Prices, per million tokens.

ModelContextLicenceInputCachedOutput
Chat and reasoning
DeepSeek V4 FlashDeepSeek · deepseek-v4-flash256KMIT€0.037€0.0015€0.254
DeepSeek V4.1 FlashDeepSeek · deepseek-v4.1-flash1MMIT€0.117€0.005€0.47
Gemma 4 12BGoogle · gemma-4-12b128KApache-2.0€0.06€0.006€0.172
Gemma 4 31BGoogle · gemma-4-31b256KApache-2.0€0.11€0.011€0.313
GLM 5.3 FlashZ.ai · glm-5.3-flash1MMIT€0.117€0.026€0.392
Mistral Small 4Mistral AI · mistral-small-4-119b256KApache-2.0€0.117€0.013€0.47
Qwen 3.8 27BAlibaba · qwen3.8-27b256KApache-2.0€0.243€0.0243€2.00
Documents and OCR
NuExtract 3NuMind · nuextract-332KApache-2.0€0.15€0.015€0.40
PaddleOCR VL 1.6Baidu · paddleocr-vl-1.616KApache-2.0€0.313€0.0313€1.25
Embeddings and reranking
BGE M3BAAI · bge-m38KMIT€0.008––
Qwen3 Embedding 8BAlibaba · qwen3-embedding-8b8KApache-2.0€0.008––
Qwen3 Reranker 8BAlibaba · qwen3-reranker-8b8KApache-2.0€0.157––
Speech-to-text
Qwen3 ASR 1.7BAlibaba · qwen3-asr-1.7b–Apache-2.0€0.0004/ min––
Whisper Large v3OpenAI · whisper-large-v3–Apache-2.0€0.0015/ min––
Whisper Large v3 TurboOpenAI · whisper-large-v3-turbo–MIT€0.0005/ min––
Moderation
Qwen3Guard 4BAlibaba · qwen3guard-gen-4b16KApache-2.0€0.141€0.0141€0.141

Euro per million tokens, excluding VAT; speech-to-text per minute of audio. Cached is the price for input the model has already processed, such as a repeated system prompt. Prices in effect on 16 November 2026; the console always shows the current price.

Pay for what you use.

Prepaid credit

You top up a balance in the console and usage is deducted from it. Top up by hand, or automatically when the balance runs low. Online payments are handled by Mollie.

Invoicing

Business customers can be invoiced monthly instead, by agreement. Write to hello@euown.ai.

Refunds

Consumers can withdraw from a credit purchase within 14 days and get the unused part back. The details are in the Terms of Service.

Stay in the loop. Only what matters.

New models and new prices, by e-mail.

Thank you. You are on the list.