Zyora Labs
Z-AI / Models

Models & providers

Every model the gateway can route to today. To unlock a provider's models, paste its key in Providers — Z-AI uses BYOK and pays your provider directly, with no markup.

Pricing

Z-AI charges no markup on tokens. You pay your provider directly via your BYOK key. The gateway tracks tokens/cost per call so you can see exactly what every request costs, broken down by model, in real time.

See spend per key in Keys and per-call breakdown in Logs.

OpenAI · 8 models

GPT-5 family + still-supported GPT-4o and o1.

Get key
openai/gpt-5.5
openai/gpt-5.4
openai/gpt-5.4-minidefault
openai/gpt-5.4-nano
openai/gpt-4o
openai/gpt-4o-mini
openai/o1-preview
openai/o1-mini
Anthropic · 7 models

Claude 4 generation plus legacy 3.5 snapshots.

Get key
anthropic/claude-opus-4-8
anthropic/claude-sonnet-4-6
anthropic/claude-haiku-4-5
anthropic/claude-haiku-4-5-20251001pinned
anthropic/claude-3-5-sonnet-20241022
anthropic/claude-3-5-haiku-20241022
anthropic/claude-3-opus-20240229
Google Gemini · 7 models

Gemini 3.x frontier + 2.5 stable line.

Get key
gemini/gemini-3.1-pro
gemini/gemini-3.5-flash
gemini/gemini-3-flash
gemini/gemini-3.1-flash-lite
gemini/gemini-2.5-pro
gemini/gemini-2.5-flash
gemini/gemini-2.5-flash-lite
Groq · 7 models

LPU inference — extreme tokens/sec, low latency.

Get key
groq/llama-3.3-70b-versatile
groq/llama-3.1-8b-instant
groq/openai/gpt-oss-120b
groq/openai/gpt-oss-20b
groq/meta-llama/llama-4-scout-17b-16e-instruct
groq/qwen/qwen3-32b
groq/moonshotai/kimi-k2-instruct-0905
Mistral · 8 models

Open-weights leader. Codestral / Devstral for code.

Get key
mistral/mistral-medium-latest
mistral/mistral-small-latest
mistral/mistral-large-latest
mistral/magistral-medium-latest
mistral/ministral-8b-latest
mistral/ministral-3b-latest
mistral/codestral-latest
mistral/devstral-medium-latest
Together AI · 11 models

DeepSeek, Kimi, MiniMax, Qwen — frontier OSS at scale.

Get key
together/deepseek-ai/DeepSeek-V4-Pro
together/moonshotai/Kimi-K2.6
together/MiniMaxAI/MiniMax-M2.7
together/zai-org/GLM-5.1
together/Qwen/Qwen3.6-Plus
together/Qwen/Qwen3.5-397B-A17B
together/Qwen/Qwen3-235B-A22B-Instruct-2507-tput
together/openai/gpt-oss-120b
together/openai/gpt-oss-20b
together/meta-llama/Llama-3.3-70B-Instruct-Turbo
together/deepcogito/cogito-v2-1-671b
Fireworks AI · 11 models

Same OSS frontier, separate serverless backend.

Get key
fireworks/accounts/fireworks/models/deepseek-v4-pro
fireworks/accounts/fireworks/models/deepseek-v4-flash
fireworks/accounts/fireworks/models/kimi-k2p6
fireworks/accounts/fireworks/models/minimax-m2p7
fireworks/accounts/fireworks/models/glm-5p1
fireworks/accounts/fireworks/models/qwen3p6-plus
fireworks/accounts/fireworks/models/gpt-oss-120b
fireworks/accounts/fireworks/models/gpt-oss-20b
fireworks/accounts/fireworks/models/llama-v3p3-70b-instruct
fireworks/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507
fireworks/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct
Nexula AIBOM · 1 model

Zyora AI Labs' in-house security model (AIBOM-8B). India-first.

Get key
nexula/aibom-8b
Custom / self-hosted endpoints

Any OpenAI-compatible endpoint (vLLM, Ollama, llama.cpp, LM Studio, sglang, Modal endpoints) works as a custom provider — paste the base_url in Providers and Z-AI will route to it.