Unified API

One interface for every model

Web Search

Real-time web access for models

Prompt Caching

Cut cost and latency

Auto Routing

Smart model selection

Fallbacks

Automatically failover handling

Request Prioritization

Critical requests jump the queue during high load.

Load Balancing

Distribute traffic across regions (EU/US/ASIA) and zones with queueing, cooldowns, timeouts, and retries.

Developer Tools

Python SDK

Clean, typed client with sensible defaults.

Streaming

Token-by-token output for snappy chat UIs.

Function Calling

Let models call your tools; supports vision, voice, PDF input, and reasoning modes (where available).

Predicted Outputs

Provide an expected answer to slash latency for small rewrites/refactors.

Prompt Formatting

Write prompts once (OpenAI style); we auto-translate to each model’s format. Override with custom templates when needed.

Parallel Functions

Run multiple tool calls at the same time and merge results.

Batching

• Many → 1 model (bulk requests)
• 1 → many models, return fastest
• 1 → many models, return all

Mock Responses

Fake LLM outputs in tests to save money and speed up CI.

Reliability Controls

Built-in retries and context-aware fallbacks to keep flows running.

Advanced AI

Finetuned Models

Use domain-specific versions for legal docs, blockchain analysis, company-specific support, or opinionated codegen.

Computer Use

Let models operate a desktop: screenshot, click, type, scroll—end-to-end task execution.

Vision Input

Let models operate a desktop: screenshot, click, type, scroll—end-to-end task execution.

PDF Processing

Let models operate a desktop: screenshot, click, type, scroll—end-to-end task execution.

Reasoning Modes

Let models operate a desktop: screenshot, click, type, scroll—end-to-end task execution.

Enterprise Ready

RAG

Connect vector stores for private data

Custom SLA

Up to 99.99% uptime guarantee

Dedicated Support

Personal account manager

Priority Access

New features and models first

Security & Compliance

Your data is protected with enterprise-grade security. SOC 2 Type I/II & ISO 27001 ready, encryption in transit, and audit-friendly logs.

AICPA

SOC 2

ISO

27001

GDPR

Integrations Coming Soon

We're building native integrations with your favorite tools. LangChain, Vercel AI SDK, and more are on the way.

API Credits Pricing

From API credits to model performance and integration steps, here are the answers developers and startups ask most.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Model

cost in ₳nyToken, input/output

01.AI: Yi Large Turbo

-

-

Alibaba: Tongyi DeepResearch 30B A3B

-

-

Alibaba: Tongyi DeepResearch 30B A3B (free)

-

-

Amazon: Nova Micro 1.0

-

-

Amazon: Nova Premier 1.0

-

-

Anthropic: Claude 3 Haiku

-

-

Anthropic: Claude 3 Opus

-

-

Anthropic: Claude 3 Sonnet

-

-

Anthropic: Claude 3.5 Haiku (2024-10-22)

-

-

Anthropic: Claude 3.5 Sonnet

-

-

Anthropic: Claude 3.5 Sonnet (2024-06-20)

-

-

Anthropic: Claude 3.7 Sonnet

-

-

Anthropic: Claude 3.7 Sonnet (thinking)

-

-

Anthropic: Claude 4 Opus

-

-

Anthropic: Claude 4 Sonnet

-

-

Anthropic: Claude Haiku 3.5

-

-

Anthropic: Claude Haiku 4.5

-

-

Anthropic: Claude Instant v1.1

-

-

Anthropic: Claude Opus 4.1

-

-

Anthropic: Claude Opus 4.5

-

-

Anthropic: Claude Opus 4.6

-

-

Anthropic: Claude Sonnet 4.5

-

-

Anthropic: Claude v2

-

-

Anthropic: Claude v2.0

-

-

Anthtopic: Claude v2.1

-

-

Arcee AI: AFM 4.5B

-

-

Arcee AI: Coder Large

-

-

Arcee AI: Maestro Reasoning

-

-

Arcee AI: Spotlight

-

-

Arcee AI: Virtuoso Large

-

-

Baidu: ERNIE 4.5 21B A3B

-

-

Baidu: ERNIE 4.5 21B A3B Thinking

-

-

Baidu: ERNIE 4.5 VL 28B A3B

-

-

ByteDance: UI-TARS 7B

-

-

CognitiveComputations: Dolphin 2.6 Mixtral 8x7B

-

-

Cohere: Command

-

-

Cohere: Command R

-

-

Cohere: Command R+

-

-

Cohere: Command R7B (12-2024)

-

-

Databricks: DBRX 132B Instruct

-

-

Deep Cogito: Cogito V2 Preview Llama 405B

-

-

DeepSeek: DeepSeek Prover V2

-

-

DeepSeek: DeepSeek R1

-

-

DeepSeek: DeepSeek R1 0528

-

-

DeepSeek: DeepSeek R1 0528 (free)

-

-

DeepSeek: DeepSeek V3

-

-

DeepSeek: DeepSeek V3.1

-

-

DeepSeek: DeepSeek V3.1 Base

-

-

DeepSeek: DeepSeek V3.1 Terminus

-

-

DeepSeek: DeepSeek V3.1 Terminus (exacto)

-

-

DeepSeek: DeepSeek V3.2

-

-

DeepSeek: DeepSeek V3.2 Exp

-

-

DeepSeek: Deepseek R1 0528 Qwen3 8B

-

-

DeepSeek: Deepseek R1 0528 Qwen3 8B (free)

-

-

Fireworks: FireLLaVA 13B

-

-

GPT-5.1-Codex-Max

-

-

Google: Gemini 1.5 Flash

-

-

Google: Gemini 1.5 Flash 8B

-

-

Google: Gemini 1.5 Flash Experimental

-

-

Google: Gemini 1.5 Pro

-

-

Google: Gemini 1.5 Pro Experimental

-

-

Google: Gemini 2.0 Flash

-

-

Google: Gemini 2.0 Flash Lite

-

-

Google: Gemini 2.5 Flash

-

-

Google: Gemini 2.5 Flash Image (Nano Banana)

-

-

Google: Gemini 2.5 Flash Image Preview

-

-

Google: Gemini 2.5 Flash Image Preview (free)

-

-

Google: Gemini 2.5 Flash Lite

-

-

Google: Gemini 2.5 Flash Lite Preview 06-17

-

-

Google: Gemini 2.5 Flash Lite Preview 09-2025

-

-

Google: Gemini 2.5 Flash Preview 05-20

-

-

Google: Gemini 2.5 Flash Preview 09-2025

-

-

Google: Gemini 2.5 Pro

-

-

Google: Gemini 2.5 Pro Experimental

-

-

Google: Gemini 2.5 Pro Preview 05-06

-

-

Google: Gemini 3 Pro Preview

-

-

Google: Gemma 2 27B

-

-

Google: Gemma 2 9B (free)

-

-

Google: Gemma 3 12B

-

-

Google: Gemma 3 12B (free)

-

-

Google: Gemma 3 27B

-

-

Google: Gemma 3 27B (free)

-

-

Google: Gemma 3n 2B (free)

-

-

Google: Gemma 3n 4B

-

-

Google: Gemma 3n 4B (free)

-

-

Google: PaLM 2 Chat

-

-

Google: PaLM 2 Code Chat

-

-

Google: PaLM 2 Code Chat 32k

-

-

IBM: Granite 4.0 Micro

-

-

LiquidAI: LFM2-2.6B

-

-

LiquidAI: LFM2-8B-A1B

-

-

Meituan: LongCat Flash Chat

-

-

Meituan: LongCat Flash Chat (free)

-

-

Meta: Llama 3 8B Instruct

-

-

Meta: Llama 3.1 405B Instruct

-

-

Meta: Llama 3.3 70B Instruct

-

-

Microsoft: Phi 4 Reasoning Plus

-

-

MiniMax: MiniMax M1

-

-

Mistral: Codestral 2508

-

-

Mistral: Devstral Medium

-

-

Frequently
Asked
Questions

From API credits to model performance and integration steps, here are the answers developers and startups ask most.

What is a credit?

A credit is our universal currency for API usage across all 400+ models. Think of it as a unified token that abstracts away the complexity of different pricing models. One credit equals roughly 1,000 tokens for most models, but premium models like GPT-4 or Claude 3 Opus consume more credits per token due to their computational costs.

Does using the Playground count against my credits?

Yes, Playground usage consumes credits just like API calls—we believe in transparent pricing with no hidden costs. However, Free plan users get unlimited access to free-tier models in the Playground, so you can experiment without worry.

Which AI model should I use?

It depends on your use case! For simple tasks like classification or summarization, cost-effective models like GPT-3.5 or Claude Instant work great. For complex reasoning, coding, or creative tasks, go with GPT-4, Claude 3 Opus, or Gemini Ultra. Our intelligent routing feature can automatically select the best model for each request based on cost and quality.

How to manage my subscription?

\Head to your Dashboard → Settings → Billing to view your current plan, usage history, and payment methods. You can upgrade, downgrade, or cancel anytime. Changes take effect at your next billing cycle, and we'll prorate any differences.

Can I integrate my own model or API key?

Absolutely! Enterprise and Custom plans support bring-your-own-key (BYOK) for major providers. You can also request custom model integrations—we've added models within 48 hours for enterprise clients. Contact our team to discuss your specific requirements.

How do I upgrade or downgrade my plan?

You can switch plans anytime from your dashboard. Upgrades take effect immediately with prorated charges. Downgrades apply at your next billing cycle, and unused credits from higher tiers roll over for up to 30 days.

What happens if I exceed my credit limit?

We've got you covered. You'll receive alerts at 75% and 90% usage. When you hit your limit, Pay-as-you-go customers are charged automatically for overages. Plan subscribers can enable auto-top-up or upgrade their plan. Your API calls won't be interrupted.

Do you offer refunds?

We offer a 14-day money-back guarantee for first-time subscribers. If you're not satisfied, contact support for a full refund—no questions asked. After that, we don't offer refunds but you can downgrade or cancel anytime.

Start Building with AnyAPI Today

Access top language models like Claude 4, GPT-4 Turbo, Gemini, and Mistral – no setup delays.

Get your API key