Models

Full GreenPT model catalog, GreenPT-branded models, direct provider chat models, embeddings, speech-to-text, and reranking.

Full GreenPT model catalog, including GreenPT-branded models, direct provider chat models, embeddings, speech-to-text, and reranking.

Catalog Notes

All models are served through the GreenPT API proxy with an OpenAI-compatible interface. Prices are in EUR per million tokens unless noted otherwise, and API pricing applies to API usage only.

Get Models

List available models and their capabilities.

GET /v1/models

Endpoint: https://api.greenpt.ai/v1/models

Example request

curl https://api.greenpt.ai/v1/models \
  -H "Authorization: Bearer sk-your_api_key"

Example response

{
  "object": "list",
  "data": [
    { "id": "green-r",       "object": "model", "created": 0, "owned_by": "greenpt"  },
    { "id": "green-r-raw",   "object": "model", "created": 0, "owned_by": "greenpt"  },
    { "id": "green-l",       "object": "model", "created": 0, "owned_by": "greenpt"  },
    { "id": "green-l-raw",   "object": "model", "created": 0, "owned_by": "greenpt"  },
    { "id": "mistral-small-3.2-24b-instruct-2506", "object": "model", "created": 0, "owned_by": "mistral" },
    { "id": "gpt-oss-120b",  "object": "model", "created": 0, "owned_by": "openai"   },
    { "id": "gemma-3-27b-it","object": "model", "created": 0, "owned_by": "google"   },
    { "id": "gemma4",        "object": "model", "created": 0, "owned_by": "greenpt"  }
  ]
}

GreenPT Models

GreenPT-branded chat models with tuned system prompts or raw variants for direct control. gemma4 is the recommended default for chat completions.

gemma4GreenPTRecommendedPreview

Backed by Google Gemma 4 31B

GreenPT-branded next-generation chat model with long-context multimodal reasoning. Recommended default for chat completions.

Input€0.50

Output€1.50

Billingper 1M tokens

Context256k

Max output32k

ChatMultimodal reasoningLong-contextDefault model

green-rGreenPT

Backed by GPT-OSS

GreenPT-branded reasoning model for advanced analysis, writing, and content generation.

Input€0.35

Output€0.95

Billingper 1M tokens

TextImagesDocumentsMultilingualAdvanced reasoningWriting & content generation

green-r-rawGreenPT

Backed by GPT-OSS

Direct access to the same reasoning stack as green-r without the GreenPT system prompt.

Input€0.35

Output€0.95

Billingper 1M tokens

TextImagesDocumentsMultilingualNo system prompt

green-lGreenPT

Backed by Mistral Small 3.2 24B

GreenPT-branded chat model tuned for multilingual writing, image understanding, and Dutch grammar guardrails.

Input€0.25

Output€0.80

Billingper 1M tokens

TextImagesDocumentsMultilingualWriting assistantDutch grammar guardrails

green-l-rawGreenPT

Backed by Mistral Small 3.2 24B

Direct access to the same GreenPT-backed model as green-l without the built-in system prompt.

Input€0.25

Output€0.80

Billingper 1M tokens

TextImagesDocumentsMultilingualNo system prompt

Raw vs Non-Raw

Non-raw models like green-r and green-l include GreenPT's Sustainability system prompt, optimized for our use cases. Raw models like green-r-raw and green-l-raw do not include a system prompt, so you can supply your own via the API.

Green Router Models

Direct access to foundation models without a GreenPT system prompt, served through Green Router.

qwen3.5-397b-a17bQwenRecommendedNew

State-of-the-art Qwen model optimized for code generation, agentic tasks, and logical reasoning.

Input€0.66

Output€3.96

Billingper 1M tokens

Context250k

Max output16k

ChatCode generationAgentic tasksLogical reasoningState-of-the-art (March 2026)

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

General-purpose model with balanced cost, function calling, and multimodal chat support.

Input€0.15

Output€0.35

Billingper 1M tokens

Context128k

Max output32k

ChatVisionFunction callingMultilingual

gpt-oss-120bOpenAI

Large open model with vision, function calling, and long-context reasoning support.

Input€0.15

Output€0.60

Billingper 1M tokens

Context128k

Max output32k

ChatVisionLong-context reasoningFunction calling

gemma-3-27b-itGoogle

Multimodal reasoning model from Google for chat and image-aware tasks.

Input€0.25

Output€0.50

Billingper 1M tokens

Context40k

Max output8k

ChatVisionMultimodal reasoning

qwen3-235b-a22b-instruct-2507Qwen

High-context multilingual reasoning model with a 250k token window.

Input€0.75

Output€2.25

Billingper 1M tokens

Context250k

Max output16k

ChatLong-contextReasoningMultilingual250k context window

qwen3-coder-30b-a3b-instructQwenCoding

Qwen coding model built for generation, completion, and debugging workflows.

Input€0.20

Output€0.80

Billingper 1M tokens

Context128k

Max output32k

ChatCode generationCompletionDebugging

devstral-2-123b-instruct-2512MistralCoding

Mistral coding model for multi-file reasoning and agentic software engineering tasks.

Input€0.60

Output€2.35

Billingper 1M tokens

Context200k

Max output16k

Code generationMulti-file reasoningAgentic coding tasks200k context

llama-3.3-70b-instructMeta

Meta instruction-following model with strong multilingual support for general chat use cases.

Input€0.90

Output€0.90

Billingper 1M tokens

Context100k

Max output16k

ChatInstruction followingMultilingual

llama-3.1-8b-instructMetaDeprecated

Fast, lightweight, and cost-efficient Meta model retained for compatibility.

Input€0.20

Output€0.20

Billingper 1M tokens

Context128k

Max output16k

ChatFast & lightweightCost-efficient inference

mistral-nemo-instruct-2407MistralDeprecated

Instruction-tuned multilingual Mistral model retained as a deprecated option.

Input€0.20

Output€0.20

Billingper 1M tokens

Context128k

Max output8k

ChatInstruction followingMultilingual

deepseek-r1-distill-llama-70bDeepSeekDeprecated

DeepSeek distilled reasoning model focused on math and code-heavy tasks.

Input€0.90

Output€0.90

Billingper 1M tokens

Context16k

Max output4k

Chain-of-thought reasoningMathCode

voxtral-small-24b-2507Mistral

Audio-aware chat model for transcription-adjacent and speech understanding use cases.

Input€0.15

Output€0.35

Billingper 1M tokens

Context32k

Max output16k

ChatAudio transcriptionSpeech understanding

Deprecated Chat Models

llama-3.1-8b-instruct, mistral-nemo-instruct-2407, and deepseek-r1-distill-llama-70b are deprecated as of January 2026 and remain available until EOL in April 2026.

Embedding Models

Dense vector embeddings for semantic search and retrieval workflows.

green-embeddingGreenPT

Backed by Qwen3-Embedding-4B

Dense multilingual embedding model for semantic search, retrieval, and RAG pipelines. Supports Matryoshka Representation Learning, so output dimensions are configurable from 32 up to 2560.

Input€0.20

OutputNo output charge

Billingper 1M tokens

Context32k

Dimensionsup to 2560

Dense embeddingsMultilingual (100+ languages)Semantic searchRAGMRL (custom dimensions)Instruction-aware

Speech-to-Text Models

Pre-recorded and live transcription models with optional multilingual support.

green-sGreenPT

Speech-to-text model for pre-recorded and live transcription.

Input€0.52/hr

Output€0.65/hr live

Billingaudio pricing

Pre-recorded transcriptionLive transcription

green-s-proGreenPTPro

Advanced speech-to-text model with multilingual transcription options.

Input€0.52/hr recorded

Output€0.78/hr live

Billingaudio pricing

Pre-recorded transcriptionLive transcriptionMultilingual input €0.60/hrMultilingual live €1.04/hr

Reranking Models

Models for document reranking and RAG result scoring.

green-rerankGreenPT

Backed by Qwen3-Reranker-4B

Cross-encoder reranking model that scores and reorders search or RAG results by relevance to a query.

Input€0.12

OutputNo output charge

Billingper 1M tokens

Context32k

Document rerankingRAG result scoringMultilingual (100+ languages)Instruction-aware

On this page