Skip to content
New GreenPT Code: glm-5.2 and kimi-k2.7-code now available GreenPT Code: glm-5.2 + kimi-k2.7-code
Create account
Aerial view of a still lake ringed by lush green forest.

Models

Every model, one efficient API

Open-weight language, reasoning, coding, vision, embedding, and speech models, all hosted by us on 100% renewable energy and tuned to run efficiently. One catalog, one key, the lowest energy use that still does the job.

Create an account 14-day free trial (opens in a new tab) See the full catalog (opens in a new tab)

The catalog

Every model, by category

Open-weight models run on 100% renewable energy with industry-leading efficiency, reachable through one OpenAI-compatible API and a single key.

Chat & language

GreenPT-branded open-weight models for everyday chat, reasoning, and writing, tuned for European languages.

  • Google Gemma 4 256K

    gemma4

    Multimodal reasoning with a long context window for documents and rich prompts.

    • Vision
    • Reasoning
    • Long context
    Input
    €0.50
    Output
    €1.50

    per 1M tokens

  • GPT-OSS

    green-r

    Advanced reasoning, writing, and multimodal understanding with GreenPT guardrails.

    • Reasoning
    • Vision
    Input
    €0.35
    Output
    €0.95

    per 1M tokens

  • Mistral Small 3.2 24B

    green-l

    Fast multilingual model with Dutch grammar guardrails for European workloads.

    • Multilingual
    • Functions
    Input
    €0.25
    Output
    €0.80

    per 1M tokens

Foundation models

Open-weight foundation models we host ourselves, tuned to run at the lowest energy use for each task.

  • Qwen 250K

    qwen3.5-397b-a17b

    Large mixture-of-experts model for code generation and agentic tasks.

    • Code
    • Agentic
    • Functions
    Input
    €0.70
    Output
    €4.35

    per 1M tokens

  • OpenAI 128K

    gpt-oss-120b

    Open-weight 120B model with vision and long-context reasoning.

    • Vision
    • Reasoning
    Input
    €0.20
    Output
    €0.70

    per 1M tokens

  • Mistral 128K

    mistral-small-3.2-24b-instruct-2506

    Efficient instruct model with function calling and vision.

    • Functions
    • Vision
    Input
    €0.20
    Output
    €0.40

    per 1M tokens

  • Google 40K

    gemma-3-27b-it

    Compact multimodal model for general reasoning and instruction-following.

    • Vision
    • Reasoning
    Input
    €0.30
    Output
    €0.60

    per 1M tokens

  • Meta 100K

    llama-3.3-70b-instruct

    Multilingual instruction-following at 70B for broad general use.

    • Multilingual
    Input
    €1.10
    Output
    €1.10

    per 1M tokens

  • Mistral 256K

    mistral-medium-3.5-128b

    Frontier-class reasoning, coding, and vision with a long context window.

    • Reasoning
    • Code
    • Vision
    Input
    €1.80
    Output
    €9.00

    per 1M tokens

Coding

Models tuned for code generation, completion, and agentic developer workflows.

  • Qwen 128K

    qwen3-coder-30b-a3b-instruct

    Code-specialised model for generation and completion across languages.

    • Code
    • Functions
    Input
    €0.25
    Output
    €0.95

    per 1M tokens

  • Mistral 200K

    devstral-2-123b-instruct-2512

    Large coding model for agentic software tasks and tool use.

    • Code
    • Agentic
    • Functions
    Input
    €0.50
    Output
    €2.40

    per 1M tokens

Audio & speech

Transcription and speech understanding, multilingual and accurate.

  • Mistral 32K

    voxtral-small-24b-2507

    Audio transcription and speech understanding in one model.

    • Audio
    Input
    €0.20
    Output
    €0.45

    per 1M tokens

  • GreenPT

    green-s

    Pre-recorded and live speech-to-text for general transcription.

    • Audio
    Recorded
    €0.52
    Live
    €0.65

    per hour

  • GreenPT

    green-s-pro

    Higher-accuracy transcription with multilingual options.

    • Audio
    • Multilingual
    Recorded
    €0.52
    Live
    €0.78

    per hour

Embeddings & retrieval

Vectors and reranking for semantic search and RAG pipelines.

  • Qwen3-Embedding-4B

    green-embedding

    Multilingual embeddings up to 2560 dimensions for semantic search and RAG.

    • Embeddings
    • Multilingual
    Price
    €0.20

    per 1M tokens

  • Qwen3-Reranker-4B

    green-rerank

    Reorders retrieved documents by true relevance, the last mile of search.

    • Reranking
    Price
    €0.12

    per 1M tokens

On the way

Coming soon

New open-weight models joining the catalog. Pricing and benchmark scores are provisional and may change at launch.

Coming soon

New open-weight models joining the catalog. Pricing and benchmarks are provisional and may change at launch.

  • z-ai New 1M

    z-ai/glm-5.2

    High-intelligence reasoning model with a 1M-token context window.

    Intel
    51.1
    Coding
    50.7
    • Functions
    • Tool Choice
    • Reasoning
    Input
    $1.50
    Cache
    $0.38
    Output
    $4.50

    per 1M tokens

  • minimax New 1M

    minimax/minimax-m3

    Agentic multimodal model with strong tool use and a 1M-token context.

    Intel
    44.4
    Coding
    43.4
    Agentic
    89%
    • Functions
    • Tool Choice
    • Reasoning
    • Vision
    Input
    $0.40
    Cache
    $0.10
    Output
    $2.00

    per 1M tokens

  • deepseek New 1M

    deepseek/deepseek-v4-pro

    Flagship DeepSeek model for coding and agentic tasks with a 1M-token context.

    Intel
    44.3
    Coding
    47.5
    Agentic
    96%
    • Functions
    • Tool Choice
    • Reasoning
    Input
    $1.75
    Cache
    $0.44
    Output
    $3.50

    per 1M tokens

  • moonshotai New 256K

    moonshotai/kimi-k2.6

    Agentic multimodal model with vision and a 256K-token context.

    Intel
    42.8
    Coding
    47.1
    Agentic
    96%
    • Functions
    • Tool Choice
    • Reasoning
    • Vision
    Input
    $1.00
    Cache
    $0.25
    Output
    $4.00

    per 1M tokens

  • moonshotai New 256K

    moonshotai/kimi-k2.7-code

    Code-focused Kimi variant with vision and a 256K-token context.

    Intel
    41.9
    Coding
    45.8
    • Functions
    • Tool Choice
    • Reasoning
    • Vision
    Input
    $1.25
    Cache
    $0.31
    Output
    $4.50

    per 1M tokens

  • deepseek New 1M

    deepseek/deepseek-v4-flash

    Low-cost, high-throughput DeepSeek model with a 1M-token context.

    Intel
    40.3
    Coding
    38.7
    Agentic
    95%
    • Functions
    • Tool Choice
    • Reasoning
    Input
    $0.15
    Cache
    $0.04
    Output
    $0.30

    per 1M tokens

Models, in short

How do I choose a model?

Pick by capability and budget. Every model is open-weight and hosted by us, so you can match the smallest model that handles your task and get strong results at the lowest energy use and cost.

Why are these models more efficient?

They are open-weight and run on 100% renewable energy in data centres with a PUE of 1.25 and a WUE of 0.25, well below the industry averages of 1.55 and 1.8. Lighter, quantised models and automatic routing mean each request uses the least compute that still does the job.

How is pricing calculated?

Most models are priced per million input and output tokens; speech models are priced per hour of audio. Prices are listed on each card and in the API docs.

See the full catalog →
What are the coming-soon models?

New open-weight models being added to the catalog. Their pricing and benchmark scores are provisional and may change at launch.

How do I call a model?

Through the OpenAI-compatible API: set the base URL and key, then pass the model id. One key covers every model, plus embeddings, reranking, OCR, speech, scraping, and search.

Read the API docs →

See the difference

One key for every model.

Start a free 14-day trial, no credit card. Call any model through one OpenAI-compatible API, hosted by us on 100% renewable energy and tuned for the lowest energy use from the first request.

Create an account 14-day free trial (opens in a new tab) See the full catalog

No credit card required.

  • 100% Renewable
  • PUE 1.25
  • Open-weight