June 4, 2026
New Models
- Nemotron 3 Ultra moved to
Available. - DigitalOcean provider coverage was added for Nemotron 3 Ultra as a coming-soon endpoint with reference pricing.
- NVIDIA NIM provider coverage was added for Nemotron 3 Ultra, Nemotron 3 Super, Nemotron 3 Nano, and Nemotron 3 Nano Omni.
June 1, 2026
New Models
- MiniMax M3 moved to
Availablewith MiniMax API, NovitaAI, and Venice coverage. - CrofAI pricing and live model coverage were synced.
- Nemotron 3 Ultra was added in
Announcedstate.
May 31, 2026
New Models
- Cosmos 3 Super Reasoner was added.
May 30, 2026
New Models
- Grok Imagine Video 1.5 Preview was added.
May 28, 2026
Product
- Qwen 3.7 Max pricing selectors and provider display were cleaned up.
- Anthropic-on-AWS branding and related provider display details were refreshed.
New Models
- Claude Opus 4.8 was added.
- Gemini 3.1 Flash Image and Gemini 3 Pro Image were added.
- Greg RP was added.
May 25, 2026
New Models
- Qwen 3.7 Max Preview and the dated
2026-05-17snapshot were added.
May 21, 2026
New Models
- Qwen 3.7 Max was added.
May 20, 2026
New Models
- Command A Plus was added.
May 19, 2026
Product
- The public TypeScript Agent SDK launch was added to the product changelog.
New Models
- Gemini 3.5 Flash was added.
- Qwen 3.5 LiveTranslate Flash Realtime (
2026-05-19) was added.
May 18, 2026
New Models
- Composer 2.5 was added.
May 16, 2026
Product
- Provider activation states, region filters, and free-router fixes shipped.
@ai-stats/agent-sdklaunched with docs and examples.
New Models
- OpenAI EU, Google Vertex EU, and Nebius Token Factory Fast were added.
- Grok TTS was added.
- OVHcloud and Scaleway pricing coverage expanded.
May 15, 2026
New Models
- Grok Build 0.1 was added.
- Aion 3.0 and Step 3.6 were tracked as
Rumoured.
May 7, 2026
Product
- Provider availability, pricing summaries, and realtime minute pricing were improved.
New Models
- Gemini 3.1 Flash-Lite was added.
- GPT Realtime 2, GPT Realtime Translate, and GPT Realtime Whisper were added.
- Kimi K2 metadata was refreshed.
May 6, 2026
Product
- Video and async job lifecycle coverage expanded.
New Models
- Grok Imagine Image Quality was added.
May 5, 2026
New Models
chat-latestwas added.
May 1, 2026
Product
- SDK
2.0.3was released across TypeScript, Python, Go, C#, Java, PHP, and Ruby.
April 30, 2026
New Models
- GPT 5.5 Cyber was announced and tracked as
Withheld. - Benchmark metadata, benchmark ranks, and CrofAI pricing or discovery checks were refreshed.
April 29, 2026
Product
- SDK
2.0.2landed with runtime model identifiers and callable-on-gateway helper updates.
New Models
- Mistral Medium 3.5 was added.
- IBM Granite 4.1 3B, 8B, and 30B were added.
April 25, 2026
Product
- Low-balance alerts, billing safeguards, and related pricing edge-case fixes shipped.
April 22, 2026
Product
- SDK
2.0.0shipped with regenerated clients and broader parity against the current gateway contract.
April 21, 2026
Product
- The announcements hub, workspace management surfaces, and related membership flows shipped.
New Models
- GPT Image 2 was added.
- Qwen 3.6 Max Preview was added.
- Kimi K2.6 was added.
April 18, 2026
Product
- SDK
1.2.0synced model availability, generated types, and docs with the latest catalog changes.
April 17, 2026
New Models
- Grok 4.3 was added.
- Qwen 3.6 35B A3B was added.
April 16, 2026
New Models
- Claude Opus 4.7 was added.
April 15, 2026
New Models
- Gemini 3.1 Flash TTS Preview was added.
April 14, 2026
New Models
- Gemini Robotics ER 1.6 Preview was added.
- GPT 5.4 Cyber was added.
April 8, 2026
New Models
- Muse Spark and Muse Spark Contemplating were added.
April 7, 2026
New Models
- Claude Mythos Preview was added.
- GLM 5.1 was added.
April 4, 2026
Product
- Mobile model pages, pricing layouts, and free-route visibility were improved, and the Pay As You Go top-up fee dropped to 5%.
April 2, 2026
New Models
- Gemma 4 26B A4B and Gemma 4 31B were added.
April 1, 2026
New Models
- GLM 5V Turbo was added.
- Qwen 3.6 Plus was added.
March 31, 2026
New Models
- Veo 3.1 Lite Preview was added.
March 22, 2026
Product
- New language SDKs shipped, TypeScript and Python SDKs were overhauled, and chat rooms went multimodal.
- Foundry launched, LLM Council became the first Foundry project, and SDK
1.1.0aligned model availability and lifecycle warnings with the API.
March 19, 2026
New Models
- MiMo V2 Pro, MiMo V2 Omni, and MiMo V2 TTS were added.
- Cursor Composer 2 was added.
March 18, 2026
New Models
- MiniMax M2.7 was added.
March 17, 2026
New Models
- GPT 5.4 Mini and GPT 5.4 Nano were added.
- Mistral Moderation 2 was added.
March 16, 2026
New Models
- Leanstral was added.
- Mistral Small 4 was added.
March 15, 2026
New Models
- GLM 5 Turbo was added.
March 12, 2026
Product
- The models display page was overhauled for clearer availability, metadata hierarchy, and support context.
New Models
- Nemotron 3 Super was added.
March 11, 2026
New Models
- Grok 4.20 was added.
March 10, 2026
Product
- A broader brand refresh shipped across the website and docs.
- Alibaba Cloud provider coverage landed across AI Stats, gateway routes, and documentation.
New Models
- Gemini Embedding 2 Preview was added.
March 5, 2026
Product
- GPT 5.4 and GPT 5.4 Pro landed across discovery, gateway, and docs.
New Models
- GPT 5.4 was added.
- GPT 5.4 Pro was added.
March 3, 2026
Product
- Gemini 3.1 Flash Lite Preview landed across product surfaces, gateway routing, and docs.
New Models
- Gemini 3.1 Flash Lite Preview was added.
March 2, 2026
Product
- Responses API assistant
phasesupport landed across request handling, response payloads, and OpenAPI docs.
February 26, 2026
Product
- Gemini 3.1 Flash Image Preview support landed across discovery, gateway compatibility, and docs.
New Models
- Gemini 3.1 Flash Image Preview (Nano Banana 2) was added.
February 24, 2026
New Models
- Mercury Edit 2 was added.
February 23, 2026
New Models
- GPT Realtime 1.5 and GPT Audio 1.5 were added.
February 19, 2026
Product
- Gemini 3.1 Pro Preview coverage landed across discovery, pricing, gateway support, and docs.
New Models
- Gemini 3.1 Pro Preview was added.
February 18, 2026
Product
- Claude Sonnet 4.6 coverage landed across discovery, gateway compatibility, and docs.
New Models
- Claude Sonnet 4.6 was added.
January 30, 2026
Product
- The gateway was overhauled again, including Anthropic-compatible
/messagessupport. - Database architecture, website UX, playground tooling, and SDK direction were all refreshed for broader expansion.
New Models
- GLM 4.5 Air X and GLM 4.5 X were added.
- Grok Imagine Image and Grok Imagine Video were added.
- Qwen 3 Max Thinking, Kimi K2.5, and MiniMax M2 Her were added.
January 19, 2026
New Models
- Bulk catalog additions were imported through Database Monitor.
January 3, 2026
New Models
- Organisation coverage expanded with Relace, Arcee AI, Liquid AI, Sourceful, Prime Intellect, and Naver HyperClova.
- New model coverage included Music 2.0, Speech 2.6, GLM 4.7, Seed 1.6, Seed 1.6 Flash, Seed 1.8, Seedream 4.5, Relace Search, and Trinity Large.
- Provider coverage expanded across Moonshot AI Turbo, Nebius Token Factory, Crusoe, Liquid, Mancer, Xiaomi, Cloudflare, Hyperbolic, Perplexity, Fireworks, SiliconFlow, and more.
December 31, 2025
New Models
- K EXAONE was added.
December 29, 2025
New Models
- HyperClova X Seed Omni 8B and HyperClova X Seed Think 32B were added.
December 23, 2025
New Models
- MiniMax M2.1 was added.
December 22, 2025
New Models
- GLM 4.7 was added.
December 19, 2025
New Models
- GPT 5.2 Codex, OCR 3, and GLM 4.7 were added.
December 18, 2025
New Models
- Gemini 3 Flash Preview was added.
December 17, 2025
New Models
- Organisation coverage expanded with Xiaomi and AllenAI.
- New model coverage included GPT Image 1.5, ChatGPT Image Latest, MiMo V2 Flash, Bolmo 1B, Bolmo 7B, Molmo 2 4B, Molmo 2 8B, and several OLMo 3 variants.
December 15, 2025
Product
- Early alpha SDK releases landed for Python and TypeScript or JavaScript.
New Models
- GPT 5.2 Mini, GPT 4o Mini TTS, GPT 4o Mini Transcribe, GPT Realtime Mini, GPT Audio Mini, and Claude 4.7 Sonnet were added.
December 12, 2025
Product
- OpenAI-compatible
/responsessupport, aligned SDKs, and gateway quickstart or pricing page updates shipped. - Docs expanded ahead of the SDK launch, and nightly CI started automatically refreshing model statuses.
New Models
- GPT 5.2, GPT 5.2 Chat, GPT 5.2 Pro, GPT 5.2 Mini, Rerank V4 Pro, and Rerank V4 Fast were added.
December 10, 2025
New Models
- Qwen 3 Omni Flash was added.
December 9, 2025
New Models
- Devstral 2, Devstral Small 2, and Nomos 1 were added.
December 8, 2025
New Models
- Essential AI Rnj-1, Nous Research Hermes 4.3, Jamba Reasoning 3B, GLM 4.6V, GLM 4.6V Flash, Qwen 3 TTS, and Gemini 3 Flash Image were added.
December 5, 2025
Product
- Dark mode shipped.
December 2, 2025
New Models
- Mistral Large 3 675B, Ministral 3 14B, Ministral 3 8B, Ministral 3 3B, Nova 2 Lite, Nova 2 Pro, Nova 2 Sonic, Nova 2 Omni, and Nova Multimodal Embeddings were added.
December 1, 2025
Product
- AI Stats relaunched with a refreshed brand, a broader gateway, and much wider data coverage.
- Model availability, benchmark pages, provider pages, and the latest-updates surfaces were overhauled.
- The unified gateway entered alpha, and the first Python and TypeScript or JavaScript SDKs launched alongside it.
New Models
- Deepseek V3.2 Speciale and DeepSeek V3.2 were added.
June 30, 2025
New Models
- Hunyuan A13B Instruct was added.
August 30, 2024
New Models
- Command R was added.