GreenPT Docs

Model Cards

Full GreenPT model catalog — chat, coding, embeddings, speech-to-text, and reranking — with pricing and relative energy efficiency.

Full GreenPT model catalog. Filter by category, compare pricing, and check each model's relative energy efficiency. To list models programmatically, see the Models API.

Catalog

glm-5.2z.aiNew
EfficiencyVery low

GreenPT Code flagship coding model with strong reasoning, agentic tool-use, and multi-file software engineering performance. See the GreenPT Code guide for IDE setup.

Input€1.32
Output€4.62
Billingper 1M tokens
Context1M
Tensor typeBF16 · F32
Released2026
Code generationAgentic coding tasksMulti-file reasoningTool use
minimax-m2.5MiniMax
EfficiencyModerate

MiniMax reasoning model optimized for agentic coding and long-horizon workflows.

Input€0.17
Output€0.99
Billingper 1M tokens
Context200k
Max output128k
Released2026
ChatReasoningAgentic codingLong-horizon tasks
kimi-k2.6Moonshot AI
EfficiencyLow

Moonshot Kimi K2.6 reasoning model with strong agentic coding and multimodal input.

Input€0.73
Output€3.85
Billingper 1M tokens
Context256k
Max output256k
Released2026
ChatReasoningAgentic codingVision
kimi-k2.7-codeMoonshot AI
EfficiencyLow

Moonshot Kimi K2.7 Code, tuned for software engineering and agentic coding tasks.

Input€0.83
Output€3.85
Billingper 1M tokens
Context256k
Max output256k
Released2026
ChatReasoningCodingAgentic tasks
gemma4GreenPT
EfficiencyHighBacked by Google Gemma 4

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
Released2026
ChatMultimodal reasoningLong-contextDefault model
green-rGreenPT
EfficiencyHighBacked by GPT-OSS

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

Input€0.35
Output€0.95
Billingper 1M tokens
ReleasedAug 2025
TextImagesDocumentsMultilingualAdvanced reasoningWriting & content generation
green-r-rawGreenPT
EfficiencyHighBacked 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
ReleasedAug 2025
TextImagesDocumentsMultilingualNo system prompt
green-lGreenPT
EfficiencyHighBacked 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
ReleasedJun 2025
TextImagesDocumentsMultilingualWriting assistantDutch grammar guardrails
green-l-rawGreenPT
EfficiencyHighBacked 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
ReleasedJun 2025
TextImagesDocumentsMultilingualNo system prompt
qwen3.5-397b-a17bQwen
EfficiencyVery low

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

Input€0.70
Output€4.35
Billingper 1M tokens
Context250k
Max output16k
ReleasedMar 2026
ChatCode generationAgentic tasksLogical reasoningState-of-the-art (March 2026)
mistral-small-3.2-24b-instruct-2506Mistral
EfficiencyHigh

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

Input€0.20
Output€0.40
Billingper 1M tokens
Context128k
Max output32k
ReleasedJun 2025
ChatVisionFunction callingMultilingual
gpt-oss-120bOpenAI
EfficiencyModerate

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

Input€0.20
Output€0.70
Billingper 1M tokens
Context128k
Max output32k
ReleasedAug 2025
ChatVisionLong-context reasoningFunction calling
gemma-3-27b-itGoogle
EfficiencyHigh

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

Input€0.30
Output€0.60
Billingper 1M tokens
Context40k
Max output8k
ReleasedMar 2025
ChatVisionMultimodal reasoning
qwen3-235b-a22b-instruct-2507Qwen
EfficiencyModerate

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

Input€0.90
Output€2.70
Billingper 1M tokens
Context250k
Max output16k
ReleasedJul 2025
ChatLong-contextReasoningMultilingual250k context window
qwen3-coder-30b-a3b-instructQwen
EfficiencyHigh

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

Input€0.25
Output€0.95
Billingper 1M tokens
Context128k
Max output32k
ReleasedJul 2025
ChatCode generationCompletionDebugging
devstral-2-123b-instruct-2512Mistral
EfficiencyLow

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

Input€0.50
Output€2.40
Billingper 1M tokens
Context200k
Max output16k
ReleasedDec 2025
Code generationMulti-file reasoningAgentic coding tasks200k context
llama-3.3-70b-instructMeta
EfficiencyModerate

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

Input€1.10
Output€1.10
Billingper 1M tokens
Context100k
Max output16k
ReleasedDec 2024
ChatInstruction followingMultilingual
qwen3.6-35b-a3bQwen
EfficiencyHigh

Frontier small Qwen model optimized for agentic and reasoning tasks across many languages.

Input€0.30
Output€1.80
Billingper 1M tokens
Context256k
Max output32k
Released2026
ChatCodeVisionAgentic & reasoning tasks
mistral-medium-3.5-128bMistral
EfficiencyLow

Unified Mistral model with strong instruct, reasoning, coding, and vision performance.

Input€1.80
Output€9.00
Billingper 1M tokens
Context256k
Max output16k
Released2026
ChatVisionReasoningCoding
voxtral-small-24b-2507Mistral
EfficiencyHigh

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

Input€0.20
Output€0.45
Billingper 1M tokens
Context32k
Max output16k
ReleasedJul 2025
ChatAudio transcriptionSpeech understanding
green-embeddingGreenPT
EfficiencyVery highBacked 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
ReleasedJun 2025
Dense embeddingsMultilingual (100+ languages)Semantic searchRAGMRL (custom dimensions)Instruction-aware
qwen3-embedding-8bScaleway
EfficiencyVery highBacked by Qwen3-Embedding-8B

State-of-the-art multilingual embedding model for semantic search, retrieval, and RAG pipelines. Supports Matryoshka Representation Learning, so output dimensions are configurable from 32 up to 4096.

Input€0.25
OutputNo output charge
Billingper 1M tokens
Context32k
Dimensionsup to 4096
Released2026
Dense embeddingsMultilingual (100+ languages)Semantic searchRAGMRL (custom dimensions)Instruction-aware
green-sGreenPT
EfficiencyHigh

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

Input€0.52/hr
Output€0.65/hr live
Billingaudio pricing
Released2025
Pre-recorded transcriptionLive transcription
green-s-proGreenPTPro
EfficiencyHigh

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

Input€0.52/hr recorded
Output€0.78/hr live
Billingaudio pricing
Released2025
Pre-recorded transcriptionLive transcriptionMultilingual input €0.60/hrMultilingual live €1.04/hr
green-rerankGreenPT
EfficiencyVery highBacked 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
ReleasedJun 2025
Document rerankingRAG result scoringMultilingual (100+ languages)Instruction-aware

Energy efficiency

The green Efficiency meter on each card is a relative estimate (1–5 bullets, more filled = more efficient) derived from the power draw of the hardware serving the model — smaller models need fewer GPUs and run greener. It is indicative, not a measured per-request figure; see Carbon calculations for our measurement methodology.

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.

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.

On this page