Current models
| Spec | Claude Fable 5.1 | Claude Opus 5.5 | Claude Sonnet 5.5 | Claude Haiku 5.5 |
|---|---|---|---|---|
| Best for | For demanding reasoning and long-horizon agentic work | For long-running agentic coding and knowledge work | The best combination of speed and intelligence | For high-volume, latency-sensitive tasks such as classification, extraction, and routing |
| Claude API ID | claude-fable-5-1 | claude-opus-5-5 | claude-sonnet-5-5 | claude-haiku-5-5 |
| Context window | 1M tokens | 1M tokens | 1M tokens | 1M tokens |
| Max output | 128K tokens | 128K tokens | 128K tokens | 128K tokens |
| Pricing | $10 / input MTok, $50 / output MTok | $4 / input MTok, $20 / output MTok | $2 / input MTok, $10 / output MTok | From $0.10 / input MTok, From $0.50 / output MTok |
| Default effort (API) | high | medium | high | medium |
| Thinking | Adaptive (always on) | Adaptive (always on) | Adaptive | Adaptive |
| Comparative latency | Slower | Moderate | Fast | Fastest |
| Reliable knowledge cutoff | Jun 2026 | Jun 2026 | Jun 2026 | Jun 2026 |
| Amazon Bedrock ID | anthropic.claude-fable-5-1 | anthropic.claude-opus-5-5 | anthropic.claude-sonnet-5-5 | anthropic.claude-haiku-5-5 |
| Claude Models on Google Cloud ID | claude-fable-5-1 | claude-opus-5-5 | claude-sonnet-5-5 | claude-haiku-5-5 |
| Microsoft Foundry ID | claude-fable-5-1 | claude-opus-5-5 | claude-sonnet-5-5 | claude-haiku-5-5 |
| Retirement | Not sooner than September 1, 2027 | Not sooner than September 22, 2027 | Not sooner than September 28, 2027 | Not sooner than October 7, 2027 |
API pricing for every model
US dollars per million tokens. Work out real totals with the API cost calculator.
| Model | Input | Output | 5m cache write | 1h cache write | Cache hit | Batch in | Batch out |
|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | $10 | $50 | $12.5 | $20 | $0.25 | $5 | $25 |
| Claude Mythos 5.1limited | $10 | $50 | $12.5 | $20 | $0.25 | $5 | $25 |
| Claude Fable 5 | $10 | $50 | $12.5 | $20 | $1 | $5 | $25 |
| Claude Mythos 5limited | $10 | $50 | $12.5 | $20 | $1 | $5 | $25 |
| Claude Opus 5.5 | $4 | $20 | $5 | $8 | $0.2 | $2 | $10 |
| Claude Opus 5 | $5 | $25 | $6.25 | $10 | $0.5 | $2.5 | $12.5 |
| Claude Opus 4.8 | $5 | $25 | $6.25 | $10 | $0.5 | $2.5 | $12.5 |
| Claude Opus 4.7 | $5 | $25 | $6.25 | $10 | $0.5 | $2.5 | $12.5 |
| Claude Opus 4.6 | $5 | $25 | $6.25 | $10 | $0.5 | $2.5 | $12.5 |
| Claude Opus 4.5 | $5 | $25 | $6.25 | $10 | $0.5 | $2.5 | $12.5 |
| Claude Opus 4.1retired | $15 | $75 | $18.75 | $30 | $1.5 | $7.5 | $37.5 |
| Claude Opus 4retired | $15 | $75 | $18.75 | $30 | $1.5 | $7.5 | $37.5 |
| Claude Sonnet 5.5 | $2 | $10 | $2.5 | $4 | $0.1 | $1 | $5 |
| Claude Sonnet 5 | $2 | $10 | $2.5 | $4 | $0.2 | $1 | $5 |
| Claude Sonnet 4.6 | $3 | $15 | $3.75 | $6 | $0.3 | $1.5 | $7.5 |
| Claude Sonnet 4.5 | $3 | $15 | $3.75 | $6 | $0.3 | $1.5 | $7.5 |
| Claude Sonnet 4retired | $3 | $15 | $3.75 | $6 | $0.3 | $1.5 | $7.5 |
| Claude Haiku 5.5 (for prompts up to 100,000 tokens) | $0.1 | $0.5 | $0.125 | $0.2 | $0.01 | $0.05 | $0.25 |
| Claude Haiku 5.5 (for prompts over 100,000 tokens) | $0.5 | $2.5 | $0.625 | $1 | $0.05 | $0.25 | $1.25 |
| Claude Haiku 4.5 | $1 | $5 | $1.25 | $2 | $0.1 | $0.5 | $2.5 |
| Claude Haiku 3.5retired | $0.8 | $4 | $1 | $1.6 | $0.08 | $0.4 | $2 |
Claude Code model aliases
defaultSpecial value that clears any model override and reverts to the runtime default for your account. Not itself a model aliasbestUses the model the fable alias resolves to where Fable is available to you, otherwise the same model as opusfableUses the Fable model for your provider for your hardest and longest-running taskssonnetUses the latest Sonnet model for daily coding tasksopusUses the latest Opus model for complex reasoning taskshaikuUses the fast and efficient Haiku model for simple taskssonnet[1m]Uses Sonnet with a 1 million token context window for long sessions. No effect when sonnet already resolves to Sonnet 5.5 or Sonnet 5 with their native 1M windowopus[1m]Uses Opus with a 1 million token context window for long sessions. No effect when opus already resolves to Opus 4.7 or later with its native 1M windowopusplanSpecial mode that uses opus during plan mode, then switches to sonnet for executionWhat the aliases resolve to on each provider
| Provider | opus | sonnet | haiku |
|---|---|---|---|
| Anthropic API | Opus 5.5 | Sonnet 5.5 | Haiku 5.5 |
| Claude Platform on AWS | Opus 5.5 | Sonnet 4.6 | Haiku 4.5 |
| Amazon Bedrock, Google Cloud's Agent Platform | Opus 5.5 | Sonnet 4.5 | Haiku 4.5 |
| Microsoft Foundry | Opus 4.6 | Sonnet 4.5 | Haiku 4.5 |
Effort levels in Claude Code
lowQuick exchanges where you review each result, such as brainstorming, a first sketch, or a small change like a renamemediumThe default on Opus 5.5, Sonnet 5.5, and Haiku 5.5. On Opus 5.5 and Sonnet 5.5, it fits day-to-day engineering work with a clear scope, such as implementing a new feature. On models with a higher default, reduces token usage for cost-sensitive work that can trade off some intelligencehighWork where verification matters or edge cases are likely, such as fixing a bug in an existing codebase. The default on every model except Opus 5.5, Sonnet 5.5, Haiku 5.5, and Opus 4.7xhighDeeper reasoning at higher token spend. The default on Opus 4.7maxHard problems you want Claude to work through without you, such as finding security vulnerabilities. max may show diminishing returns and is prone to overthinking, so test before adopting it broadlyultracodeA Claude Code setting rather than a level: plans a dynamic workflow for each substantive task at any effort levelPicking a model in Claude Code
Switch mid-session with /model or Option+P (Alt+P on Windows and Linux), start with claude --model opus, or set "model" in settings.json. Subagents can run a cheaper model than the main session through their model field; build one with the subagent generator.
Frequently asked questions
What is the latest Claude model?
The current lineup is Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5. Anthropic suggests starting with Claude Opus 5.5 for most work and using Claude Fable 5.1 for the hardest reasoning and long-running agentic tasks.
What model ID do I use in the API?
Use the Claude API ID from the table: claude-fable-5-1, claude-opus-5-5, claude-sonnet-5-5, claude-haiku-5-5. On Amazon Bedrock, use the Bedrock ID, which adds an anthropic. prefix.
What do opus, sonnet and haiku mean in Claude Code?
They are aliases that resolve to the newest model in each family on the Anthropic API, so /model opus or --model opus picks the latest Opus. On Bedrock, Google Cloud and Foundry they can resolve to older versions; the provider table on this page shows which.
How big is the Claude context window?
Every current model has a 1M tokens context window and up to 128K tokens of output. Use the token counter on this site to see how much of it your files take up.
How much does Claude cost per token?
Prices are per million tokens (MTok). Claude Opus 5.5 is $4 input and $20 output. The full table, with cache and batch prices, is on this page, and the API cost calculator works out real totals.
Sources: Models overview, Pricing, Claude Code model configuration. Claude Code Agents is an independent site, not affiliated with Anthropic.