Unbiased
Blog
Measured writing about AI model pricing, benchmarks, and infrastructure. Every number on these pages has a receipt.
LLM API cost calculator
Price any workload across nine models at once: pick a task profile or paste your own prompt, set daily volume, compare the bills.
AI gateway fee calculator
Enter monthly spend, get each gateway's annual fee cost sorted cheapest first, with the flat-vs-percentage crossover called out.
Fable 5 pricing, explained: real bills from real requests
The flagship breakdown: measured side-by-sides with playable outputs, a real Claude Code session ledger, the full market ladder, a paste-your-prompt calculator, and the price-history answer to whether it gets cheaper.
OpenRouter alternatives in 2026: an honest comparison from a competitor
Real fees, measured gateway latency, a which-gateway quiz that will happily recommend our competitors, and the category's open secret: the fee is not the money.
Fable 5 alternatives: what actually comes close
Opus 5 at half price, GPT-5.6 Sol, Sonnet 5, batching the model you already use, and Pareto's blended model. What each costs and what you give up.
Claude Opus 5 pricing: same rate card, bigger bills
$5/$25, unchanged from 4.8. The measured surprise: the identical prompt billed 60% more on Opus 5, because verbosity is a price.
Claude Opus 4.8 pricing: the quiet bargain in Anthropic's ladder
Same price as its successor, fewer tokens per task in our meters. Why the previous flagship is still worth pricing, with the benchmark receipts anchored to it.
Claude Sonnet 5 pricing: the $2/$10 rate ends August 31
$2/$10 is an introductory rate with an expiry date. The scheduled 50% increase, the Terra comparison, and measured task bills for the mid tier.
GPT-5.6 Sol pricing: the frontier tier with an output premium
$5/$30: input tied with Opus 5, output 20% higher, and generation work is output-heavy. The cache math and the market table.
GPT-5.6 Luna pricing: the volume-tier bake-off
Luna at $1/$6 versus Haiku 4.5 at $1/$5. At a million tasks a month the gap is real money, and quality cliffs cost more than rates.
LiteLLM alternatives: when self-hosting stops being free
What free actually costs in ops time, and the managed options for teams whose constraint changed.
Portkey alternatives: control plane, gateway, or neither
Portkey charges for visibility, not tokens. The alternatives depend on which direction you came from, and whether the bill was the real problem.
OpenAI API alternatives in 2026: what each one costs
Anthropic's ladder rung for rung, the open-weights math, and gateways. Every price verified and dated.
Anthropic API alternatives in 2026: prices and trade-offs
Start with the alternatives inside Anthropic: batch, cache, and tier down. Then the OpenAI comparison and what migration actually costs.