---
title: "Posts by \"AISIX\" - API7.ai"
description: "Latest blog from API7.ai on \"AISIX\""
url: "https://api7.ai/tags/aisix"
---

# All posts tagged

## "AISIX"

[![AISIX 1.10.0: Keep AI Coding Sessions on a Matched Semantic Route](https://static.api7.ai/uploads/2026/11/13/5rPD4mvs_aisix-1-10-0-semantic-routing-session-affinity.webp)](https://api7.ai/blog/aisix-1-10-0-semantic-routing-session-affinity)

Products

November 12, 2026

#### [AISIX 1.10.0: Keep AI Coding Sessions on a Matched Semantic Route](https://api7.ai/blog/aisix-1-10-0-semantic-routing-session-affinity)

AISIX 1.10.0 brings semantic routing to Messages and Responses APIs, model-group targets, and optional session affinity for supported AI coding and agent sessions.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[Semantic Routing](https://api7.ai/tags/semantic-routing)

[![AI Gateway Configuration Changes: Validate, Reload, Verify, and Roll Back](https://static.api7.ai/uploads/2026/11/09/dGL3lHkE_ai-gateway-configuration-change-runbook-v2.webp)](https://api7.ai/blog/ai-gateway-configuration-change-runbook)

Technology

November 9, 2026

#### [AI Gateway Configuration Changes: Validate, Reload, Verify, and Roll Back](https://api7.ai/blog/ai-gateway-configuration-change-runbook)

Use a four-gate runbook to validate an AI gateway configuration, apply it safely, prove the effective state, and roll back without confusing readiness with freshness.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Platform Engineering](https://api7.ai/tags/platform-engineering)

[![Kong vs LiteLLM vs AISIX: Choosing a Self-Hosted AI Gateway](https://static.api7.ai/uploads/2026/11/09/WGLNy0sV_self-hosted-ai-gateway-cover.png)](https://api7.ai/blog/self-hosted-ai-gateway-kong-litellm-aisix)

Technology

November 9, 2026

#### [Kong vs LiteLLM vs AISIX: Choosing a Self-Hosted AI Gateway](https://api7.ai/blog/self-hosted-ai-gateway-kong-litellm-aisix)

Compare Kong, LiteLLM and AISIX for self-hosted AI gateways: deployment dependencies, licensing, shared quotas and the path to centralized management.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[LiteLLM](https://api7.ai/tags/litellm)

[![AISIX 1.9.0: Connect MCP Users with Their Own Upstream Authorization](https://static.api7.ai/uploads/2026/11/12/HBiZRdR1_aisix-1-9-0-per-user-mcp-oauth.webp)](https://api7.ai/blog/aisix-1-9-0-per-user-mcp-oauth)

Products

November 6, 2026

#### [AISIX 1.9.0: Connect MCP Users with Their Own Upstream Authorization](https://api7.ai/blog/aisix-1-9-0-per-user-mcp-oauth)

AISIX 1.9.0 adds per-user upstream MCP OAuth, allowing users to authorize an upstream service from their MCP client while AISIX manages the upstream credentials.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[MCP](https://api7.ai/tags/mcp)

[![Kong AI Gateway vs AISIX: Which Gateway Fits When Teams Share AI Models?](https://static.api7.ai/uploads/2026/11/09/ue5pqd2T_kong-ai-gateway-vs-aisix-v2.png)](https://api7.ai/blog/kong-ai-gateway-vs-aisix)

Technology

November 6, 2026

#### [Kong AI Gateway vs AISIX: Which Gateway Fits When Teams Share AI Models?](https://api7.ai/blog/kong-ai-gateway-vs-aisix)

Compare Kong AI Gateway and AISIX for shared LLM access: open-source options, licensing, self-hosted deployment, failover, rate limits, and cost controls.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Kong AI Gateway](https://api7.ai/tags/kong-ai-gateway)

[![Migrating from LiteLLM to AISIX: Keep Model Profiles, Add Gateway Orchestration](https://static.api7.ai/uploads/2026/11/03/w1ZDPFFD_litellm-migration.png)](https://api7.ai/blog/litellm-migration-aliases-inference-parameters)

Technology

November 5, 2026

#### [Migrating from LiteLLM to AISIX: Keep Model Profiles, Add Gateway Orchestration](https://api7.ai/blog/litellm-migration-aliases-inference-parameters)

Move LiteLLM profiles to AISIX, centralize model-specific request rules, and add gateway-owned orchestration using tested configuration examples.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[LiteLLM](https://api7.ai/tags/litellm)

[![LiteLLM vs AISIX: Choosing an AI Gateway for Production](https://static.api7.ai/uploads/2026/11/05/FKwg8x8B_litellm-vs-aisix-production.png)](https://api7.ai/blog/litellm-vs-aisix-production-ai-gateway)

Technology

November 5, 2026

#### [LiteLLM vs AISIX: Choosing an AI Gateway for Production](https://api7.ai/blog/litellm-vs-aisix-production-ai-gateway)

Compare LiteLLM and AISIX through five production questions: compatibility, failover, costs, security, and operations, with clear open-source and commercial boundaries.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[LiteLLM](https://api7.ai/tags/litellm)

[![Decision Models Through an AI Gateway: Test the API Contract](https://static.api7.ai/uploads/2026/10/27/Nt041Da0_decision-making-cover.webp)](https://api7.ai/blog/decision-model-api-contract-testing)

Technology

October 27, 2026

#### [Decision Models Through an AI Gateway: Test the API Contract](https://api7.ai/blog/decision-model-api-contract-testing)

Validate AISIX decision-model requests, answer ordering, refusals, token usage, and failure paths with a runnable application-side contract checker.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[API Testing](https://api7.ai/tags/api-testing)

[![AISIX 1.7.0: Turn AI Spend Into an Operating Boundary](https://static.api7.ai/uploads/2026/10/26/qZ0mRtyd_aisix-1-7-0-cost-attribution-tags.webp)](https://api7.ai/blog/aisix-1-7-0-cost-attribution-tags)

Products

October 22, 2026

#### [AISIX 1.7.0: Turn AI Spend Into an Operating Boundary](https://api7.ai/blog/aisix-1-7-0-cost-attribution-tags)

AISIX 1.7.0 adds inherited cost-attribution tags so teams can connect AI usage, budgets, and rate-limit policy to the organization that owns the work.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[Cost Governance](https://api7.ai/tags/cost-governance)

[![Codex Proxy: Route OpenAI Codex Through AISIX](https://static.api7.ai/uploads/2026/10/13/9A4TPjrT_codex-proxy-aisix.webp)](https://api7.ai/blog/codex-proxy-aisix)

Technology

October 13, 2026

#### [Codex Proxy: Route OpenAI Codex Through AISIX](https://api7.ai/blog/codex-proxy-aisix)

Route Codex through AISIX with scoped credentials and a tested Responses contract, while preserving tools, streaming, continuation, and useful errors.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[OpenAI Codex](https://api7.ai/tags/openai-codex)

[![LLM Monitoring with Prometheus: SLOs for AI Traffic](https://static.api7.ai/uploads/2026/10/13/vJoXpfa4_llm-monitoring-prometheus.webp)](https://api7.ai/blog/llm-monitoring-prometheus)

Technology

October 13, 2026

#### [LLM Monitoring with Prometheus: SLOs for AI Traffic](https://api7.ai/blog/llm-monitoring-prometheus)

Build LLM monitoring with Prometheus using terminal request outcomes, streaming latency, TTFT, fallback, and policy signals from AISIX 1.6.0.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Prometheus](https://api7.ai/tags/prometheus)

[![AISIX 1.6.0: Make Streaming SLOs Reflect the Outcome](https://static.api7.ai/uploads/2026/10/15/JvxAcYMU_aisix-1-6-0-stream-metrics-terminal-outcomes.webp)](https://api7.ai/blog/aisix-1-6-0-stream-metrics-terminal-outcomes)

Products

October 12, 2026

#### [AISIX 1.6.0: Make Streaming SLOs Reflect the Outcome](https://api7.ai/blog/aisix-1-6-0-stream-metrics-terminal-outcomes)

AISIX 1.6.0 records supported streamed requests when they end, so request metrics and duration histograms reflect terminal outcomes instead of response start.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[Observability](https://api7.ai/tags/observability)

[![Claude Code Gateway: Govern Coding Agent Traffic](https://static.api7.ai/uploads/2026/10/08/QMnsXVp6_claude-code-gateway.webp)](https://api7.ai/blog/claude-code-gateway)

Technology

October 8, 2026

#### [Claude Code Gateway: Govern Coding Agent Traffic](https://api7.ai/blog/claude-code-gateway)

Route Claude Code through AISIX with scoped caller keys, stable model aliases, limits, guardrails, and usage visibility.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Claude Code](https://api7.ai/tags/claude-code)

[![MCP Security Best Practices: Auth, Tool Access, and Egress](https://static.api7.ai/uploads/2026/10/08/Nd9pj31A_mcp-security-best-practices.webp)](https://api7.ai/blog/mcp-security-best-practices)

Technology

October 8, 2026

#### [MCP Security Best Practices: Auth, Tool Access, and Egress](https://api7.ai/blog/mcp-security-best-practices)

Secure MCP with resource-bound authentication, least-privilege tools, separate credentials, correctly timed guardrails, and egress controls.

[MCP](https://api7.ai/tags/mcp)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[![AI Gateway High Availability: Survive Control-Plane Outages](https://static.api7.ai/uploads/2026/09/29/1wugfBAj_ai-gateway-high-availability.webp)](https://api7.ai/blog/ai-gateway-high-availability)

Technology

September 29, 2026

#### [AI Gateway High Availability: Survive Control-Plane Outages](https://api7.ai/blog/ai-gateway-high-availability)

Design an AI gateway that safely serves accepted policy through control-plane outages, restarts, stale state, shared-service failures, and recovery drills.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[High Availability](https://api7.ai/tags/high-availability)

[![Model Deprecation Runbook: Migrate LLMs Without Breaking Apps](https://static.api7.ai/uploads/2026/11/09/2XrZ1o3X_model-deprecation-runbook.webp)](https://api7.ai/blog/ai-model-gateway-migration)

Technology

September 29, 2026

#### [Model Deprecation Runbook: Migrate LLMs Without Breaking Apps](https://api7.ai/blog/ai-model-gateway-migration)

Turn a provider model retirement into an owned migration: inventory callers, test a pinned replacement, canary a stable alias, prove zero old traffic, and preserve rollback.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[LLM Gateway](https://api7.ai/tags/llm-gateway)

[AISIX](https://api7.ai/tags/aisix)

[![AISIX 1.5.0: Run Non-Chat AI Workloads Through Model Groups](https://static.api7.ai/uploads/2026/09/30/10SkWMYQ_aisix-1-5-0-model-groups-beyond-chat.webp)](https://api7.ai/blog/aisix-1-5-0-model-groups-beyond-chat)

Products

September 29, 2026

#### [AISIX 1.5.0: Run Non-Chat AI Workloads Through Model Groups](https://api7.ai/blog/aisix-1-5-0-model-groups-beyond-chat)

AISIX 1.5.0 extends Model Group routing, retry, failover, balancing, and per-attempt usage records to supported single-request AI endpoints.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[Reliability](https://api7.ai/tags/reliability)

[![AI Gateway for Dify, n8n, and Open WebUI](https://static.api7.ai/uploads/2026/09/22/qD4mad1A_ai-gateway-ai-application-platforms.webp)](https://api7.ai/blog/ai-gateway-ai-application-platforms)

Technology

September 22, 2026

#### [AI Gateway for Dify, n8n, and Open WebUI](https://api7.ai/blog/ai-gateway-ai-application-platforms)

Connect Dify, n8n, and Open WebUI to AISIX with stable model aliases, protected provider keys, policy, usage attribution, and workload tests.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Dify](https://api7.ai/tags/dify)

[![AISIX 1.4.0: Redis Startup Resilience and Bounded Usage Retry](https://static.api7.ai/uploads/2026/09/24/ghrWGIkp_aisix-1-4-0-keep-serving-through-outages.webp)](https://api7.ai/blog/aisix-1-4-0-redis-startup-usage-retry)

Products

September 22, 2026

#### [AISIX 1.4.0: Redis Startup Resilience and Bounded Usage Retry](https://api7.ai/blog/aisix-1-4-0-redis-startup-usage-retry)

AISIX 1.4.0 can serve in degraded mode when Redis is unavailable at startup and can retry usage delivery within strict limits when deduplication evidence permits.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[Reliability](https://api7.ai/tags/reliability)

[![OpenAI-Compatible AI Gateway: Test the Contract](https://static.api7.ai/uploads/2026/09/22/Dnx7BccM_openai-compatible-ai-gateway.webp)](https://api7.ai/blog/openai-compatible-ai-gateway)

Technology

September 22, 2026

#### [OpenAI-Compatible AI Gateway: Test the Contract](https://api7.ai/blog/openai-compatible-ai-gateway)

Test an OpenAI-compatible AI gateway across auth, model discovery, streaming, tool calls, errors, usage, and provider translation.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[LLM Gateway](https://api7.ai/tags/llm-gateway)

[AISIX](https://api7.ai/tags/aisix)

[![AISIX 1.3.0: Run Structured AI Agent Workflows Across Providers](https://static.api7.ai/uploads/2026/09/18/MUYaGH2i_aisix-1-3-0-structured-agent-workflows.webp)](https://api7.ai/blog/aisix-1-3-0-structured-agent-workflows)

Products

September 18, 2026

#### [AISIX 1.3.0: Run Structured AI Agent Workflows Across Providers](https://api7.ai/blog/aisix-1-3-0-structured-agent-workflows)

AISIX 1.3.0 expands structured output and Responses translation, with explicit guardrail boundaries and clearer records of completed agent requests.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AI Agents](https://api7.ai/tags/ai-agents)

[![Private LLM Gateway: Secure vLLM, SGLang, and Ollama](https://static.api7.ai/uploads/2026/09/15/4CMHboqS_private-llm-gateway.webp)](https://api7.ai/blog/private-llm-gateway)

Technology

September 15, 2026

#### [Private LLM Gateway: Secure vLLM, SGLang, and Ollama](https://api7.ai/blog/private-llm-gateway)

Learn how a private LLM gateway secures vLLM, SGLang, and Ollama with stable model aliases, traffic policy, routing, and observability.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[LLM](https://api7.ai/tags/llm)

[AISIX](https://api7.ai/tags/aisix)

[![What Is an MCP Registry? Discovery and Gateway Control](https://static.api7.ai/uploads/2026/09/15/PL8CU1Q1_what-is-mcp-registry.webp)](https://api7.ai/blog/what-is-mcp-registry)

Technology

September 15, 2026

#### [What Is an MCP Registry? Discovery and Gateway Control](https://api7.ai/blog/what-is-mcp-registry)

Learn how an MCP Registry catalogs servers, differs from a marketplace and gateway, and supports governed MCP discovery and tool execution.

[MCP](https://api7.ai/tags/mcp)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AI Agents](https://api7.ai/tags/ai-agents)

[![AI Gateway for Batch Inference and Fine-Tuning](https://static.api7.ai/uploads/2026/09/08/1oakSlUL_ai-gateway-batch-inference-fine-tuning.webp)](https://api7.ai/blog/ai-gateway-batch-inference-fine-tuning)

Technology

September 8, 2026

#### [AI Gateway for Batch Inference and Fine-Tuning](https://api7.ai/blog/ai-gateway-batch-inference-fine-tuning)

Learn how an AI Gateway governs Files, Batch, and Fine-tuning APIs with secure routing, credential isolation, job lifecycle control, and usage attribution.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Batch Inference](https://api7.ai/tags/batch-inference)

[![Multimodal AI Gateway for Image, Audio, and Video](https://static.api7.ai/uploads/2026/09/08/jsFG35oO_multimodal-ai-gateway.webp)](https://api7.ai/blog/multimodal-ai-gateway)

Technology

September 8, 2026

#### [Multimodal AI Gateway for Image, Audio, and Video](https://api7.ai/blog/multimodal-ai-gateway)

Learn how a multimodal AI Gateway governs image, audio, video, and realtime APIs across identity, policy, provider routing, cost, and telemetry.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Multimodal AI](https://api7.ai/tags/multimodal-ai)

[![AISIX 1.0.0: Make AI Guardrails Measurable Before You Rely on Them](https://static.api7.ai/uploads/2026/09/07/HF3Ljx3T_aisix-1-0-0-measurable-ai-guardrails.webp)](https://api7.ai/blog/aisix-1-0-0-measurable-ai-guardrails)

Products

September 7, 2026

#### [AISIX 1.0.0: Make AI Guardrails Measurable Before You Rely on Them](https://api7.ai/blog/aisix-1-0-0-measurable-ai-guardrails)

AISIX 1.0.0 adds semantic guardrail testing and decision scores, with clearer failure policies and controls for production AI traffic.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AI Guardrails](https://api7.ai/tags/ai-guardrails)

[![AI Gateway Audit Logging: Build Evidence for AI Governance and Compliance](https://static.api7.ai/uploads/2026/09/01/yp4wliZO_ai-gateway-audit-logging.webp)](https://api7.ai/blog/ai-gateway-audit-logging)

Technology

September 1, 2026

#### [AI Gateway Audit Logging: Build Evidence for AI Governance and Compliance](https://api7.ai/blog/ai-gateway-audit-logging)

Learn how AI Gateway audit logging connects requests, policy outcomes, configuration changes, retention, and exports for AI governance and investigations.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[AI Governance](https://api7.ai/tags/ai-governance)

[![PII Redaction in an AI Gateway: Protect Sensitive Data Before It Reaches an LLM](https://static.api7.ai/uploads/2026/09/01/2G8m9g09_ai-gateway-pii-redaction.webp)](https://api7.ai/blog/ai-gateway-pii-redaction)

Technology

September 1, 2026

#### [PII Redaction in an AI Gateway: Protect Sensitive Data Before It Reaches an LLM](https://api7.ai/blog/ai-gateway-pii-redaction)

Learn how AI Gateway PII redaction detects, masks, or blocks sensitive data in LLM requests and responses before it crosses a trust boundary.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Security](https://api7.ai/tags/security)

[![Rolling Out AI Gateway Guardrails: Monitor, Block, and Handle Streaming Safely](https://static.api7.ai/uploads/2026/08/25/gJlmAdvv_ai-gateway-guardrails.webp)](https://api7.ai/blog/ai-gateway-guardrails)

Technology

August 25, 2026

#### [Rolling Out AI Gateway Guardrails: Monitor, Block, and Handle Streaming Safely](https://api7.ai/blog/ai-gateway-guardrails)

Use AISIX AI Gateway guardrails safely with monitor and block modes, input and output hooks, scoped policies, streaming controls, and failure handling.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Security](https://api7.ai/tags/security)

[![Rotate LLM Provider Keys in AISIX Without Breaking Model Aliases](https://static.api7.ai/uploads/2026/08/25/61viB4d5_ai-gateway-provider-key-management.webp)](https://api7.ai/blog/ai-gateway-provider-key-management)

Technology

August 25, 2026

#### [Rotate LLM Provider Keys in AISIX Without Breaking Model Aliases](https://api7.ai/blog/ai-gateway-provider-key-management)

Rotate LLM provider credentials in AISIX Cloud or open-source AISIX while keeping caller API keys and model aliases stable, tested, and recoverable.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[Security](https://api7.ai/tags/security)

[![MCP 2026-07-28 Support in AISIX AI Gateway](https://static.api7.ai/uploads/2026/08/19/XzdYJ6os_aisix-mcp-2026-cover.svg)](https://api7.ai/blog/aisix-mcp-2026-07-28-stateless-protocol)

Products

August 19, 2026

#### [MCP 2026-07-28 Support in AISIX AI Gateway](https://api7.ai/blog/aisix-mcp-2026-07-28-stateless-protocol)

AISIX AI Gateway now serves the stateless MCP 2026-07-28 revision alongside every 2025 revision on one endpoint, with per-server protocol pinning and a one-call-one-execution guarantee.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[MCP](https://api7.ai/tags/mcp)

[![Open Source AI Gateway: Envoy, AISIX, Kong, and Cloudflare Compared](https://static.api7.ai/uploads/2026/07/01/jsSaiicU_4-7-1.webp)](https://api7.ai/blog/open-source-ai-gateway)

Technology

July 1, 2026

#### [Open Source AI Gateway: Envoy, AISIX, Kong, and Cloudflare Compared](https://api7.ai/blog/open-source-ai-gateway)

Compare open source AI Gateway options and learn how to evaluate AI traffic control, security, cost governance, and enterprise readiness.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AISIX](https://api7.ai/tags/aisix)

[API Gateway](https://api7.ai/tags/api-gateway)

[![AI Gateway for AI Agents: An Onboarding Acceptance Checklist](https://static.api7.ai/uploads/2026/11/02/8vJHSuzb_ai-agent-onboarding-acceptance.webp)](https://api7.ai/blog/ai-gateway-for-ai-agents)

Technology

June 17, 2026

#### [AI Gateway for AI Agents: An Onboarding Acceptance Checklist](https://api7.ai/blog/ai-gateway-for-ai-agents)

Onboard one AI agent through an AI gateway with explicit identity, model access, provider credentials, limits, failure handling, and audit evidence.

[AI Gateway](https://api7.ai/tags/ai-gateway)

[AI Agents](https://api7.ai/tags/ai-agents)

[AISIX](https://api7.ai/tags/aisix)

[![Model Ensembles: Several Low-Cost LLMs, One Better Answer](https://static.api7.ai/uploads/2026/06/17/2u3aG96O_aisix-ensemble-cover.svg)](https://api7.ai/blog/model-ensembles-panel-judge)

Products

June 17, 2026

#### [Model Ensembles: Several Low-Cost LLMs, One Better Answer](https://api7.ai/blog/model-ensembles-panel-judge)

AISIX model ensembles fan one chat request to a panel of LLMs, then a judge synthesizes one answer — so several low-cost models can rival a frontier model.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)

[LLM](https://api7.ai/tags/llm)

[![Announcing AISIX: The AI-Native AI Gateway](https://static.api7.ai/uploads/2026/03/31/gVuNRZ66_aisix-cover.webp)](https://api7.ai/blog/aisix-ai-native-ai-gateway)

Products

March 31, 2026

#### [Announcing AISIX: The AI-Native AI Gateway](https://api7.ai/blog/aisix-ai-native-ai-gateway)

Learn why API7 built AISIX from scratch as an AI-native gateway for LLM workloads, with unified model access, observability, and fine-grained traffic control.

[AISIX](https://api7.ai/tags/aisix)

[AI Gateway](https://api7.ai/tags/ai-gateway)
