Skip to main content
Using Claude

Claude Model Comparison: Opus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5.1 (November 2026)

Compare specs and pricing for the four current Claude models (Fable 5.1, Opus 5.5, Sonnet 5.5, Haiku 5.5) and get selection criteria by task type, based on the official model docs.

ByUpdated
🌐 This article was machine-translated and may contain inaccuracies. Read the Korean original if in doubt.

The Claude API offers several models, and which one you choose drives both cost and quality. Based on the official model docs (as of November 2026, reflecting the 5.5 generation), this article compares the current models' specs and pricing and lays out selection criteria by task type.

🟢 Model references match the current lineup · model notice · Fable subscription
🟢 Model references match the current lineup · Claude Opus 5.5 / Claude Sonnet 5.5 / Claude Haiku 5.5 (higher tier: Claude Fable 5.1). This notice changes only when Anthropic ships a new model.

Fable 5 and 5.1 subscription (updated November 1, 2026): Claude Fable 5.1, released September 1, 2026, is the current Fable model and Fable 5 is now legacy. Plan terms are the same for both — Max, Ultra, and Team Premium plans include Fable at up to 50% of the weekly usage limit; Pro and Team Standard use usage credits ($10/M input, $50/M output tokens). The one-time $100 credit applied only to the Fable 5 transition and is not offered for 5.1. Some coding and debugging requests may be answered by an Opus model due to a security classifier (both models). See the Fable 5.1 guide and the Fable 5 availability guide for details.

Claude Model Comparison (November 2026) Pricing = USD per MTok · Haiku 5.5 for prompts up to 100K tokens · Subject to change Fable 5.1 claude-fable-5-1 Price (in/out) $10 / $50 Context 1M Max output 128k Hardest frontier workloads Adaptive thinking (always on) Opus 5.5 claude-opus-5-5 Price (in/out) $4 / $20 Context 1M Max output 128k Complex reasoning & agentic coding Adaptive thinking (always on) Sonnet 5.5 claude-sonnet-5-5 Price (in/out) $2 / $10 Same price as Sonnet 5 Context 1M Max output 128k Best speed/intelligence balance Adaptive thinking (default) Haiku 5.5 claude-haiku-5-5 Price (in/out) $0.10 / $0.50 Context 1M Max output 128k Fastest, cheapest bulk processing Adaptive thinking (default on)

Current model lineup

Per the official model docs, the main current models are below. Opus 5.5 arrived on September 22, 2026, Sonnet 5.5 on September 28 and Haiku 5.5 on October 7, so the previous generation (Opus 5, Sonnet 5, Haiku 4.5) is now legacy and still available. All are offered via the Claude API and major clouds such as Amazon Bedrock.

  • Claude Opus 5.5 (claude-opus-5-5) — released September 22, 2026. The Opus tier for complex reasoning and long-horizon agentic coding. Pricing $4 input / $20 output per MTok (down from Opus 5's $5/$25), 1M context, 128k max output. Adaptive thinking is always on and can't be turned off; the default effort is medium.
  • Claude Sonnet 5.5 (claude-sonnet-5-5) — released September 28, 2026. Balances speed, intelligence and cost. $2 / $10 (same as Sonnet 5), 1M context, 128k max output. Uses adaptive thinking, doesn't support turning thinking off (disabled), and defaults to high effort.
  • Claude Haiku 5.5 (claude-haiku-5-5) — released October 7, 2026. The fastest and cheapest tier. Tiered pricing: $0.10 / $0.50 when a request's prompt is up to 100K tokens, $0.50 / $2.50 above that. 1M context, 128k max output, adaptive thinking on by default, default effort medium. A new tokenizer means the same text counts as roughly 30% more tokens than on Haiku 4.5.
  • Claude Fable 5.1 (claude-fable-5-1) — released September 1, 2026. Anthropic's most capable widely released model, for the most demanding reasoning and long-horizon agentic work. $10 / $50, 1M context, 128k max output. Adaptive thinking is always on.

Note: Claude Mythos 5.1 (released September 1, 2026) follows the same model — Glasswing organizations only, with the same specs and pricing as Fable 5.1. Claude Mythos 5 / Mythos Preview are offered separately via Project Glasswing (invitation-only, defensive cybersecurity workloads) with no self-serve signup.

Pricing & spec comparison

Cost is priced per million tokens (MTok) of input/output. Current models range widely: Haiku 5.5 $0.10/$0.50 → Sonnet 5.5 $2/$10 → Opus 5.5 $4/$20 → Fable 5.1 $10/$50 (Haiku 5.5 for prompts up to 100K tokens). Output costs more than input, so prompt design that shortens output directly affects cost.

  • Context window — the most a single request can handle: 1M tokens on all four current models. The legacy Haiku 4.5 has 200k.
  • Max output: 128k on all four current models (synchronous Messages API). The Batch API goes up to 300k in beta.
  • Thinking — the model reasoning internally before it answers: all current models use adaptive thinking (the model decides how much to think). It's always on for Opus 5.5 and Fable 5.1, and Sonnet 5.5 doesn't support turning it off. Opus 5.5 rejects requests that set a thinking budget (budget_tokens), so you control it with effort.
  • Knowledge cutoff: June 2026 for Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.1 (official model docs).
  • Tokenizer: Sonnet 5 and Haiku 5.5 produce roughly 30% more tokens for the same text than the previous generation. Re-measure token budgets and cost estimates set for older models when you migrate.
Which model should I pick? When unsure, start complex tasks with Opus 5.5 Task difficulty? Cost vs. quality trade-off Bulk · simple · low-latency → Haiku 5.5 Everyday production default → Sonnet 5.5 Complex reasoning · agents → Opus 5.5 Frontier-difficulty work → Fable 5.1 Key considerations · Long docs/codebases → 1M context (all four current models) · Thinking → all current models are adaptive (tune with effort) · Variable difficulty in a workflow → Route different models per step Always verify specs in official docs

Choosing by task type

The official docs advised starting complex tasks with the Opus tier when unsure (Opus 5 when we checked in September). In practice, this cost/quality split works well:

  • High-volume, simple, low-latency work (classification, short replies, real-time chatbots) → Haiku 5.5. Fastest and cheapest; just note the rate rises fivefold for prompts over 100K tokens.
  • Everyday production default (most coding, generation, summarization) → Sonnet 5.5. The speed/intelligence/cost balance.
  • Complex reasoning and long-horizon agentic coding → Opus 5.5. When answer quality matters most.
  • Hardest frontier work → Fable 5.1. Only for workloads hard enough to justify the extra cost.

All current models have 1M context, so long documents and codebases are fine on any of them, and for workflows whose difficulty varies by step, routing a different model per step is another option.

Model IDs are pinned snapshots

A caveat: every Claude model ID is a pinned snapshot — think of it like a frozen recipe card, not a live feed. IDs with a date (e.g., 20251001) are fixed to that release, and starting with the 4.6 generation the dateless format (e.g., claude-sonnet-5-5) is also a pinned snapshot, not an evergreen pointer that silently updates. You can query model capabilities and token limits programmatically via the Models API (returns max_input_tokens, max_tokens, and a capabilities object).

Summary

A sensible model-selection flow: (1) gauge task difficulty and cost tolerance → (2) pick a tier among Haiku / Sonnet / Opus / Fable → (3) fine-tune by context window, thinking mode, and output needs. To learn more, see Claude API Model IDs and Versioning and Context Window and Tokens.

This article summarizes public information from the official Anthropic docs (platform.claude.com/docs) as of November 2, 2026, updated for the 5.5 generation (Opus 5.5 checked September 27, Sonnet and Haiku 5.5 checked October 26). The model lineup, pricing, and specs change frequently, so always verify against the official Models overview and Pricing pages when choosing. This site is not an official Anthropic site.

Was this helpful?

Keep reading

Opus vs Sonnet: Opus 5.5 vs Sonnet 5.5 — Which Claude Model Should You Use?

Claude Opus 5.5 and Sonnet 5.5 differ in price (2x), speed, thinking and default effort. Benchmarks, how to choose in the API or app, and what breaks when moving from Sonnet 5.

622

Claude API Pricing by Model — Input/Output Token Rates and How to Cut Costs with Batch and Prompt Caching

Compare Claude API token pricing across Opus 5, Sonnet 5, Haiku 4.5, and Fable 5.1, and learn how Batch API's 50% discount and prompt caching's up to 90% discount can lower your costs.

150

Anthropic Updates Roundup - 2026/10 (22 items)

A monthly roundup of 22 Anthropic updates in 2026/10

4

Claude Code Desktop Environments Explained: This Computer, Cloud and New Environment (October 2026)

A guide to the environment menu in the Claude Code desktop app: Local vs Cloud, what saved environments do, which to pick when, and notes on environment variables and plans, per the official docs as of October 2026.

5