Skip to main content

Models

The models available for inference in AI Studio, by modality, with pricing and how to manage them.

Hyperstack AI Studio provides a catalog of text and image models that you can use for inference through the playgrounds and the API. This page lists the available models by modality, explains how they are priced, and shows how to manage them from the Model Catalog page in AI Studio.

Models are served through third-party provider API integrations and appear on the Model Catalog page under the Base Models tab (see here). Because these models are provided by external services, AI Studio cannot guarantee continued availability, and access may be revoked at any time if a provider changes or removes support for a model. Pricing is also subject to change and may be updated by the provider at any time. Requests may be processed by external providers in order to fulfill your request, and usage is subject to the availability, reliability, and data-handling practices of those providers.

Model Modalities​

Model Catalog - Base ModelsModel Catalog - Base Models

Hyperstack AI Studio offers a range of models spanning multiple modalities. You can filter models by modality on the Model Catalog page:

  • Text-to-Text – Generate text from text inputs (e.g., chat, summarization, code generation)
  • Image-to-Text – Generate text from an image and a text prompt (e.g., describe or answer questions about an image)
  • Text-to-Image – Generate images from text prompts
  • Image-to-Image – Transform or edit existing images using image inputs

Learn more about each model type, including supported models and how to use them in AI Studio:

Text-to-Text Models​

Text-to-text models process text inputs and generate text outputs. These are used for tasks such as chat, summarization, reasoning, and code generation. These models can be used within the Text Playground.

Click to expand list of text-to-text models
Availability varies

The models available can change at any time. For the list of models currently available, see the Model Catalog in AI Studio.

  • alpindale/WizardLM-2-8x22B
  • arcee-ai/Trinity-Mini
  • baichuan-inc/Baichuan-M2-32B
  • baidu/ERNIE-4.5-21B-A3B-PT
  • baidu/ERNIE-4.5-300B-A47B-Base-PT
  • deepcogito/cogito-671b-v2.1
  • deepcogito/cogito-671b-v2.1-FP8
  • deepcogito/cogito-v2-preview-llama-405B
  • deepcogito/cogito-v2-preview-llama-70B
  • deepreinforce-ai/Ornith-1.0-35B
  • deepreinforce-ai/Ornith-1.0-35B-FP8
  • deepseek-ai/DeepSeek-Prover-V2-671B
  • deepseek-ai/DeepSeek-R1
  • deepseek-ai/DeepSeek-R1-0528
  • deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
  • deepseek-ai/DeepSeek-R1-Distill-Llama-70B
  • deepseek-ai/DeepSeek-R1-Distill-Llama-8B
  • deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
  • deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  • deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
  • deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
  • deepseek-ai/DeepSeek-V3
  • deepseek-ai/DeepSeek-V3-0324
  • deepseek-ai/DeepSeek-V3.1
  • deepseek-ai/DeepSeek-V3.1-Terminus
  • deepseek-ai/DeepSeek-V3.2
  • deepseek-ai/DeepSeek-V3.2-Exp
  • deepseek-ai/DeepSeek-V4-Flash
  • deepseek-ai/DeepSeek-V4-Flash-0731
  • deepseek-ai/DeepSeek-V4-Pro
  • deepseek-ai/DeepSeek-V4-Pro-0813
  • EssentialAI/rnj-1-instruct
  • google/gemma-2-2b-it
  • google/gemma-2-9b-it
  • google/gemma-3-12b-it
  • google/gemma-3-27b-it
  • google/gemma-3-4b-it
  • google/gemma-3n-E4B-it
  • google/gemma-4-26B-A4B-it
  • google/gemma-4-31B-it
  • ibm-granite/granite-4.2-30b
  • ibm-granite/granite-4.2-3b
  • ibm-granite/granite-4.2-8b
  • inclusionAI/Ling-2.6-1T
  • inclusionAI/Ling-3.0-flash
  • marin-community/marin-8b-instruct
  • meta-llama/Llama-3.2-3B-Instruct
  • meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
  • meta-llama/Llama-4-Scout-17B-16E-Instruct
  • meta-llama/Meta-Llama-3-70B-Instruct
  • meta-llama/Meta-Llama-3-8B-Instruct
  • meta-models/Muse-Glimmer-30B
  • microsoft/phi-4
  • MiniMaxAI/MiniMax-M1-80k
  • MiniMaxAI/MiniMax-M2
  • MiniMaxAI/MiniMax-M2.1
  • MiniMaxAI/MiniMax-M2.5
  • MiniMaxAI/MiniMax-M2.7
  • MiniMaxAI/MiniMax-M3
  • moonshotai/Kimi-K2-Instruct
  • moonshotai/Kimi-K2-Instruct-0905
  • moonshotai/Kimi-K2-Thinking
  • moonshotai/Kimi-K2.5
  • moonshotai/Kimi-K2.6
  • moonshotai/Kimi-K2.7-Code
  • moonshotai/Kimi-K3
  • NousResearch/Hermes-2-Pro-Llama-3-8B
  • NousResearch/Hermes-3-Llama-3.1-70B
  • NousResearch/Hermes-4-405B
  • NousResearch/Hermes-4-70B
  • nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
  • nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
  • nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
  • nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
  • nvidia/NVIDIA-Nemotron-Nano-12B-v2
  • openai/gpt-oss-20b
  • pearl-ai/Gemma-4-31B-it-pearl
  • PrimeIntellect/INTELLECT-3-FP8
  • Qwen/Qwen2.5-72B-Instruct
  • Qwen/Qwen2.5-7B-Instruct
  • Qwen/Qwen2.5-Coder-32B-Instruct
  • Qwen/Qwen2.5-Coder-3B-Instruct
  • Qwen/Qwen2.5-Coder-7B
  • Qwen/Qwen2.5-Coder-7B-Instruct
  • Qwen/Qwen2.5-VL-72B-Instruct
  • Qwen/Qwen3-14B
  • Qwen/Qwen3-235B-A22B
  • Qwen/Qwen3-235B-A22B-FP8
  • Qwen/Qwen3-235B-A22B-Instruct-2507
  • Qwen/Qwen3-235B-A22B-Thinking-2507
  • Qwen/Qwen3-30B-A3B
  • Qwen/Qwen3-30B-A3B-Instruct-2507
  • Qwen/Qwen3-30B-A3B-Thinking-2507
  • Qwen/Qwen3-32B
  • Qwen/Qwen3-4B-Instruct-2507
  • Qwen/Qwen3-4B-Thinking-2507
  • Qwen/Qwen3-8B
  • Qwen/Qwen3-Coder-30B-A3B-Instruct
  • Qwen/Qwen3-Coder-480B-A35B-Instruct
  • Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8
  • Qwen/Qwen3-Coder-Next
  • Qwen/Qwen3-Coder-Next-FP8
  • Qwen/Qwen3-Next-80B-A3B-Instruct
  • Qwen/Qwen3-Next-80B-A3B-Thinking
  • Qwen/Qwen3-VL-235B-A22B-Instruct
  • Qwen/Qwen3-VL-235B-A22B-Thinking
  • Qwen/Qwen3-VL-30B-A3B-Instruct
  • Qwen/Qwen3.5-122B-A10B
  • Qwen/Qwen3.5-27B
  • Qwen/Qwen3.5-35B-A3B
  • Qwen/Qwen3.5-397B-A17B
  • Qwen/Qwen3.5-9B
  • Qwen/Qwen3.6-27B
  • Qwen/Qwen3.6-35B-A3B
  • Qwen/Qwen3.8-2.4T-A95B
  • Qwen/Qwen3.8-27B
  • Qwen/QwQ-32B
  • Sao10K/L3-70B-Euryale-v2.1
  • Sao10K/L3-8B-Lunaris-v1
  • Sao10K/L3-8B-Stheno-v3.2
  • stepfun-ai/Step-3.5-Flash
  • stepfun-ai/Step-3.7-Flash
  • tencent/Hy3
  • thinkingmachines/Inkling
  • tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4
  • XiaomiMiMo/MiMo-V2-Flash
  • XiaomiMiMo/MiMo-V2.5
  • XiaomiMiMo/MiMo-V2.5-Pro
  • zai-org/AutoGLM-Phone-9B-Multilingual
  • zai-org/GLM-4-32B-0414
  • zai-org/GLM-4.5
  • zai-org/GLM-4.5-Air
  • zai-org/GLM-4.5-Air-FP8
  • zai-org/GLM-4.5V
  • zai-org/GLM-4.6
  • zai-org/GLM-4.6V-Flash
  • zai-org/GLM-4.7
  • zai-org/GLM-4.7-Flash
  • zai-org/GLM-4.7-FP8
  • zai-org/GLM-5
  • zai-org/GLM-5.1
  • zai-org/GLM-5.1-FP8
  • zai-org/GLM-5.2
  • zai-org/GLM-5.3-Flash

Image-to-Text Models​

Image-to-text models (also called vision-language models) accept an image alongside your text prompt and generate a text response, such as describing an image or answering questions about it. These models can be used within the Text Playground by attaching an image to your message.

Click to expand list of image-to-text models
Availability varies

The models available can change at any time. For the list of models currently available, see the Model Catalog in AI Studio and filter by Image-to-Text.

  • google/gemma-3-12b-it
  • google/gemma-3-27b-it
  • google/gemma-3-4b-it
  • google/gemma-3n-E4B-it
  • google/gemma-4-26B-A4B-it
  • google/gemma-4-31B-it
  • meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
  • meta-llama/Llama-4-Scout-17B-16E-Instruct
  • MiniMaxAI/MiniMax-M3
  • moonshotai/Kimi-K2.5
  • moonshotai/Kimi-K2.6
  • moonshotai/Kimi-K2.7-Code
  • moonshotai/Kimi-K3
  • Qwen/Qwen2.5-VL-72B-Instruct
  • Qwen/Qwen3-VL-235B-A22B-Instruct
  • Qwen/Qwen3-VL-235B-A22B-Thinking
  • Qwen/Qwen3-VL-30B-A3B-Instruct
  • Qwen/Qwen3.5-122B-A10B
  • Qwen/Qwen3.5-27B
  • Qwen/Qwen3.5-35B-A3B
  • Qwen/Qwen3.5-397B-A17B
  • Qwen/Qwen3.5-9B
  • Qwen/Qwen3.6-27B
  • Qwen/Qwen3.6-35B-A3B
  • stepfun-ai/Step-3.7-Flash
  • thinkingmachines/Inkling
  • zai-org/AutoGLM-Phone-9B-Multilingual
  • zai-org/GLM-4.5V
  • zai-org/GLM-4.6V-Flash

Text-to-Image Models​

Text-to-image models (vision models) generate images from text prompts. These are used for creating visuals such as illustrations, product mockups, and creative assets. These models can be used within the Image Playground.

For the most up-to-date availability and pricing, see Vision Models Pricing.

Click to expand list of text-to-image models
Availability varies

The models available can change at any time. For the models currently available and up-to-date pricing, see Vision Models Pricing in AI Studio.

  • CogView4-6B
  • FLUX.1-dev
  • FLUX.1-Krea-dev
  • FLUX.1-schnell
  • GLM-Image
  • HiDream-I1-Fast
  • HiDream-I1-Full
  • HunyuanImage-3.0
  • Hyper-SD
  • LongCat-Image
  • Qwen-Image
  • Qwen-Image-2512
  • SRPO
  • stable-diffusion-3.5-large
  • stable-diffusion-3.5-large-turbo
  • stable-diffusion-3.5-medium
  • Z-Image-Turbo

Image-to-Image Models​

Image-to-image models (vision models) transform or edit existing images using an input image and optional prompts. These are used for workflows such as style transfer, image enhancement, and guided edits. These models can be used within the Image Playground.

For the most up-to-date availability and pricing, see Vision Models Pricing.

Click to expand list of image-to-image models
Availability varies

The models available can change at any time. For the models currently available and up-to-date pricing, see Vision Models Pricing in AI Studio.

  • FLUX.1-Kontext-dev
  • FLUX.2-dev
  • LongCat-Image-Edit
  • Qwen-Image-Edit
  • Qwen-Image-Edit-2511

Managing Models​

Models can be accessed and managed directly from the Base Models tab on the Model Catalog page of AI Studio. Here, you can explore detailed information about each model, view pricing (cost per 1 million tokens for text and image-to-text models, cost per 16×16 patch for image generation), and more. Each model is labeled with its modality, and you can filter the catalog by modality.

Model Catalog - Base ModelsModel Catalog - Base Models

Pricing​

Models are billed through AI Studio and appear in its unified billing system. You can view pricing and billing information by clicking View Model Details for any model.

Pricing depends on what the model generates, not on whether it processes images:

  • Text-to-Text and Image-to-Text Models generate text and are billed per token. Image-to-text models are vision-language models: they accept an image as input, which is included in your input tokens, and return a text response.

    • Cost per 1 million input tokens
    • Cost per 1 million output tokens

  • Text-to-Image and Image-to-Image Models generate images and are billed per patch.

    • Cost per 16×16 patch, where 1 patch = 256 pixels (a 16×16 pixel region) of generated image output. See the Vision Models Pricing page for the most up-to-date per-model pricing.

Pricing is subject to change. For the most up-to-date pricing, refer to the Base Models Pricing page in AI Studio. For more details on billing within AI Studio, click here.

On this page