Changelog
Stay up to date with the latest features, improvements, and fixes in LLM Gateway.
Grok 4 Fast Models: Flagship and Fast Variants Now Available
Added support for Grok 4 Fast Reasoning, and Grok 4 Fast Non-Reasoning models via xAI provider.
Read more →
50% Off Claude Code - Limited Time Offer
Get 50% off Claude Code for a limited time. Use any model via LLMGateway's unified API.
Read more →
New Alibaba Qwen Models: Qwen3 Next, Max, Plus, Flash, Vision
Added support for qwen-max, qwen-max-latest, qwen-plus-latest, qwen-flash, qwen-vl-max, qwen-vl-plus and the new Qwen3 Next 80B A3B Instruct and Thinking models.
Read more →
Claude Code Configuration Now Supported
Configure Claude Code to use any LLM model through LLMGateway's unified API with simple environment variable setup.
Read more →
Qwen3 Max Model Now Available
Access Alibaba's powerful Qwen3 Max model with 256K context window, advanced reasoning capabilities, vision support, and function calling - all at competitive pricing.
Read more →
Enhanced Auto-Routing & 5 New Free Models via RouteWay
Expanding auto-routing options & access DeepSeek R1T2 Chimera, GLM-4.5 Air, Kimi K2, GPT-OSS 20B, and GPT-4.1 completely free through our RouteWay integration.
Read more →
Introducing Our First Image Generation Model: Gemini 2.5 Flash Image Preview
Generate stunning images with Google's Gemini 2.5 Flash Image Preview - our first image generation model with 32.8k context window and competitive pricing.
Read more →
DeepSeek v3.1 Model Support
Added support for DeepSeek's latest v3.1 model with 128K context window and competitive pricing for advanced reasoning capabilities.
Read more →
New Models Directory & Free Llama 3.1 70B via CloudRift
Browse and compare 100+ AI models with advanced filtering, plus access Meta Llama 3.1 70B Instruct FP8 completely free through our CloudRift partnership.
Read more →
API Key Usage Limits & Credit Controls
Set individual credit limits for API keys to better control spending and prevent unexpected overages.
Read more →
GPT-5 Model Family Now Available
Get instant access to OpenAI's powerful new GPT-5 model family including gpt-5, gpt-5-mini, gpt-5-nano, and gpt-5-chat-latest with 400k context windows.
Read more →
AI SDK Provider v2.0 Released
Released v2.0 of our @llmgateway/ai-sdk-provider npm package with improved Vercel AI SDK integration and simplified model access.
Read more →
Claude 4.1 Models: Opus and Sonnet Now Available
Added support for Claude 4.1 models including claude-opus-4-1, claude-opus-4-20250514, and claude-sonnet-4-20250514 via Anthropic provider.
Read more →
New GPT-OSS Models: 120B and 20B via Groq
Added support for GPT-OSS-120B and GPT-OSS-20B models via Groq, offering powerful open-source alternatives with extensive context windows and competitive pricing.
Read more →
New Providers: Cloudrift, Moonshot AI and Novita AI Support
Added support for Cloudrift, Moonshot AI and Novita AI providers, both offering the powerful kimi-k2 model with extensive context windows and competitive pricing.
Read more →
New Providers: Groq and xAI Support + Always-Visible Credits
Added support for Groq and xAI providers with their latest models, plus credits are now always visible in the sidebar for easy access.
Read more →
Dashboard UI Improvements & Project Context
Introducing organizations and projects for clearer controls and statistics.
Read more →
Pro Subscription Launch
Bring your own LLM provider keys or use credits with zero gateway fees. Includes premium analytics, higher rate limits, and priority email support.
Read more →
Self-Hosting Just Got Easier
New and improved self-hosting documentation for teams and enterprises looking to deploy LLM Gateway on their own infrastructure.
Read more →
Deepseek Discount + Mistral Joins the Lineup
Massive savings with Deepseek models and the arrival of Mistral models for all users. Discover new performance benchmarks at lower costs.
Read more →
LLM Gateway v1.0 Launch
The unified AI gateway is here! Access 30+ models from 8 providers through one OpenAI-compatible API with transparent pricing and powerful analytics.
Read more →