Providers
One gateway, every AI provider
Connect to 9 providers and 50+ models through a single integration. Direct API, cloud gateways, enterprise platforms, and self-hosted — all with unified security and zero vendor lock-in.
9
Providers supported
50+
Models available
4
Credential modes
9 providers, one unified API.
| Provider | Type | Top Models | Status |
|---|---|---|---|
| OpenAI | Direct API | GPT-5.2, GPT-4o, o1 | ✓ healthy |
| Anthropic | Direct API | Opus 4.6, Sonnet 4.5, Haiku 3.5 | ✓ healthy |
| Direct API | Gemini 3 Pro, 3 Flash, 2.5 Pro | ✓ healthy | |
| Mistral | Direct API | Large, Small, Codestral | ✓ healthy |
| DeepSeek | Direct API | Chat, Reasoner | ✓ healthy |
| Vertex AI | Multi-vendor | Gemini + Claude + Mistral + Llama | ✓ healthy |
| Azure AI | Multi-vendor | GPT-4o + Llama + Mistral + DeepSeek | ✓ healthy |
| AWS Bedrock | Cloud | Claude Opus, Sonnet, Haiku | ✓ healthy |
| Ollama | Self-hosted | Llama, Mistral, Qwen, Phi | ✓ healthy |
Flexible authentication for every environment.
BYOK (Bring Your Own Key)
Use your own API keys. Keep your enterprise pricing and negotiated rates.
Platform-Managed
Use Bastio-managed credentials. No API keys to manage or rotate.
Cloud IAM
GCP Service Account, AWS IAM, or Azure AD credentials for enterprise SSO.
Self-Hosted
Connect to local Ollama instances. Zero external API calls, complete data control.
Four ways to connect, from direct API to self-hosted.
| Category | Providers | Description | Models |
|---|---|---|---|
| Direct API | 5 providers | Connect directly with API keys | 50+ models across OpenAI, Anthropic, Google, Mistral, DeepSeek |
| Multi-Vendor | 2 providers | Multiple AI vendors, one credential | Vertex AI (4 vendors) and Azure AI Foundry (5 vendors) |
| Enterprise Cloud | 1 provider | AWS-native governance and compliance | Claude models via AWS Bedrock with IAM integration |
| Self-Hosted | 1 provider | On-premises, air-gapped deployment | Any Ollama-compatible model, zero API costs |
What's included
Every provider, fully integrated
All providers connected through Bastio get automatic security scanning, caching, failover, and observability at no extra configuration.
Switch Providers
Change one line to route through a different provider. Same SDK, same code.
from openai import OpenAI
client = OpenAI(
api_key="sk-your-bastio-key",
base_url="https://api.bastio.com/v1/guard/px_..."
)
response = client.chat.completions.create(
model="gpt-4o", # OpenAI
# model="claude-sonnet-4-5", # Anthropic
# model="gemini-3-pro", # Google
messages=[{"role": "user", "content": "Hello"}],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta.content, end="")Anthropic SDK
Native Anthropic SDK support. Point your base URL at Bastio and use the Claude API natively.
import anthropic
client = anthropic.Anthropic(
api_key="sk-your-bastio-key",
base_url="https://api.bastio.com/v1/guard/px_..."
)
message = client.messages.create(
model="claude-sonnet-4-5",
max_tokens=1024,
messages=[
{"role": "user", "content": "Hello, Claude"}
]
)
print(message.content[0].text)Unified Security Layer
Every provider, every model protected by the same threat detection, PII scanning, and jailbreak prevention.
Bring Your Own Keys
Keep your negotiated enterprise pricing. Store keys encrypted, rotate without code changes.
Zero Lock-in
Switch providers with a config change. Compare performance and cost across vendors in real-time.
Start routing to any AI provider today
9 providers included with every plan. Connect your own API keys or use platform-managed credentials.