--- title: "last shipped" description: "product updates from impossibl." canonical: https://impossibl.com/changelog human_url: https://impossibl.com/changelog markdown_url: https://impossibl.com/changelog.md --- [models]() · [docs]() · [changelog]() · [company]() # last shipped impossibl changelog ## sep 10, 2026 ### deepseek/deepseek-v4.1-flash **new model** deepseek v4.1 flash joins the gateway. ## sep 9, 2026 ### openai/gpt-image-2.5-flare **new model** openai/gpt-image-2.5-flare is live on /v1/images/generations at $5.00 input and $30.00 output per 1M tokens. ### openai/gpt-image-2.5-sunburst **new model** openai/gpt-image-2.5-sunburst is live on /v1/images/generations at $5.00 input and $30.00 output per 1M tokens. ## sep 4, 2026 ### openai/gpt-6-astra **new model** gpt-6 astra joins the gateway with a 1,050,000 token context window and text plus image input. ## sep 3, 2026 ### meta/muse-spark-1.3 **new model** muse spark 1.3 and muse spark 1.3 contributor join the ai api. ### workspaces **new feature** workspaces join the console: invite your team, give each member a role — owner, admin, developer, or viewer — and switch between the workspaces you belong to from the top of the console. keys, balance, and usage belong to the workspace. ## sep 2, 2026 ### google/gemini-3.8-flash **new model** gemini 3.8 flash joins the ai api with a 1m-token context window. it is promo-priced at $0.75 / $3.75 per million tokens through 2026-12-31. ## sep 1, 2026 ### anthropic/claude-fable-5-1 **new model** claude fable 5.1 joins the ai api with a 1m-token context window and adaptive thinking. cache reads bill at $0.25 per million tokens, a quarter of fable 5's rate. ## aug 26, 2026 ### zai/glm-5.3-flash **new model** glm 5.3 flash joins the ai api. ### qwen/qwen3.8-27b **new model** qwen3.8 27b joins the ai api. ## aug 19, 2026 ### zai/glm-5.3 **new model** glm 5.3 joins the ai api. ## aug 14, 2026 ### deepseek/deepseek-v4-pro-0813 **new model** deepseek v4 pro 0813 joins the ai api. ### google/gemini-3.7-flash **new model** gemini 3.7 flash joins the gateway. ### xai/grok-4.6 **new model** grok 4.6 joins the gateway. ### qwen/qwen3.8-2.4t-a95b **new model** qwen3.8 2.4t a95b joins the ai api. ## aug 11, 2026 ### meta/muse-glimmer-30b **new model** muse glimmer 30b joins the ai api. ### nvidia/nemotron-3.5-lightning **new model** nemotron 3.5 lightning joins the ai api. ## aug 5, 2026 ### log exports take your request log with you. filter the logs room, press export csv, and the whole filtered window walks itself into a spreadsheet — not just the rows on screen. ### sub-cent costs a cheap request no longer reads as free. costs under a cent keep their digits down to the credit, so a log of small calls stops printing as a column of $0.00. ## aug 3, 2026 ### qwen/qwen3.8-max **new model** qwen3.8 max joins the ai api. ## aug 1, 2026 ### deepseek/deepseek-v4-flash-0731 **new model** deepseek v4 flash 0731 joins the ai api. ## jul 30, 2026 ### google/gemini-3.1-flash-tts-preview **new model** gemini 3.1 flash tts brings 30 steerable voices to /v1/audio/speech, billed per token like every other gemini model. ### google/gemini-robotics-er-2-preview **new model** gemini robotics-er 2 preview is now available. ### xai/grok-voice-tts-1.0 **new model** grok voice tts brings five expressive voices and mp3, wav or pcm output to the new /v1/audio/speech endpoint. ## jul 28, 2026 ### audio and video input send audio and video to gemini models on chat completions, the responses api, and the gemini-native endpoint, with audio billed at the provider's audio rate. ### openai/gpt-transcribe **new model** gpt-transcribe brings high-accuracy speech-to-text for completed files and streamed transcripts to /v1/audio/transcriptions. ## jul 27, 2026 ### embeddings **new model** the ai api now turns text into vectors on /v1/embeddings, starting with openai/text-embedding-3-small and openai/text-embedding-3-large. ## jul 25, 2026 ### image generation **new model** the ai api now generates images, starting with openai/gpt-image-2 on /v1/images/generations. ## jul 24, 2026 ### anthropic/claude-opus-5 **new model** claude opus 5 joins the ai api with a 1m-token context window and native anthropic fallback. ### tencent/hy3 **new model** hunyuan 3 joins the ai api through atlascloud. ### qwen/qwen3.7-plus **new model** qwen 3.7 plus joins the ai api through fireworks. ## jul 21, 2026 ### atlascloud **new provider** atlascloud joins the gateway, serving mimo 2.5 and minimax m3. ### google/gemini-3.5-flash-lite **new model** gemini 3.5 flash-lite is now available. ### google/gemini-3.6-flash **new model** gemini 3.6 flash is now available. ### logs every request is now logged. browse them in the dashboard, or have agents pull their own from /v1/requests. ### xiaomi/mimo-v2.5 **new model** mimo 2.5 joins the ai api through atlascloud. ### minimaxai/minimax-m3 **new model** minimax m3 joins the ai api through atlascloud. ### realtime dashboard usage and balance update live in the dashboard as requests come in. ## jul 20, 2026 ### xai/grok-4.5 **new model** grok 4.5 joins the gateway. ### qwen **new provider** alibaba's qwen models join the gateway. ### qwen/qwen3.8-max-preview **new model** qwen's 3.8 max preview joins the gateway. ## jul 19, 2026 ### faster failovers failed routes no longer slow down every request. in our benchmarks, failover times dropped from 6 seconds to under 1 millisecond. ## jul 17, 2026 ### auto top-up recharge when your balance runs low. ### moonshotai/kimi-k3 **new provider** moonshot joins the gateway. ### /onboarding a better start. ## jul 16, 2026 ### thinkingmachines/inkling **new model** two context tiers: 64k and 256k. ## jul 10, 2026 ### cerebras, groq, fireworks **new provider** three fast-inference providers join the gateway. ### google gen ai sdk one-liner migration now supported ## jul 9, 2026 ### openai/gpt-5.6-luna **new model** luna joins the gateway. ### openai/gpt-5.6-sol **new model** sol joins the gateway. ### openai/gpt-5.6-terra **new model** terra joins the gateway. ### web\_search on /v1/responses xai's native web_search and x_search tools. ## jul 8, 2026 ### deepseek v4 + v3.2 **new model** v4 and v3.2 join the gateway. ## jul 6, 2026 ### byok bring your own provider keys now supported ## jul 1, 2026 ### anthropic/claude-fable-5 **new model** fable 5 redeployed. ## jun 30, 2026 ### accounts + provider pricing humans can claim agent-created accounts and merge balances. usage stays at provider price. ### anthropic/claude-sonnet-5 **new model** sonnet 5 launches. ### z.ai **new provider** glm models join the gateway. ## jun 29, 2026 ### human dashboard api keys, credit top-ups and the model catalog. ## jun 27, 2026 ### /v1/messages, images & tools anthropic messages support, with image input and tool calling on every surface. ## jun 26, 2026 ### hello world impossibl init © 2026 impossibl, inc.