GreenPT Docs

Token Pricing

Transparent pricing for all AI models and services across input and output tokens.

Transparent pricing for all AI models and services across input and output tokens. Use the tabs below to switch between input-token and output-token pricing.

Language models

Chat completion and text generation models.

ModelDescriptionPrice / 1M tokens
GreenLLightweight, efficient language model.€0.25
GreenRReasoning-optimized language model.€0.35
gemma4Long-context multimodal model (256k). Public Preview.€0.50

Chat models

Direct provider chat models available through the GreenPT API proxy (per 1M input tokens).

ModelPrice / 1M
llama-3.3-70b-instruct€1.10
gemma-3-27b-it€0.30
devstral-2-123b-instruct-2512€0.50
qwen3-235b-a22b-instruct-2507€0.90
mistral-small-3.2-24b-instruct-2506€0.20
qwen3-coder-30b-a3b-instruct€0.25
qwen3.5-397b-a17b€0.70
qwen3.6-35b-a3b€0.30
mistral-medium-3.5-128b€1.80
gpt-oss-120b€0.20
voxtral-small-24b-2507€0.20

Vector & search models

Embedding and reranking services.

Note: embedding and reranking models only charge for input tokens. There are no output token costs for these services.

ModelDescriptionPrice / 1M tokens
Green EmbeddingText vectorization and semantic search.€0.20
qwen3-embedding-8bLarger multilingual embedding model.€0.25
Green RerankDocument reranking and relevance scoring.€0.12

Speech-to-text models

Audio transcription services (priced per second).

New pricing, now live: the per-hour model rates below are updated and in effect today. The add-on features are a separate launch promo and free for now.

Limited promo: 50% off (July & August 2026)

All speech-to-text model rates are half price through 31 August 2026. The promo column below shows the discounted rate.

ModelModeRegular ratePromo (Jul–Aug 2026, −50%)
GreenSPre-recorded audio (batch)€0.23 / hour€0.12 / hour
GreenSLive audio (real-time)€0.31 / hour€0.16 / hour
GreenS ProMonolingual: pre-recorded€0.23 / hour€0.12 / hour
GreenS ProMonolingual: live audio€0.31 / hour€0.16 / hour
GreenS ProMultilingual: pre-recorded€0.28 / hour€0.14 / hour
GreenS ProMultilingual: live audio€0.37 / hour€0.19 / hour

Additional features

Launch promo: the speech-to-text add-ons below are free right now. The prices shown are the standard per-hour rates that apply once the promo ends; you are not charged for them today.

FeatureRate (promo: free now)
Redaction€0.10 / hour
Entity detection€0.08 / hour
Streaming diarization (live audio)€0.10 / hour
Keyterm prompting€0.07 / hour

Speaker diarization is included free for pre-recorded audio. Multichannel audio is billed per channel, so 2-channel audio is charged at double the per-hour rate.

Language model completions

Generated text and chat responses.

ModelDescriptionPrice / 1M tokens
GreenLFast, efficient completions.€0.80
GreenRAdvanced reasoning completions.€0.95
gemma4Long-context multimodal completions. Public Preview.€1.50

Chat models

Direct provider chat models available through the GreenPT API proxy (per 1M output tokens).

ModelPrice / 1M
llama-3.3-70b-instruct€1.10
gemma-3-27b-it€0.60
devstral-2-123b-instruct-2512€2.40
qwen3-235b-a22b-instruct-2507€2.70
mistral-small-3.2-24b-instruct-2506€0.40
qwen3-coder-30b-a3b-instruct€0.95
qwen3.5-397b-a17b€4.35
qwen3.6-35b-a3b€1.80
mistral-medium-3.5-128b€9.00
gpt-oss-120b€0.70
voxtral-small-24b-2507€0.45

Note: embedding, reranking, and speech-to-text services don't generate output tokens. They're billed only on input. See the Input tokens tab.

Token usage examples

Understanding token consumption for different use cases.

GreenL usage examples

Use caseTokensCost
Short answer50€0.00004
Paragraph200€0.00016
Article1,000€0.0008
  • Short answer: brief responses, simple Q&A.
  • Paragraph: detailed explanations, summaries.
  • Article: long-form content, reports.

GreenR usage examples

Use caseTokensCost
Analysis50€0.0000475
Detailed report200€0.00019
Research paper1,000€0.00095
  • Analysis: complex reasoning, analysis.
  • Detailed report: in-depth analysis, research.
  • Research paper: academic content, detailed analysis.

Cost comparison

Input vs output token pricing.

ModelInput / 1MOutput / 1MOutput multiplier
GreenL€0.25€0.803.2×
GreenR€0.35€0.952.7×

Pricing notes

  • All prices are in EUR and exclude applicable taxes.
  • Token counting follows OpenAI-compatible standards.
  • Speech-to-text pricing is based on audio duration, not tokens.
  • Output tokens are typically priced higher than input tokens.
  • Embedding and reranking models only charge for input tokens (no output costs).
  • Volume discounts available for enterprise customers.
  • Prices subject to change with 30 days notice.

On this page