Model Registry

100+ models available through the Zima encrypted gateway. Every request end-to-end encrypted in hardware. Provider costs passed through at-rate.

Provider
OpenAI
Anthropic
Google
Meta
Mistral
Cohere
xAI
Capability
Chat
Code
Vision
Reasoning
Embedding
Image Gen
21 models

GPT-4oSecure

Multimodal flagship with vision, code, and advanced reasoning.

Input$2.50
Output$10.00
Context128K

GPT-4o MiniStandard

Fast and affordable multimodal model for lightweight tasks.

Input$0.15
Output$0.60
Context128K

o3Secure

Advanced reasoning model for complex multi-step problems.

Input$10.00
Output$40.00
Context200K

o4-miniBridge

Cost-effective reasoning model balancing speed and depth.

Input$1.10
Output$4.40
Context200K

Claude Opus 4Secure

Most capable Claude model for complex analysis and extended tasks.

Input$15.00
Output$75.00
Context200K

Claude Sonnet 4Bridge

Balanced intelligence and speed for production workloads.

Input$3.00
Output$15.00
Context200K

Claude Haiku 3.5Standard

Fastest Claude for high-throughput, cost-sensitive pipelines.

Input$0.80
Output$4.00
Context200K

Gemini 2.5 ProSecure

Million-token context with native multimodal understanding.

Input$1.25
Output$10.00
Context1M

Gemini 2.5 FlashStandard

Ultra-fast inference with million-token context at minimal cost.

Input$0.15
Output$0.60
Context1M

Gemini 2.0 FlashStandard

Previous-gen Flash model, optimized for speed and throughput.

Input$0.10
Output$0.40
Context1M

Llama 3.3 70BBridge

Open-weight model with strong code and instruction-following.

Input$0.50
Output$0.75
Context128K

Llama 3.1 405BSecure

Largest open-weight model rivaling closed-source flagships.

Input$3.00
Output$9.00
Context128K

Llama 3.1 8BStandard

Lightweight open model for simple tasks and prototyping.

Input$0.05
Output$0.08
Context128K

Mistral LargeSecure

Mistral's most capable model for complex enterprise workloads.

Input$2.00
Output$6.00
Context128K

Mistral SmallStandard

Efficient model for classification, routing, and simple tasks.

Input$0.10
Output$0.30
Context128K

CodestralBridge

Purpose-built for code generation with 256K context window.

Input$0.30
Output$0.90
Context256K

Command R+Secure

Enterprise RAG and tool-use specialist with grounded generation.

Input$2.50
Output$10.00
Context128K

Command RBridge

Balanced model for conversational and retrieval-augmented tasks.

Input$0.15
Output$0.60
Context128K

Embed v4Standard

State-of-the-art embedding model for search and classification.

Input$0.10
Output
Context512

Grok 3Secure

xAI's frontier model with deep reasoning and real-time knowledge.

Input$3.00
Output$15.00
Context128K

Grok 3 MiniStandard

Compact Grok variant for fast, cost-effective inference.

Input$0.30
Output$0.50
Context128K

Provider costs passed through at-rate. Zero markup. Pricing reflects per-million-token rates.