Study guide
5.3 Model Versioning, Snapshot Pinning & Migration
Claude Certified Developer - Foundations CCDV-F
Track your progress as you read
Finished sections get a check mark.
1 Chapter 1: Core Messages API & Streaming
1.1 Messages API Fundamentals & Request Lifecycle 1.2 Streaming & Server-Sent Events (SSE) 1.3 Thinking: Adaptive Mode, Effort & Reasoning Budgets
2 Chapter 2: Optimization & Asynchronous Batches
2.1 Prompt Caching Mechanics & Breakpoints 2.2 Message Batches API & Asynchronous Workloads
3 Chapter 3: Structured Outputs, Documents & Files API
3.1 Structured Outputs & JSON Extraction 3.2 Files API, Document Blocks & Citations
4 Chapter 4: Application Design, Resilience & Delivery Life Cycle
4.1 API Resilience, Error Handling & Retries 4.2 Production Backend Architecture & State Management 4.3 Requirements Analysis & Claude Application Design 4.4 The Claude Application Life Cycle & Configuration Management
5 Chapter 5: LLM Fundamentals, Model Selection & Versioning
5.1 LLM & Technical Fundamentals: Tokens, Context Windows & Sampling 5.2 Claude Model Family Selection 5.3 Model Versioning, Snapshot Pinning & Migration 5.4 Latency & Throughput Optimization
6 Chapter 6: Cost Engineering & Context Management
6.1 Production Cost Optimization Strategies 6.2 Context Window Management & Compaction
7 Chapter 7: Foundations of Workflows & Deterministic Patterns
7.1 Agent vs. Workflow Architectural Foundations 7.2 Workflow Patterns: Prompt Chaining & Routing 7.3 Workflow Patterns: Parallelization & Voting
8 Chapter 8: Autonomous Agents & Multi-Step Systems
8.1 Workflow Patterns: Orchestrator-Workers & Evaluator-Optimizer 8.2 Agent Loop Implementation & State Tracking 8.3 Agent Frameworks & Human-in-the-Loop (HITL)
9 Chapter 9: Prompt and Context Engineering
9.1 System Prompt Design & Role Framing 9.2 XML Tags & Structural Prompt Delimiters 9.3 Few-Shot Prompting & In-Context Learning 9.4 RAG Context Injection & Document Formatting
10 Chapter 10: Tool Calling & Model Context Protocol (MCP)
10.1 Tool Schema Design & Parameter Validation 10.2 Tool Execution, Multi-Tool Calls & Error Handling 10.3 MCP Architecture & Core Primitives 10.4 MCP Transports & Client/Server Integration 10.5 Agentic Customization: Built-in Tools, Custom Tools, Skills & MCP
11 Chapter 11: Security, Safety & Governance
11.1 Direct & Indirect Prompt Injection Defenses 11.2 Tool Permissions, Sandboxing & Least Privilege 11.3 Data Privacy, Redaction & Audit Logging 11.4 Identity, Secrets & API Key Management
12 Chapter 12: Claude Code Developer Tooling
12.1 Claude Code Architecture & Project Configuration 12.2 Permissions, Modes & Hooks
13 Chapter 13: Evaluation, Testing & Production Observability
13.1 Evaluation Design & Golden Datasets 13.2 Production Observability, Tracing & Debugging
5.3 Model Versioning, Snapshot Pinning & Migration
Key Takeaways Explain This Topic AI
Every Claude model ID is a pinned snapshot, including the dateless IDs used from the Claude 4.6 generation on, so claude-opus-5-5 and claude-sonnet-5-5 name fixed weights rather than moving pointers.
For models before the 4.6 generation the dateless form is a convenience alias that points to the most recent dated snapshot for that minor version (for example claude-haiku-4-5 resolving to claude-haiku-4-5-20251001); the pinning guarantee covers model IDs, not these aliases.
Claude 4.7 and later models use a newer tokenizer that produces roughly 30% more tokens for the same text, so a migration across that boundary changes token counts even when the prompt is byte-identical.
Model IDs must be externalized to environment variables, a config service, or a feature flag so canary rollout and rollback need no code deploy.
Anthropic publishes a retirement commitment date for each model on Anthropic-operated platforms, while Amazon Bedrock and Google Cloud set their own lifecycle dates.
Last updated: October 2026
Model Versioning, Snapshot Pinning & Migration
Exam Blueprint Focus: CCDV-F tests whether you can name a model deterministically and move production off one model onto another without a quality incident. The naming rules changed with the Claude 4.6 generation, and the current rules are what the exam grades.
Model Naming Anatomy: What a Model ID Actually Guarantees
The model parameter on POST /v1/messages takes a string. Every model ID is a pinned snapshot , whether it carries a date or not — this is the part most candidates get wrong. The only strings that can move are the convenience aliases that the Claude API accepts for some models released before the 4.6 generation. +-----------------------------------------------------------------------------------------+
- | MODEL IDENTIFIER TAXONOMY (CURRENT) |
- +-----------------------------------------------------------------------------------------+
- | Form | Example | Pinned? | Notes |
- |-----------------+------------------------------+---------+------------------------------|
- | Dateless ID | claude-opus-5-5 | YES | 4.6 generation onward. |
- | (4.6 gen on) | claude-sonnet-5-5 | | Its own pinned snapshot; |
- | | claude-fable-5-1 | | the alias row repeats it. |
- |-----------------+------------------------------+---------+------------------------------|
- | Dated snapshot | claude-haiku-4-5-20251001 | YES | Immutable weights. |
- |-----------------+------------------------------+---------+------------------------------|
- | Convenience | claude-haiku-4-5 | NO | Pre-4.6 pointer to the most |
- | alias | | pointer | recent dated snapshot for |
- | | | | that minor version. |
- +-----------------------------------------------------------------------------------------+
Every Claude model ID is a pinned snapshot, including the dateless IDs used from the 4.6 generation on. claude-opus-5 did not re-target when Anthropic shipped Claude Opus 5.5, which arrived under its own ID, claude-opus-5-5 . For models before the 4.6 generation, the dateless alias (for example claude-haiku-4-5 ) is a convenience pointer that resolves to the most recent dated snapshot for that minor version, currently claude-haiku-4-5-20251001 . Anthropic's pinning guarantee covers model IDs, not these convenience aliases, so production code that needs a pre-4.6 model to stay fixed should use the dated ID.
The rule that replaced "never use -latest"
Older Anthropic guidance told teams to avoid -latest aliases in production because they could re-point under you. That hazard class is gone from the current lineup: there is no -latest string in the current model table. The engineering discipline it protected, however, is still exam-relevant and still correct:
Core CCDV-F rule: Pin the exact model ID your evals ran against, externalize it as configuration, and treat a change to that string as a deployment event with its own rollout and rollback plan.
The threat has simply moved from "the provider changes my model" to "an engineer changes my model in a pull request without re-running evals," and from silent drift to a hard retirement date .
Why Changing the Model String Is a Behavioural Change
Whether the change is claude-sonnet-4-6 → claude-sonnet-5 or claude-opus-5 at high effort → claude-opus-5 at low effort, the same four hazards apply:
1. Prompt drift and semantic shift
Instruction-following improves between generations, which is not the same as staying identical. A prompt tuned to produce exactly three paragraphs may produce four. A persona framing calibrated on one generation may read differently on the next. Because nothing in your CI changed, root-causing the shift is expensive.
2. Output formatting and schema regressions
Downstream services parse Claude's output with Pydantic, Zod, or a plain JSON decoder. A new model may fence JSON in a markdown block where the previous one returned bare JSON, or change casing conventions, or add a preamble sentence. Each of those is a deserialization exception in production. Structured outputs or a strict tool (see the structured-outputs section) are the durable defence, because the schema is enforced by the API rather than by prompt convention. Note that forced tool_choice itself returns a 400 error on Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, so a migration onto those models must remove it.
3. Eval baseline invalidation
Your accuracy baselines are only meaningful against a fixed model. Change the model without re-baselining and you can no longer tell whether a metric moved because of your prompt edit or the model swap. Re-run the golden dataset and store the model ID alongside every recorded score.
4. Cost, latency, and tokenizer shifts
A new generation can change both price and token count. Two concrete facts to carry into the exam: Claude Sonnet 5 and Claude Sonnet 5.5 are $2/$10 per MTok against Claude Sonnet 4.6's $3/$15 , so that particular migration is cheaper per token; and Claude 4.7 and later models use a newer tokenizer that produces roughly 30% more tokens for the same text . A migration that crosses that tokenizer boundary changes your token counts even when the prompt is byte-identical, so re-measure cost per transaction rather than assuming the price-per-MTok delta is the whole story.
Safe Model Migration: A Five-Stage Lifecycle Stage 1 Offline golden eval -> Stage 2 Schema & safety diff -> Stage 3 Config externalization
- |
- Stage 5 Full cutover + sunset <- Stage 4b Canary 1% -> 10% -> 100% <- Stage 4a Shadow traffic
- Stage 1 — Offline golden dataset benchmarking
Run the frozen golden dataset against both model IDs. Compare per-case pass rates, not just the aggregate: a migration that improves the mean while breaking one high-stakes category is a failed migration. Record the model ID in the results file.
Stage 2 — Schema and behavioural diffing
Validate every response against the production schema. Diff refusal behaviour, tool-call arity, and output length distributions. Length matters commercially: a model that is 15% more verbose raises output spend by 15% at the same quality.
Stage 3 — Configuration externalization
The model ID belongs in an environment variable, config service, or feature flag — never a string literal scattered across handlers. This is what makes Stage 4 and the rollback in Stage 5 possible without a code deploy. import os
from anthropic import Anthropic
- client = Anthropic()
- MODEL = os.environ.get("CLAUDE_MODEL", "claude-sonnet-5-5")
- CANARY_MODEL = os.environ.get("CLAUDE_CANARY_MODEL")
- CANARY_PCT = float(os.environ.get("CLAUDE_CANARY_PCT", "0"))
def pick_model(request_id: str) -> str:
if CANARY_MODEL and stable_hash_pct(request_id) < CANARY_PCT:
- return CANARY_MODEL
- return MODEL
Hashing a stable request or tenant key keeps a given user on one model for the duration of the experiment, so you are measuring the model rather than measuring session-level noise.
Stage 4a — Shadow traffic
Send real production requests to the candidate model asynchronously, discard its output, and log it. You get production-distribution evidence with zero user risk. Shadowing doubles token spend for its duration, so run it on a sampled slice and set an end date.
Stage 4b — Canary rollout
Move 1% → 10% → 100% with an automated rollback trigger on schema-validation failure rate, refusal rate, p95 latency, and cost per request. Define the abort thresholds before you start; deciding them mid-incident guarantees you decide them badly.
Stage 5 — Cutover and sunset
Flip the default, keep the old ID available behind the flag for one release cycle, then remove it. Delete stale eval baselines so nobody compares against a retired model six months later.
Retirement Lifecycles and Sunset Windows
Anthropic publishes a retirement commitment date for each model on Anthropic-operated platforms — for example, not sooner than September 22, 2027 for Claude Opus 5.5, September 28, 2027 for Claude Sonnet 5.5, July 24, 2027 for Claude Opus 5, and June 30, 2027 for Claude Sonnet 5. Partner-operated platforms (Amazon Bedrock, Google Cloud) set their own lifecycle dates, so a multi-cloud deployment has more than one clock to track.
Retirement is real, not theoretical: Claude 3 Opus, Claude 3.5 Sonnet, Claude 3.7 Sonnet, Claude Sonnet 4, Claude Opus 4, Claude Opus 4.1, and Claude Haiku 3.5 have all been retired from the first-party Claude API, some remaining available only on Bedrock or Google Cloud. Treat "we are still on a model that has a published sunset date" as scheduled work with an owner, not as a background risk.
Operational checklist: track the retirement date of every model ID in your config; keep the golden eval suite runnable on demand; keep the canary machinery wired up between migrations so it is not built under time pressure; and query the Models API programmatically if you need max_input_tokens , max_tokens , and capability flags at runtime rather than hardcoding them.