Changelog

Mistral Medium 3.5

Mistral Medium 3.5 is a 128B dense instruction-following model from Mistral AI, supporting text and image inputs with text output. It is designed for agentic workflows, coding, and complex multi-step reasoning, with strong reliability in multi-tool orchestration and long-horizon tasks.

The model features a 256K token context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. With support for self-hosting on as few as four GPUs and availability under open weights, it is well suited for scalable, production-grade deployments.

Cobuddy

CoBuddy is a code generation model from Baidu, optimized for coding tasks and AI agent workflows. It delivers high inference throughput and low end-to-end latency, making it well suited for responsive development and automation environments.

The model includes native support for tool calling and reasoning, runs with FP8 quantization for efficient deployment, and supports a 131K token context window with up to 65K output tokens, enabling long-context coding and multi-step agentic workflows.

Enjoy them.

Full Audio API Support

Apertis now supports the OpenAI-compatible Audio API. Use a single API key to access leading TTS (text-to-speech) and STT (speech-to-text) models across providers.

Supported Models

Text-to-Speech (TTS)

• gemini-3.1-flash-tts-preview — Google's latest Flash TTS preview
• gpt-4o-mini-tts — OpenAI's lightweight real-time speech synthesis

Speech-to-Text (STT)

• gpt-4o-transcribe — Flagship high-accuracy transcription
• gpt-4o-mini-transcribe — Cost-efficient real-time transcription
• whisper-large-v3-turbo — Accelerated Whisper v3
• whisper-large-v3 — Full-precision Whisper
• whisper-1 — The classic, battle-tested baseline

Endpoints

Drop-in compatible with the OpenAI SDK — no code changes required:

• POST /v1/audio/speech — text → audio
• POST /v1/audio/transcriptions — audio → text
• POST /v1/audio/translations — audio → translated text

Billing

• PAYG (pay-as-you-go): shares the same quota balance as chat/completions
• Per-dimension billing: priced separately on input tokens / output

tokens / audio seconds, with admin-tunable AudioRatio

• File limit: 25 MB per multipart upload
• Subscriptions: audio models are PAYG-only for now (not included

in subscription plans)

Example

  from openai import OpenAI

  client = OpenAI(
      api_key="sk-your-apertis-key",
      base_url="https://api.apertis.ai/v1"
  )

  # TTS
  speech = client.audio.speech.create(
      model="gpt-4o-mini-tts",
      voice="alloy",
      input="Hello from Apertis."
  )
  speech.stream_to_file("hello.mp3")

  # STT
  with open("audio.mp3", "rb") as f:
      transcript = client.audio.transcriptions.create(
          model="whisper-large-v3-turbo",
          file=f
      )
  print(transcript.text)

Model Detail Page Updates

• Endpoint and code samples auto-switch based on the model's task
• TTS models now emit ready-to-run OpenAI SDK Python snippets
• Web Search pricing column hidden for voice models (:web is unsupported)

Grok 4.3

Grok 4.3 is a reasoning-focused model from xAI designed for agentic workflows, instruction following, and high factual accuracy tasks. It supports text and image inputs with text output, with reasoning always active and not configurable by effort level.

The model features a 1M-token context window with effectively no output token limit, making it well suited for long-document analysis, deep research, and multi-step agentic workflows. It uses tiered pricing, with higher rates applied to requests exceeding 200K total tokens.

Enjoy it.

Nemotron 3 Nano Omni (Free)

NVIDIA Nemotron 3 Nano Omni is an open 30B-A3B multimodal model designed as a perception and context sub-agent for enterprise agent systems. It supports text, image, video, and audio inputs with text output, enabling unified multimodal reasoning within a single inference loop. Built on a hybrid MoE Transformer–Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers significantly improved efficiency for video reasoning—achieving ~2× higher throughput and 2.5× lower compute compared to separate pipelines.

With up to 300K context length and extended thinking support, it is well suited for scalable, multimodal agent workflows.

Enjoy it.

Qwen3.5 Plus 2026-04-20

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba, supporting text, image, and video inputs with text output. It features a 1M-token context window, enabling large-scale reasoning and multimodal workflows within a single interaction.

This updated version of Qwen3.5 Plus introduces tiered pricing beyond 256K tokens, making it suitable for high-context applications while maintaining flexibility for cost optimization in long-input scenarios.

Qwen3.6 Flash

Qwen3.6 Flash is a fast and efficient model from Alibaba's Qwen 3.6 series, supporting text, image, and video inputs with a 1M-token context window for high-context multimodal workflows.

Optimized for performance and cost efficiency, it features tiered pricing beyond 256K tokens and supports prompt caching with both cache creation and read pricing, making it well suited for large-scale, high-throughput applications.

Qwen3.6 Max Preview

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse Mixture-of-Experts (MoE) architecture with approximately 1 trillion parameters. It is optimized for agentic coding, tool use, and long-context reasoning, supporting a 262K token context window.

The model includes an integrated thinking mode that preserves reasoning across multi-turn interactions, along with support for structured outputs and function calling.

Enjoy them.