CONCENTRATE
PricingDocs
CONCENTRATE

One API for every major LLM provider — routing, spend, logs, and controls in one place.

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

LLM Gateway
  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls
Features
  • Universal API Keys
  • BYOK
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs
  • Centralized Billing
  • Volume-Based Pricing
Teams
  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance
Integrations
  • All Integrations
  • Migration Guides
Platform
  • Pricing
  • ROI Calculator
  • Model Fortress
  • Enterprise
  • Documentation
  • Status
Legal
  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy
  • Trust Center

LLM Gateway

  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls

Features

  • Universal API Keys
  • BYOK
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs
  • Centralized Billing
  • Volume-Based Pricing

Teams

  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance

Integrations

  • All Integrations
  • Migration Guides

Platform

  • Pricing
  • ROI Calculator
  • Model Fortress
  • Enterprise
  • Documentation
  • Status

Legal

  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy
  • Trust Center

Offices

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

AICPA SOC for Service OrganizationsSOC 2 Type II

© 2026 Concentrate AI. All rights reserved.

CONCENTRATE
Blog
Request a DemoLog In
Log In
CONCENTRATE

One API for every major LLM provider — routing, spend, logs, and controls in one place.

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

LLM Gateway
  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls
Features
  • Universal API Keys
  • BYOK
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs
  • Centralized Billing
  • Volume-Based Pricing
Teams
  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance
Integrations
  • All Integrations
  • Migration Guides
Platform
  • Pricing
  • ROI Calculator
  • Blog
  • Model Fortress
  • Enterprise
  • Documentation
  • Status
Legal
  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy
  • Trust Center

LLM Gateway

  • LLM Gateway
  • Request Routing
  • Usage Monitoring
  • Spend Management
  • Data Security
  • Access Controls

Features

  • Universal API Keys
  • BYOK
  • Spend Tracking
  • Token Allocation
  • Usage Analytics
  • Request Logs
  • Alerts
  • Data Redaction
  • Zero Data Retention
  • Audit Logs
  • Centralized Billing
  • Volume-Based Pricing

Teams

  • AI Engineering
  • Engineering Leadership
  • Finance & Operations
  • Security & Compliance

Integrations

  • All Integrations
  • Migration Guides

Platform

  • Pricing
  • ROI Calculator
  • Blog
  • Model Fortress
  • Enterprise
  • Documentation
  • Status

Legal

  • Privacy Policy
  • Terms of Service
  • Data Processing Addendum
  • Acceptable Use Policy
  • Trust Center

Offices

New York

130 E 59th St, 17th floor

New York, NY 10022

Wilmington

1201 N. Market Street, Suite 200

Wilmington, DE 19801

AICPA SOC for Service OrganizationsSOC 2 Type II

© 2026 Concentrate AI. All rights reserved.

Model Fortress

ModelsProviders

Compare pricing, context windows, and capabilities across every major LLM provider

Filters

71 of 207

PHI requires a signed BAA from Concentrate and HIPAA-enabled organization.

ModelProvidersInput$/MOutput$/MContextMax OutputCapabilities
OpenAI
GPT-6.1 Terra
$1.00$5.001.1M128K
Baseten
Elephant 1
$0.04$0.0016K16K
Baseten
Mammoth 1
$0.10$0.0016K16K
DeepSeek
DeepSeek V4.1 Flash 1017
$0.30$1.201.0M262K
DeepSeek
DeepSeek V4.1 Flash 1017 Fast
$0.60$2.401.0M262K
Reflection
Beam 1.0
$0.40$1.201.0M131K
Meta
Muse Spark Open
$1.25$4.251.0M131K
Google
Gemini 4 Argon
$2.00$10.001.0M66K
Anthropic
Claude Haiku 5.5
$0.10$0.501.0M128K
OpenAI
GPT-6.1 Sol
$2.00$10.001.1M128K
Anthropic
Claude Sonnet 5.5
$2.00$10.001.0M128K
Anthropic
Claude Opus 5.5
$4.00$20.001.0M128K
OpenAI
GPT-6 Sol
$2.00$10.001.1M128K
OpenAI
GPT-6 Luna
$0.10$0.501.1M128K
xAI
Grok 4.7
$2.00$6.00524K125K
DeepSeek
DeepSeek V4.1 Flash
+1$0.30$1.201.0M131K
OpenAI
GPT-6 Astra
$10.00$50.001.1M128K
Google
Gemini 3.8 Flash
$0.75$3.751.0M66K
Anthropic
Claude Fable 5.1
$10.00$50.001.0M128K
z.ai
GLM-5.3-Flash
$0.15$0.501.0M262K
z.ai
GLM-5.3
$1.40$4.401.0M262K
Google
Gemini 3.7 Flash
$0.75$3.751.0M66K
xAI
Grok 4.6
$2.00$6.00200K128K
NVIDIA
Nemotron Lightning 3.5 30B A3B
$0.05$0.20262K66K
Alibaba Cloud
Qwen3.8 Max
$2.00$6.00262K66K
Anthropic
Claude Opus 5
$5.00$25.001.0M128K
Google
Gemini 3.6 Flash
$0.75$3.751.0M66K
Google
Gemini 3.5 Flash Lite
$0.30$2.501.0M66K
Moonshot AI
Kimi K3
$3.00$15.001.0M262K
OpenAI
GPT 5.6 Sol
$4.00$20.001.1M128K
OpenAI
GPT 5.6 Terra
$2.00$12.001.1M128K
OpenAI
GPT 5.6 Luna
$0.20$1.201.1M128K
Anthropic
Claude Sonnet 5
$2.00$10.001.0M128K
z.ai
GLM-5.2
$1.40$4.401.0M262K
Anthropic
Claude Fable 5
$10.00$50.001.0M128K
NVIDIA
Nemotron 3 Ultra NVFP4
$0.60$2.40262K66K
MiniMax
MiniMax M3
$0.30$1.20512K128K
Anthropic
Claude Opus 4.8
$5.00$25.001.0M128K
Google
Gemini 3.5 Flash
$1.50$9.001.0M66K
OpenAI
GPT 5.5
$5.00$30.001.1M128K
Moonshot AI
Kimi K2.6
$0.95$4.00262K66K
xAI
Grok 4.3
$1.25$2.50200K8K
Anthropic
Claude Opus 4.7
$5.00$25.001.0M128K
OpenAI
GPT 5.4 Mini
$0.75$4.50400K128K
OpenAI
GPT 5.4 Nano
$0.20$1.25400K128K
OpenAI
GPT 5.4 Pro
$30.00$180.001.1M128K
OpenAI
GPT 5.4
$2.50$15.001.1M128K
Google
Gemini 3.1 Pro Preview
$2.00$12.001.0M66K
Anthropic
Claude Sonnet 4.6
$3.00$15.001.0M128K
Anthropic
Claude Opus 4.6
$5.00$25.001.0M128K
OpenAI
GPT 5.3 Codex
$1.75$14.00400K128K
Moonshot AI
Kimi K2.5
$0.60$3.00262K66K
Google
Gemini 3 Flash Preview
$0.50$3.001.0M66K
OpenAI
GPT 5.2
$1.75$14.00400K128K
DeepSeek
DeepSeek V3.2
$0.58$1.68128K32K
Anthropic
Claude Opus 4.5
$5.00$25.00200K64K
OpenAI
GPT 5.1
$1.25$10.00400K128K
Anthropic
Claude Haiku 4.5
$1.00$5.00200K64K
Anthropic
Claude Sonnet 4.5
$3.00$15.00200K64K
OpenAI
GPT 5
$1.25$10.00400K128K
OpenAI
GPT 5 Mini
$0.25$2.00400K128K
OpenAI
GPT 5 Nano
$0.05$0.40400K128K
OpenAI
OpenAI gpt-oss 120B
$0.15$0.60131K33K
Google
Gemini 2.5 Flash Lite
$0.10$0.401.0M66K
Google
Gemini 2.5 Pro
$1.25$10.001.0M66K
Google
Gemini 2.5 Flash
$0.30$2.501.0M66K
OpenAI
OpenAI o3
$2.00$8.00200K100K
OpenAI
GPT 4.1
$2.00$8.001.0M33K
OpenAI
GPT 4.1 Mini
$0.40$1.601.0M33K
OpenAI
GPT 4o Mini
$0.15$0.60128K16K
OpenAI
GPT 4o
$2.50$10.00128K16K

Access all models through one API

Stop juggling multiple provider SDKs. Concentrate gives you a single endpoint for every model listed above, with built-in guardrails, analytics, and spend management.

Get Started Free

Frequently Asked Questions

What is the Concentrate.ai Model Fortress?

The Concentrate.ai Model Fortress is a live catalog of every LLM accessible through the Concentrate.ai API. It shows provider-specific pricing (input and output cost per million tokens), context window sizes, and capabilities like function calling, vision, streaming, and JSON mode for each model across every available provider.

How often is the Model Fortress updated?

The Model Fortress pulls live data from the Concentrate.ai model catalog API and revalidates every hour. Pricing and availability reflect the current state of each provider.

Which AI providers are included?

The Model Fortress includes models from OpenAI, Anthropic, Google, Meta (Llama), DeepSeek, Mistral, Cohere, xAI, and many more. Each model shows all providers that offer it, so you can compare the same model across different providers and pick the cheapest or best-fit option.