Skip to content
HIPS
  • Earn with your GPU
  • Pricing
  • Docs
Sign inJoin early access
01The catalog, filed by task_

Find the model that fits the task

A useful catalog starts with what you want to do. We’re preparing a curated collection of open-weight models across language, image, audio, video, and specialist tasks.

Explore by capability, compare the details that affect your application, and move into the playground when you are ready to try an input.

Join early accessDeploy your model

We are inviting early-access interest while we develop the platform.

  1. 02The catalog, by capability
  2. 03Every model page
  3. 04Your examples first
Sheet01 of 04

The catalog

02The catalog, by capability_
  • Language

    When your product needs responses or summaries.

  • Image

    For visual workflows.

  • Audio

    For speech tasks.

  • Video

    For visual workflows.

  • Specialist

    When a focused decision or classification is the right output.

Loading the catalog

More than a model name

Each model page will explain the supported task, input and output formats, relevant limits, model version, and billing units. Where a model has specific licensing or usage conditions, those belong alongside the practical details.

For language models, see input and output token pricing separately. For classification, compare a defined task at a price per 1,000 classifications. For media, understand how dimensions, duration, or other supported settings affect the charge.

03Every model page_

Your task comes first

Look for language models when your product needs responses or summaries. Explore image and video models for visual workflows. Use audio models for speech tasks, and specialist models when a focused decision or classification is the right output.

A model’s size alone does not tell you whether it is right for your application. The catalog should help you evaluate its behavior, constraints, and cost with your own examples.

04Your examples first_

Have a model already

Already have a model trained for your application? Bring its requirements to HIPS and explore the route from your weights to inference.

Deploy your model

Product

  • Inference
  • Models
  • Deploy your model
  • Always-on GPU capacity
  • How it works
  • Use cases
  • Pricing

Developer

  • Docs
  • Quickstart
  • Migrate to HIPS
  • HIPS SDK
  • Batch jobs
  • API reference

Provider

  • Earn with your GPU
  • Register GPU interest
  • Download for Mac
  • Download for Windows
  • Download for Linux

Resource

  • Security and Data
  • Resources
  • llms.txt

Compare

  • OpenRouter alternatives
  • Together AI alternatives
  • Groq alternatives
  • All comparisons

Company

  • About
  • Contact
  • Affiliate program
  • HIPS Payments

Legal

  • Legal
  • Consumer Health Data Privacy Policy
  • Report content
  • Cookie preferences

Support

  • Contact HIPS
  • Looking for payments support?

HIPS. AI inference for builders.

hips.com

Hyperscale Inference Processing Systems OÜ

Capability
  • DeepSeek: DeepSeek V4.1 FlashIn early access
    deepseek-v4.1-flash
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 1,048,576
    Model version
    1 (deepseek-v4.1-flash-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $0.098 / $0.70 per million tokens

  • DeepSeek: DeepSeek V4.1 Flash 1017In early access
    deepseek-v4.1-flash-1017
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 1,048,576
    Model version
    1 (deepseek-v4.1-flash-1017-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    mit
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $0.098 / $0.70 per million tokens

  • DeepSeek: DeepSeek V4 Flash 0423In early access
    deepseek-v4-flash-0423
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 1,048,576
    Model version
    1 (deepseek-v4-flash-0423-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    mit
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $0.098 / $0.196 per million tokens

  • DeepSeek: DeepSeek V4 Flash 0731In early access
    deepseek-v4-flash-0731
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 1,048,576
    Model version
    1 (deepseek-v4-flash-0731-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    mit
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $0.098 / $0.196 per million tokens

  • DeepSeek: DeepSeek V4 ProIn early access
    deepseek-v4-pro
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 393,216
    Model version
    1 (deepseek-v4-pro-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    mit
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $0.70 / $2.80 per million tokens

  • DeepSeek: DeepSeek V4 Pro 0813In early access
    deepseek-v4-pro-0813
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 393,216
    Model version
    1 (deepseek-v4-pro-0813-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    mit
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $0.70 / $2.80 per million tokens

  • gemma 4 31B itIn early access
    gemma-4-31b-it
    Supported task
    Chat
    Input and output formats
    text, image in; text out
    Relevant limits
    Context tokens: 262,144; Max output tokens: 32,768
    Model version
    842da379 (gemma-4-31b-it-842da379)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code, OpenCode and Claude Code: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.1372 / $0.392 per million tokens

  • gemma 4 E4B itIn early access
    gemma-4-e4b-it-8b
    Supported task
    Chat
    Input and output formats
    text, image in; text out
    Relevant limits
    Context tokens: 131,072; Max output tokens: 32,768
    Model version
    4ecc2ba6 (gemma-4-e4b-it-8b-4ecc2ba6)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code, Claude Code and Codex: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.03234 / $0.09604 per million tokens

  • Z.ai: GLM 5.2In early access
    glm-5.2
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 131,072
    Model version
    1 (glm-5.2-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    mit
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $1.05 / $3.36 per million tokens

  • Z.ai: GLM 5.3In early access
    glm-5.3
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 131,072
    Model version
    1 (glm-5.3-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    glm-5.3
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $1.05 / $3.36 per million tokens

  • Z.ai: GLM 5.3 FlashIn early access
    glm-5.3-flash
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 131,072
    Model version
    1 (glm-5.3-flash-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    mit
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $0.105 / $0.70 per million tokens

  • gpt oss 120bIn early access
    gpt-oss-120b
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 131,072; Max output tokens: 32,768
    Model version
    b5c939de (gpt-oss-120b-b5c939de)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Supported by its template, not tested yet
    Coding agents
    HIPS Code, OpenCode and Claude Code: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.0294 / $0.147 per million tokens

  • gpt oss 20bIn early access
    gpt-oss-20b
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 131,072; Max output tokens: 32,768
    Model version
    6cee5e81 (gpt-oss-20b-6cee5e81)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Supported by its template, not tested yet
    Coding agents
    HIPS Code, Claude Code and Codex: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.01764 / $0.0882 per million tokens

  • granite 4.2 8bIn early access
    granite-4.2-8b
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 131,072; Max output tokens: 32,768
    Model version
    a7042144 (granite-4.2-8b-a7042144)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code, Claude Code and Codex: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.0588 / $0.147 per million tokens

  • MoonshotAI: Kimi K3In early access
    kimi-k3
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 1,048,576
    Model version
    1 (kimi-k3-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    kimi-k3
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $2.80 / $19.60 per million tokens

  • MoonshotAI: Kimi K3.1 ProIn early access
    kimi-k3.1-pro
    Supported task
    Chat
    Relevant limits
    Context tokens: 1,048,576; Max output tokens: 1,048,576
    Model version
    1 (kimi-k3.1-pro-1)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    kimi-k3.1-pro
    Tool calls
    No
    Coding agents
    No
    Batch
    Not offered

    from $2.24 / $15.68 per million tokens

  • Mistral Nemo Instruct 2407In early access
    mistral-nemo-instruct-2407-12b
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 131,072; Max output tokens: 32,768
    Model version
    04d8a905 (mistral-nemo-instruct-2407-12b-04d8a905)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Supported by its template, not tested yet
    Coding agents
    HIPS Code and OpenCode: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.01764 / $0.04 per million tokens

  • North Mini Code 1.0In early access
    north-mini-code-1.0-30b
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 500,000; Max output tokens: 32,768
    Model version
    d11e61a8 (north-mini-code-1.0-30b-d11e61a8)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Supported by its template, not tested yet
    Coding agents
    HIPS Code, OpenCode, Claude Code and Codex: meets the requirements, not tested yet
    Batch
    Not offered

    The price for this model is not published yet.

  • Qwen2.5 7B InstructIn early access
    qwen2.5-7b-instruct
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 32,768; Max output tokens: 32,768
    Model version
    a09a3545 (qwen2.5-7b-instruct-a09a3545)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code and Claude Code: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.098 / $0.196 per million tokens

  • Qwen3 14BIn early access
    qwen3-14b
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 40,960; Max output tokens: 32,768
    Model version
    40c06982 (qwen3-14b-40c06982)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code and OpenCode: meets the requirements, not tested yet
    Batch
    Offered

    from $0.098 / $0.2156 per million tokens

  • Qwen3 235B A22B Instruct 2507 FP8In early access
    qwen3-235b-a22b-instruct-2507-fp8
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 262,144; Max output tokens: 32,768
    Model version
    e156cb4e (qwen3-235b-a22b-instruct-2507-fp8-e156cb4e)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Supported by its template, not tested yet
    Coding agents
    HIPS Code, OpenCode, Claude Code and Codex: meets the requirements, not tested yet
    Batch
    Not offered

    The price for this model is not published yet.

  • Qwen3 30B A3B Instruct 2507 FP8In early access
    qwen3-30b-a3b-instruct-2507-fp8
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 262,144; Max output tokens: 32,768
    Model version
    5a5a7763 (qwen3-30b-a3b-instruct-2507-fp8-5a5a7763)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code, OpenCode, Claude Code and Codex: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.0882 / $0.294 per million tokens

  • Qwen3 32BIn early access
    qwen3-32b
    Supported task
    Chat
    Input and output formats
    text in; text out
    Relevant limits
    Context tokens: 40,960; Max output tokens: 32,768
    Model version
    9216db57 (qwen3-32b-9216db57)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code, OpenCode, Claude Code and Codex: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.0784 / $0.2744 per million tokens

  • Qwen3.6 40B Uncensored ThinkingIn early access
    qwen3.6-40b-uncensor
    Supported task
    Chat
    Input and output formats
    text, image in; text out
    Relevant limits
    Context tokens: 262,144; Max output tokens: 32,768
    Model version
    bc23dff6 (qwen3.6-40b-uncensor-bc23dff6)
    Billing units
    Input tokens, cached input tokens and output tokens
    Licensing or usage conditions
    apache-2.0
    Tool calls
    Validated
    Coding agents
    HIPS Code and Claude Code: meets the requirements, not tested yet
    Batch
    Not offered

    from $0.196 / $2.94 per million tokens