Pulse
Real-time AI model tracking across 48 providers. New releases, deprecations, and catalog changes — as they happen.
Today
00:00
00:00
November 9
19:26
New Model
Fable 5.2
Fable 5.2 by Anthropic: the most capable generally available Claude, for demanding reasoning and long-horizon agentic work. 1M context, 128K output, adaptive…
00:21
New Model
Mercury 3
Inception Labs' most capable diffusion LLM: a 1M-token context, 131,072 max output, tool calling, reasoning_effort instant/low/medium/high (medium by default).
November 8
20:09
20:09
20:09
20:09
20:09
20:09
20:09
20:09
20:09
20:09
November 6
23:26
New Model
Gemini Omni Flash 1.2
Google's omni-modal Flash 1.2, GA — fast conversational generation that answers in text and, when asked, in video with native audio. Served through the Interactions…
23:26
New Model
Kling 4.0 Flash
Kling 4.0 Flash, 720p, the faster and lighter Kling 4.0. Text-to-video and image-to-video from a first frame, 3 to 20 seconds.
November 3
15:21
15:16
Deprecated
Tripo V2.5 Multiview-to-3D
Model is still callable but scheduled for sunset. Consider migrating. Replaced by: tripo-v3.1-multiview Sunset date: 2026-11-30
15:16
Deprecated
Gemini 2.5 Flash
Model is still callable but scheduled for sunset. Consider migrating. Replaced by: gemini-3.1-flash-lite Sunset date: 2026-11-30
15:16
Deprecated
Gemini 2.5 Pro
Model is still callable but scheduled for sunset. Consider migrating. Replaced by: gemini-3.6-flash Sunset date: 2026-11-30
15:16
Deprecated
Tripo V2.5 Image-to-3D
Model is still callable but scheduled for sunset. Consider migrating. Replaced by: tripo-v3.1-image Sunset date: 2026-11-30
15:16
Deprecated
Tripo V2.5 Text-to-3D
Model is still callable but scheduled for sunset. Consider migrating. Replaced by: tripo-v3.1-text Sunset date: 2026-11-30
November 2
15:01
14:48
New Model
Sound Effects v3
Sound effects from a text description that follow multi-part prompts more closely, with better vocal and musical sounds: automatic length or a set length up to 30…
November 1
23:49
23:43
New Model
RD Plus
Retro Diffusion's all-rounder with the largest style library: watercolor, cartoon, isometric, top-down maps, skill icons and more. 64-384px; classic and skill icons…
23:43
New Model
RD Pro
Retro Diffusion's highest-quality pixel art: the cleanest pixel work and the closest prompt following, from 12px sprites to dungeon maps, typography and UI panels.…
17:05
New Model
Voxtral Mini Transcribe 3
Mistral's speech-to-text at a competitive price, with the language detected. Voxtral 3, the successor of Voxtral Mini Transcribe 2.
17:05
New Model
Voxtral Small Transcribe 3
Mistral's flagship speech-to-text, its most accurate transcription, with the language detected. Voxtral 3.
12:31
12:31
October 31
20:18
New Model
Wan 3.0
Alibaba Wan 3.0, all-in-one video with native audio: text-to-video, or from a first frame and an optional last frame. 2 to 30 seconds, 480p to 1080p (native…
20:18
New Model
Wan 3.0 Prime
Alibaba Wan 3.0 Prime, the faster tier of Wan 3.0 with the same capabilities: text-to-video or first/last frame, native audio, 2 to 30 seconds, 480p to 1080p…
20:09
New Model
Seedream 5.0 Flash
ByteDance Seedream 5.0 Flash, the fast tier of Seedream 5.0: text-to-image up to 2K at the lowest price of the line. Native via BytePlus (Ark).
20:09
New Model
Kling 4.0
Kling 4.0, 720p, native stereo audio always on. Text-to-video and image-to-video, 3 to 30 seconds.
19:55
19:54
19:54
19:54
19:54
19:54
19:54
19:54
19:54
19:54
19:54
19:54
19:54
00:00
October 29
15:00
15:00
15:00
15:00
15:00
October 28
23:44
New Model
Qwen3.7 Flash
Low-cost Flash model with 1M context. Accepts text and images, with tool use and thinking.
23:44
New Model
Qwen3.8 Flash
Alibaba's newest Flash model. 1M context, accepts text and images, with tool use and thinking.
22:17
New Model
Kimi K3.1 Pro
Moonshot's headline model: a 1M-token context window, native image understanding, tool use and reasoning.
22:17
New Model
Kimi K3.1 Pro Highspeed
Kimi K3.1 Pro at about 2–3× the speed, at a higher price: the same intelligence, with a 1M-token context window.
October 27
13:46
13:46
13:46
02:36
New Model
GPT-6.1 Sol
OpenAI GPT-6.1 Sol: GPT-6.1 reasoning at a fifth of Astra's price, over a 1M-token context window.
02:24
New Model
GPT-6.1 Terra
OpenAI GPT-6.1 Terra: the mid-tier GPT-6.1 model at a tenth of Astra's price per token, over a 1M-token context window.
October 25
18:25
October 24
20:55
New Model
Fibo 2.0
Bria's licensed-data model for text-to-image and controllable edits with up to four reference images or a single-image mask.
October 23
00:00
00:00
00:00
00:00
00:00
00:00
00:00
October 22
00:00
October 21
12:11
12:11
12:11
12:11
12:11
12:11
October 20
19:02
October 19
21:57
19:14
19:14
15:30
15:30
October 16
18:02
18:02
October 15
22:56
New Model
Gemini 4 Argon
Google's flagship reasoning model: a 1M-token context, text, image, video and audio in, text out, with native tool use and three thinking levels.
00:00
October 12
13:00
New Model
Nano Banana 2.1
Google's high-efficiency image generation and editing model — improved visual quality, typography, and multi-turn consistency; 1K/2K/4K. The unit rate is the 1K…
13:00
New Model
Gemini Omni Flash 1.1
Google's omni-modal Flash, GA — fast conversational generation with native video output. Served via the Interactions API like its preview parent, text-in today…
October 11
19:01
New Model
Mistral Large 4
Mistral's open-weight flagship (public preview, 2026-10-06). 1.05T MoE (52B active) with a vision encoder; reasoning on demand, tools. 1M context.
October 10
00:00
00:00
October 9
00:43
New Model
Haiku 5.5
Haiku 5.5 by Anthropic (2026-10-07): the fastest Claude, for high-volume, latency-sensitive work such as classification, extraction and routing. 1M context, 128K…
00:00
00:00
00:00
00:00
00:00