All tools
Organised by the question you are trying to answer, not by feature.
Which model should I use?
Model picker
Three questions, get Flash or V4 Pro
Flash vs V4 Pro
Price multiples, specs, use cases
Flash details
Specs, per-call cost, comparisons
V4 Pro details
Specs, per-call cost, use cases
What will it cost?
Cost calculator
Monthly cost from your token volume
Token estimator
Paste text, get tokens and cost
Off-peak guide
Halve your bill by scheduling
Price list
Peak, off-peak, cache, Search
Which provider is cheapest?
DeepSeek providers
45 providers, widest spread 18x
V4.1 Flash 1017
All 45 quotes with quantization
All DeepSeek models
13 models, price ranges and spreads
Global price table
Cross-vendor comparison
How should I prompt it?
Prompt library
40 prompts with token costs
Writing
Rewrite, summarise, headlines
Coding
Review, debug, refactor, test
Extraction
JSON, batch classification
Should I self-host?
Self-hosting overview
When to build, when to buy
Build vs buy calculator
Break-even volume
VRAM calculator
How much memory you need
Quantization guide
Q4 to Q8 trade-offs
How has pricing changed?
Price history
2024 to today, every change
Current prices
Verified against official docs
OpenAI prices
GPT models and provider spreads
Anthropic prices
Claude models and provider spreads
Ecosystem
Super-Agent
The proactive coding agent, explained
Harness
The agent framework around the model
Error codes
All 7 official codes, and when to retry
FAQ
Pricing, timing, model choice
About
Independent third-party project. We compile publicly available pricing and provider data, and build calculators on top of it. We do not provide API access, resell DeepSeek services, or offer consulting.