Criterion Claude Developer Platform (Claude API) OpenAI API
CategoryLLM APIs & Model PlatformsLLM APIs & Model Platforms
In one sentenceDeveloper access to Anthropic's Claude models with usage-based pricing, batch discounts and prompt caching.Pay-per-token developer access to OpenAI's GPT models for building apps, agents and automations.
Problem it solvesBuilding assistants, agents and document workflows on a hosted model without managing GPUs or model training.Adding language understanding, generation and reasoning to a product without training or hosting a model yourself.
Free planNoNo
Developer APIYes — docsYes — docs
Open sourceNoNo
PlatformsWeb (Claude Console), REST API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWSWeb (platform dashboard), REST API
Pricing (summary)Usage-based per 1M tokens. Fable 5.1 is $10 input / $50 output, Opus 5.5 $4 / $20, Sonnet 5.5 $2 / $10 and Haiku 5.5 from $0.10 / $0.50 (higher above 100K-token prompts). Batch requests are 50% off and cache reads cost a small fraction of input price.
Checked 2026-10-19		Usage-based billing per 1M tokens, with separate rates for input, cached input and output. GPT-6 Astra costs $10 input / $50 output, GPT-6.1 Sol $2 / $10 and GPT-6 Luna $0.10 / $0.50 per 1M tokens on the Standard tier. Batch and Flex are about half price; Fast mode costs more.
Checked 2026-10-19
Strengths
  • 1M context on all current models without a long-context surcharge (except Haiku 5.5 pricing by prompt length)
  • Strong caching and batch discounts
  • Multi-cloud availability with matching model IDs
  • Clear model tiers with published per-token prices
  • Very large context window on current models
  • Multiple cost-saving modes (Batch, Flex, caching)
Limitations
  • Top-tier Fable 5.1 costs $50 per 1M output tokens
  • Haiku 5.5 price rises for prompts over 100,000 tokens
  • Only a small, unspecified amount of free credit for new users
  • No documented free API tier for the GPT models
  • Costs can grow quickly at the top tier ($50 per 1M output tokens for Astra)
  • Higher pricing applies above 272K input tokens per the pricing page tables