# Claude API Models: Complete 2026 Identifier Guide

*Edition of November 13, 2026 — facts verified November 13, 2026. Current edition always at https://tygartmedia.com/claude-api-model/.*

> **Canonical URL:** https://tygartmedia.com/claude-api-model/
> **Format:** Single-source Markdown twin generated directly from the live page.

---

*Last verified: November 13, 2026 against the [models overview](https://platform.claude.com/docs/en/about-claude/models/overview) and [Anthropic pricing docs](https://platform.claude.com/docs/en/about-claude/pricing). Historical strings below the current table were not each re-fetched.*

Model Accuracy Note — Updated November 13, 2026

Current models (November 13, 2026): **Fable 5.2 · Opus 5.5 · Sonnet 5.5 · Haiku 5.5** — all 1M context / 128K output. Fable 5.1, Sonnet 5, Haiku 4.5, Opus 5, Fable 5, Opus 4.8, and Sonnet 4.6 are legacy. [Current model tracker →](https://tygartmedia.com/current-claude-model-version/)

> **Direct Answer (November 13, 2026):** Current Claude API IDs are `claude-fable-5-2` ($8/$40), `claude-opus-5-5` ($4/$20 — start here for most workloads), `claude-sonnet-5-5` ($2/$10), and `claude-haiku-5-5` ($0.10/$0.50 ≤100K, $0.50/$2.50 >100K) — all with 1M context and 128K output. Fable 5.1, Sonnet 5, Haiku 4.5 (`claude-haiku-4-5-20251001`, 200K context), Opus 5, and Opus 4.8 are legacy.

Claude AI · Fitted Claude

When you’re building on Claude via the API, you need the exact model string — not just the name. Anthropic uses specific model identifiers that change with each version, and using a deprecated string will break your application. This is the identifier desk. The current lineup below was verified November 13, 2026. Older strings further down are not the current default.

Quick reference:

Current IDs are

claude-fable-5-2

,

claude-opus-5-5

,

claude-sonnet-5-5

, and

claude-haiku-5-5

— all sharing a 1M-token context window and 128K max output. Legacy Haiku 4.5 still uses

claude-haiku-4-5-20251001

/

claude-haiku-4-5

(200K context).

## Current Claude API model strings (November 13, 2026)

*Current Claude API model strings.*

| Model | API Model String | Context Window | Best for |
| --- | --- | --- | --- |
| **Claude Fable 5.2** | claude-fable-5-2 | 1M tokens (128K out) | Current flagship for demanding reasoning and long-horizon work. $8 / $40 ($0.20 read) |
| **Claude Opus 5.5** | claude-opus-5-5 | 1M tokens | Daily driver. Start here for most workloads. $4 / $20 |
| **Claude Sonnet 5.5** | claude-sonnet-5-5 | 1M tokens (128K out) | Current Sonnet workhorse. $2 / $10 ($0.10 read) |
| **Claude Haiku 5.5** | claude-haiku-5-5 | 1M tokens (128K out) | Current speed tier. $0.10/$0.50 (≤100K) or $0.50/$2.50 (>100K) |

Anthropic publishes the full, current list of model strings in their [official models documentation](https://platform.claude.com/docs/en/about-claude/models/overview). Always verify there before updating production systems — model strings are updated with each new release.

**Legacy models & third-party gateways:** Legacy strings still listed on Anthropic’s overview include Fable 5.1 (`claude-fable-5-1`), Sonnet 5 (`claude-sonnet-5`), Haiku 4.5 (`claude-haiku-4-5-20251001` / `claude-haiku-4-5`), Fable 5, Opus 5, Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6. For current Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry partner identifiers, check the live [Anthropic models overview](https://platform.claude.com/docs/en/about-claude/models/overview).

## How to Use Model Strings in an API Call

*How to use model strings in an API call.*

```
import anthropic

client = anthropic.Anthropic()

message = client.messages.create(
    model="claude-opus-5-5",  # current Opus daily driver (verified Nov 13, 2026)
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Your prompt here"}
    ]
)

print(message.content)
```

## Model Selection: Which String to Use When

*Model selection — which string to use when.*

The right model depends on your task requirements. Here’s the practical routing logic:

**Use Haiku 5.5** (`claude-haiku-5-5`) when: you need speed and low cost at scale ($0.10/$0.50 ≤100K, $0.50/$2.50 >100K, 1M context) — classification, extraction, routing, metadata, high-volume pipelines.

**Use Sonnet 5.5** (`claude-sonnet-5-5`) when: you want a fast daily workhorse at $2 / $10 ($0.10 cache read).

**Use Opus 5.5** (`claude-opus-5-5`) when: you are starting most workloads. Input $4 / output $20 per million tokens ($0.20 cache read).

**Use Fable 5.2** (`claude-fable-5-2`) when: evals on Opus 5.5 at higher effort still fall short. Input $8 / output $40 per million tokens ($0.20 cache read).

## API Pricing by Model

| Model | Input (per M tokens) | Output (per M tokens) |
| --- | --- | --- |
| Claude Haiku 5.5 | $0.10 (≤100K) / $0.50 (>100K) | $0.50 (≤100K) / $2.50 (>100K) |
| Claude Sonnet 5.5 | $2.00 | $10.00 |
| Claude Opus 5.5 | $4.00 | $20.00 |
| Claude Fable 5.2 | $8.00 | $40.00 |
| Legacy: Fable 5.1 & Fable 5 | $10.00 | $50.00 |
| Legacy: Sonnet 4.6 | $3.00 | $15.00 |
| Legacy: Opus 5 and Opus 4.8 | $5.00 | $25.00 |

The Batch API is 50% off input and output. For a full pricing breakdown, see [Anthropic API Pricing: Every Model and Mode Explained](https://tygartmedia.com/anthropic-api-pricing/).

## Important: Versioned Strings vs. Aliases

Anthropic occasionally provides alias strings (like `claude-sonnet-latest`) that point to the current version of a model family. These are convenient for development but can create problems in production — when Anthropic updates the model the alias points to, your application silently starts using a different model without a code change. For production systems, always pin to a versioned model string and upgrade intentionally.

## Frequently Asked Questions

### What is the Claude API model string for Sonnet?

The current Sonnet string is `claude-sonnet-5-5` ($2 / $10). `claude-sonnet-5` and Sonnet 4.6 (`claude-sonnet-4-6`, $3 / $15) are legacy.

### How do I specify which Claude model to use in the API?

Pass the model string in the `model` parameter of your API call. For example: `model="claude-sonnet-5-5"`. The model string must match exactly — Anthropic’s API will return an error if the string is invalid or deprecated.

### What Claude API model should I use for production?

Start with Opus 5.5 (claude-opus-5-5, $4/$20) or Sonnet 5.5 (claude-sonnet-5-5, $2/$10) for daily work. Use Haiku 5.5 (claude-haiku-5-5, $0.10/$0.50 ≤100K) when speed and cost are the priority. Use Fable 5.2 (claude-fable-5-2, $8/$40) when Opus 5.5 at higher effort still falls short.

💼 Deploying Claude or AI Infrastructure in Your Business?

At Tygart Media, we engineer custom Model Context Protocol (MCP) servers, multi-model content pipelines, and AI operational systems. Explore our [Claude AI Team Implementation Services](https://tygartmedia.com/ai-setup/) or check out our complete [Restoration Operations & AI Kit](https://tygartmedia.com/complete-restoration-operations-kit/).

---

## Primary & Reference Links Cited on This Page

- [models overview](https://platform.claude.com/docs/en/about-claude/models/overview)
- [Anthropic pricing docs](https://platform.claude.com/docs/en/about-claude/pricing)
- [Tygart Media: Current model tracker →](https://tygartmedia.com/current-claude-model-version/)
- [Tygart Media: Anthropic API Pricing: Every Model and Mode Explained](https://tygartmedia.com/anthropic-api-pricing/)
- [Tygart Media: Claude AI Team Implementation Services](https://tygartmedia.com/ai-setup/)
- [Tygart Media: Restoration Operations & AI Kit](https://tygartmedia.com/complete-restoration-operations-kit/)
