# Outdated Claude Model Versions on the Claude API Canonical: https://www.pointfive.co/efficiency-hub/inefficiencies/outdated-claude-model-versions-on-the-claude-api Claude API requests are billed at the rate of the model ID they name, and applications usually pin an ID in code or configuration. By: PointFive Updated: 2026-09-28 [Cloud Efficiency Hub](https://www.pointfive.co/efficiency-hub) The short version Claude API requests are billed at the rate of the model ID they name, and applications usually pin an ID in code or configuration. PointFive Research Cloud cost research at PointFive Anthropic service [Claude API](https://www.pointfive.co/efficiency-hub/cloud-services/claude-api) Category [AI](https://www.pointfive.co/efficiency-hub/service-category/ai) Reference CER-0505 Type Outdated Version ## Explanation Why the waste happens and who it affects. When Anthropic ships a newer model in the same family, pinned workloads keep running on the older one. Several older models that are still active are priced higher per token than their successors: Claude Sonnet 4.5 and 4.6 list at $3 / $15 per million input / output tokens against $2 / $10 for Sonnet 5 and 5.5, and Claude Opus 4.5 through Opus 5 list at $5 / $25 against $4 / $20 for Opus 5.5. Anthropic's own cost guide calls the model string the cheapest lever for teams a model or two behind, and reports that in its measurements each newer model usually solved at least as many tasks for less per solved task. The saving is not automatic, though. Claude 4.7 and later models use a tokenizer that produces about 30 percent more tokens for the same text, and Sonnet 5.5 and Opus 5.5 run adaptive thinking by default, billed as output tokens. Anthropic also states the direction is not guaranteed: on one of its benchmarks the upgrade cost more per task. The waste is paying a higher price per result on an older model without having measured the alternative. ## Billing model The pricing dimensions that drive this cost. Per-model token pricing Input and output tokens are billed per million at the rate of the model ID in each request Tokenizer change Claude 4.7 and later models produce about 30 percent more tokens for the same text, so per-token prices are not directly comparable across that boundary Thinking tokens Billed as output tokens; newer models that think by default can emit more output per request unless effort is tuned Retired models Requests to retired model IDs fail rather than bill, so the cost risk sits with active but superseded versions ## How to detect 4 checks to find it in your estate. - Group usage by model with the Usage and Cost Admin API usage report, or export the Console Usage page to CSV, which breaks usage down by API key and model - Flag traffic on active but superseded IDs such as claude-sonnet-4-5-20250929, claude-sonnet-4-6, claude-opus-4-5-20251101, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8 and claude-opus-5, and on models marked Deprecated - Check the model deprecations page for each pinned ID's lifecycle state and tentative retirement date, and prioritize workloads whose model is nearest retirement - Search code and configuration for hard-coded model IDs that have no owner or review date ## How to fix 5 ways to remove the waste. - Evaluate the current model in the same family on a sample of real traffic and compare cost per completed task, not cost per token, as Anthropic recommends - Sweep effort on the newer model rather than carrying over old settings; a newer model at lower effort is often the cheapest configuration, and Sonnet 5.5 can run without up-front thinking using the between\_tools setting - Follow the model's migration guide for breaking changes such as rejected sampling parameters, forced tool choice and prefill, and re-baseline max\_tokens because it now covers thinking plus text - Roll out behind a shadow or canary slice, then move the pinned ID and record an owner and review date so the next upgrade is not missed - Where the measured cost per task on the newer model is higher for a workload, keep the older model until its retirement date and document why ## Documentation Vendor references for pricing and configuration. - [Optimizing for cost and intelligence - Claude Platform Docs platform.claude.com](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence) - [Pricing - Claude Platform Docs platform.claude.com](https://platform.claude.com/docs/en/about-claude/pricing) - [Model deprecations - Claude Platform Docs platform.claude.com](https://platform.claude.com/docs/en/about-claude/model-deprecations) - [Migrating to Claude Opus 5.5 - Claude Platform Docs platform.claude.com](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide) - [Migrating to Claude Sonnet 5.5 - Claude Platform Docs platform.claude.com](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide) ## Related inefficiencies [Browse the library](https://www.pointfive.co/efficiency-hub) - Claude API CER-0503 ### [Missing Prompt Caching on the Claude API](https://www.pointfive.co/efficiency-hub/inefficiencies/missing-prompt-caching-on-the-claude-api) Agents, coding assistants, RAG applications and multi-turn chat on the Claude API resend the same long prefix on every request: tool definitions, a system prompt, reference documents and the conversation so far. Without prompt caching,... AI - Claude API CER-0504 ### [Latency-Tolerant Claude API Workloads Not Using the Message Batches API](https://www.pointfive.co/efficiency-hub/inefficiencies/latency-tolerant-claude-api-workloads-not-using-the-message-batches-api) Many Claude API workloads have no user waiting on the answer: evaluation suites, content moderation backlogs, bulk classification and tagging, data extraction, summarization of document sets and generation of product descriptions. When... AI - Claude API CER-0506 ### [Using High-Cost Claude Models for Low-Complexity Tasks](https://www.pointfive.co/efficiency-hub/inefficiencies/using-high-cost-claude-models-for-low-complexity-tasks) Routing, classification, tagging, entity extraction, short summarization and similar high-volume tasks are often sent to the same top-tier Claude model that powers an application's hardest agentic work, simply because one model ID is... AI --- Source: the public page above. Product screenshots and illustrative interfaces are examples, not live customer data.