Transparent token economics

Pricing built for real usage conversations, not opaque AI spend.

Review list pricing by model group, compare input and output rates, and align teams on how model choice affects cost, context, and infrastructure posture.

Value that scales

Pay as you go
Simple 5% management fee
  • No committed monthly platform fee
  • Per-model input/output pricing
  • Public visibility into list rates
  • Volume based discounts available

User Led Optimisation

Granular usage feedback and budgeting controls empower users to manage their spend.

Visible trade-offs

Compare price with context window, infrastructure type, and model family in one place. Auto supplier error capture and redirect for higher uptime and less agentic flow disruption.

Enterprise-ready

Role based access, GDPR & ISO compliance, multi-provider for resilience.

Model group

Chat & Completion

Public list pricing for currently grouped models.

38 models
Model Family Context Infrastructure Pricing Unit Regions Status
Kimi K2.6
kimi-k2.6
chat 262K cloud $0.9 input / $4.00 output / MTok MTok πŸ‡¨πŸ‡³ SiliconFlow, πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ OpenRouter Live
GLM 5.1
glm-5.1
chat 200K cloud $1.4 input / $4.4 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡¨πŸ‡³ SiliconFlow Live
Minimax M2.7
minimax-m2.7
chat 204K cloud $0.4 input / $1.6 output / MTok MTok πŸ‡ΈπŸ‡¬ MiniMax Direct, πŸ‡ΊπŸ‡Έ OpenRouter Live
Hy3 Preview
hy3-preview
chat 262K cloud $0.066 input / $0.26 output / MTok MTok πŸ‡¨πŸ‡³ SiliconFlow, πŸ‡ΊπŸ‡Έ OpenRouter Live
Qwen3.5
qwen3.5
chat 262K cloud $0.39 input / $2.34 output / MTok MTok πŸ‡¨πŸ‡³ Alibaba DashScope, πŸ‡ΊπŸ‡Έ OpenRouter Live
Codestral
codestral
chat 256K cloud $0.3 input / $0.9 output / MTok MTok πŸ‡«πŸ‡· Mistral AI Live
Qwen3 235b
qwen3-235b
chat 256K cloud $0.0568 input / $0.08 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra Live
Gemini 2.5 Pro
gemini-2.5-pro
chat 1M cloud $1.25 input / $10.00 output / MTok MTok πŸ‡ΊπŸ‡Έ Google AI (Gemini), πŸ‡ΊπŸ‡Έ OpenRouter Live
Qwen 3 32b
qwen-3-32b
chat 40K cloud $0.064 input / $0.224 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra Live
Qwq 32b
qwq-32b
chat 40K cloud $0.064 input / $0.224 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra Live
Qwen 2.5 7b
qwen-2.5-7b
chat 33K cloud $0.048 input / $0.096 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra Live
Gemma 3 27b
gemma-3-27b
chat 128K cloud $0.064 input / $0.128 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra Live
Gemma 4 31b
gemma-4-31b
chat 256K cloud $0.12 input / $0.37 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ OpenRouter Live
Qwen3.5 Plus
qwen3.5-plus
chat 1M cloud $0.26 input / $1.56 output / MTok MTok πŸ‡¨πŸ‡³ Alibaba DashScope, πŸ‡ΊπŸ‡Έ OpenRouter Live
GLM 4.5 Air
glm-4.5-air
chat 128K cloud $0.05 input / $0.1 output / MTok MTok πŸ‡¨πŸ‡³ SiliconFlow Live
Llama 3.1 8b
llama-3.1-8b
chat 128K cloud $0.016 input / $0.04 output / MTok MTok πŸ‡ΊπŸ‡Έ Groq Live
Deepseek R1 70b
deepseek-r1-70b
chat 128K cloud $0.56 input / $0.64 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra Live
Llama 3.3 70b
llama-3.3-70b
chat 128K cloud $0.08 input / $0.256 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra Live
Llama 4 Scout
llama-4-scout
chat 320K cloud $0.064 input / $0.24 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ Groq Live
Magistral Medium
magistral-medium
chat 40K cloud $2.00 input / $5.00 output / MTok MTok πŸ‡«πŸ‡· Mistral AI Live
Mistral Small 24b
mistral-small-24b
chat 32K cloud $0.2 input / $0.6 output / MTok MTok πŸ‡«πŸ‡· Mistral AI Live
Qwen3 30b
qwen3-30b
chat 131K cloud $0.15 input / $0.75 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ Groq Live
Magistral Small
magistral-small
chat 40K cloud $0.5 input / $1.5 output / MTok MTok πŸ‡«πŸ‡· Mistral AI Live
Mistral Medium
mistral-medium
chat 131K cloud $1.5 input / $7.5 output / MTok MTok πŸ‡«πŸ‡· Mistral AI Live
Qwen 72b
qwen-72b
chat 33K cloud $0.6 input / $1.00 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡¨πŸ‡³ SiliconFlow, πŸ‡ΊπŸ‡Έ OpenRouter Live
GLM 4 Flash
glm-4-flash
chat 203K cloud $0.1 input / $0.6 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ OpenRouter Live
Qwen Coder 32b
qwen-coder-32b
chat 41K cloud $0.3 input / $0.9 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ Groq, πŸ‡ΊπŸ‡Έ OpenRouter Live
Minimax M2.5
minimax-m2.5
chat 197K cloud $0.4 input / $1.6 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡¨πŸ‡³ SiliconFlow, πŸ‡ΈπŸ‡¬ MiniMax Direct, πŸ‡ΊπŸ‡Έ OpenRouter Live
Deepseek Chat
deepseek-chat
chat 64K cloud $0.2 input / $0.6 output / MTok MTok πŸ‡¨πŸ‡³ DeepSeek, πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ OpenRouter Live
Claude Fable 5
claude-fable-5
chat 1M cloud $10.00 input / $50.00 output / MTok MTok πŸ‡ΊπŸ‡Έ Anthropic Corporate, πŸ‡ΊπŸ‡Έ OpenRouter Live
GPT 5.5 Pro
gpt-5.5-pro
chat 400K cloud $45.00 input / $270.00 output / MTok MTok πŸ‡ΊπŸ‡Έ OpenAI Corporate, πŸ‡ΊπŸ‡Έ OpenRouter Live
Claude Opus 4.8
claude-opus-4.8
chat 200K cloud $5.00 input / $25.00 output / MTok MTok πŸ‡ΊπŸ‡Έ Anthropic Corporate, πŸ‡ΊπŸ‡Έ OpenRouter Live
GPT 5.5
gpt-5.5
chat 400K cloud $1.75 input / $14.00 output / MTok MTok πŸ‡ΊπŸ‡Έ OpenAI, πŸ‡ΊπŸ‡Έ OpenAI Corporate, AWS Bedrock OpenAI, πŸ‡ΊπŸ‡Έ OpenRouter Live
Gemini 3.1 Pro Preview
gemini-3.1-pro-preview
chat 2M cloud $2.00 input / $12.00 output / MTok MTok πŸ‡ΊπŸ‡Έ Google AI (Gemini) Live
GPT 5.4
gpt-5.4
chat 1.1M cloud $1.75 input / $14.00 output / MTok MTok πŸ‡ΊπŸ‡Έ OpenAI, πŸ‡ΊπŸ‡Έ OpenRouter, πŸ‡ΊπŸ‡Έ OpenAI Corporate Live
Claude Sonnet 4.6
claude-sonnet-4.6
chat 1M cloud $3.00 input / $15.00 output / MTok MTok πŸ‡ΊπŸ‡Έ Anthropic Corporate, πŸ‡ΊπŸ‡Έ OpenRouter Live
Gemini 3.5 Flash
gemini-3.5-flash
chat 1M cloud $1.5 input / $9.00 output / MTok MTok πŸ‡ΊπŸ‡Έ Google AI (Gemini) Live
Gemini 3.1 Flash Lite
gemini-3.1-flash-lite
chat 1M cloud $0.25 input / $1.5 output / MTok MTok πŸ‡ΊπŸ‡Έ Google AI (Gemini) Live
Model group

Vision & Multimodal

Public list pricing for currently grouped models.

3 models
Model Family Context Infrastructure Pricing Unit Regions Status
Pixtral Large
pixtral-large
vision 128K cloud $2.00 input / $6.00 output / MTok MTok πŸ‡«πŸ‡· Mistral AI Live
Qwen2.5 VL 72b
qwen2.5-vl-72b
vision 33K cloud $0.4 input / $1.2 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡ΊπŸ‡Έ OpenRouter Live
Qwen3 VL
qwen3-vl
vision 262K cloud $0.25 input / $1.00 output / MTok MTok πŸ‡ΊπŸ‡Έ DeepInfra, πŸ‡¨πŸ‡³ SiliconFlow, πŸ‡ΊπŸ‡Έ OpenRouter Live
Model group

OCR & Documents

Public list pricing for currently grouped models.

7 models
Model Family Context Infrastructure Pricing Unit Regions Status
Mistral Ocr
mistral-ocr
ocr - cloud $2.00 / 1K Pages 1K Pages πŸ‡«πŸ‡· Mistral AI Live
Olmocr 2 7b Fp8
olmocr-2-7b-fp8
ocr 33K cloud $8.00 / 1K Pages 1K Pages OTE Greece, Athens OCR olmOCR Live
Paddleocr VL 1 6
paddleocr-vl-1-6
ocr 33K cloud $6.00 / 1K Pages 1K Pages OTE Greece, Athens OCR PaddleOCR-VL Live
Paddleocr V5
paddleocr-v5
ocr - cloud $1.00 / 1K Pages 1K Pages Athens OCR CPU Utilities, OTE Greece Live
Docling Granite 258m
docling-granite-258m
ocr - cloud $3.00 / 1K Pages 1K Pages OTE Greece, Athens OCR CPU Utilities Live
Paddleocr Structure V3
paddleocr-structure-v3
ocr - cloud $4.00 / 1K Pages 1K Pages Athens OCR CPU Utilities Live
Smoldocling 256m Preview
smoldocling-256m-preview
ocr - cloud $2.00 / 1K Pages 1K Pages Athens OCR CPU Utilities Live
Model group

Document Conversion

Public list pricing for currently grouped models.

3 models
Model Family Context Infrastructure Pricing Unit Regions Status
Docx Native Parser
docx-native-parser
document_conversion - cloud β€” / Request Request TaaS Gateway Live
Markitdown Text Preview
markitdown-text-preview
document_conversion - cloud β€” / Request Request TaaS Gateway Live
Markitdown Full Preview
markitdown-full-preview
document_conversion - cloud β€” / Request Request TaaS Gateway Live
Model group

Image Generation

Public list pricing for currently grouped models.

1 models
Model Family Context Infrastructure Pricing Unit Regions Status
GPT Image 2
gpt-image-2
image - cloud from $0.04 / Image Image πŸ‡ΊπŸ‡Έ OpenAI, πŸ‡ΊπŸ‡Έ OpenAI Corporate, AWS Bedrock OpenAI, πŸ‡ΊπŸ‡Έ OpenRouter Live
Model group

Embedding

Public list pricing for currently grouped models.

1 models
Model Family Context Infrastructure Pricing Unit Regions Status
BGE M3
bge-m3
embedding - sovereign $0.05 input / MTok MTok OTE Greece, CloudSigma Live
Model group

Reranking

Public list pricing for currently grouped models.

1 models
Model Family Context Infrastructure Pricing Unit Regions Status
BGE Reranker V2 M3
bge-reranker-v2-m3
reranker - sovereign $0.5 / 1K Rerank Pairs 1K Rerank Pairs OTE Greece, CloudSigma Live
Model group

Text-to-Speech

Public list pricing for currently grouped models.

2 models
Model Family Context Infrastructure Pricing Unit Regions Status
Kokoro
kokoro
tts - cloud $0.006 / 1K Characters 1K Characters OTE Greece Live
F5 TTS
f5-tts
tts - cloud $0.012 / 1K Characters 1K Characters OTE Greece Live
Model group

Transcription

Public list pricing for currently grouped models.

2 models
Model Family Context Infrastructure Pricing Unit Regions Status
Whisper
whisper
transcription - cloud $0.006 / Audio Minute Audio Minute OTE Greece, πŸ‡ΊπŸ‡Έ Groq Live
Whisper 1
whisper-1
transcription - cloud $0.006 / Audio Minute Audio Minute OTE Greece, πŸ‡ΊπŸ‡Έ Groq Live
Model group

Speaker Recognition

Public list pricing for currently grouped models.

3 models
Model Family Context Infrastructure Pricing Unit Regions Status
Ecapa Tdnn
ecapa-tdnn
speaker - cloud $0.0015 / Audio Minute Audio Minute OTE Greece Live
Xvector
xvector
speaker - cloud $0.0015 / Audio Minute Audio Minute OTE Greece Live
Wavlm Base Plus Sv
wavlm-base-plus-sv
speaker - cloud $0.0015 / Audio Minute Audio Minute OTE Greece Live
Model group

Audio Understanding

Public list pricing for currently grouped models.

3 models
Model Family Context Infrastructure Pricing Unit Regions Status
Clap
clap
audio - cloud $0.002 / Audio Minute Audio Minute OTE Greece Live
Ast
ast
audio - cloud $0.002 / Audio Minute Audio Minute OTE Greece Live
Mert
mert
audio - cloud $0.002 / Audio Minute Audio Minute OTE Greece Live

Transparent from day one

  • Public price list for planning
  • User and API Key level budgeting
  • Easy model-by-model comparison

Designed for internal governance

  • Support budget ownership conversations
  • Align technical and commercial trade-offs
  • Make cost visible before rollout

Need enterprise terms?

  • Higher-volume commercial discussions
  • Dedicated infrastructure pathways
  • Compliance and procurement alignment
Next step

Pick a model strategy with full visibility into price and platform fit.

Use the pricing tables with the public model catalog and API documentation to decide what your team should test, approve, and scale.