Claude API Pricing 2026:
Fable 5.1, Opus 5.5, Sonnet 5.5 & Haiku 5.5 Costs
Current Anthropic Claude API pricing for Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5, plus the previous generation still on the API. Compare token costs, prompt caching, batch discounts and context windows. Last verified: 2026-10-16.
Anthropic's current Claude lineup has four tiers: Claude Fable 5.1, its most capable widely released model, for the hardest reasoning and long-horizon agentic work; Claude Opus 5.5 for complex analysis and agents; Claude Sonnet 5.5 as the everyday production default; and Claude Haiku 5.5 for high-volume, latency-sensitive work such as classification, extraction and routing. All four have a 1 million token context window and up to 128K output tokens.
Claude API Standard Pricing 2026
| Model | Input / 1M tokens | Output / 1M tokens | Context window | Best for |
|---|---|---|---|---|
| Claude Fable 5.1 | $10.00 | $50.00 | 1M tokens | Hardest reasoning and long-horizon agentic work |
| Claude Opus 5.5 | $4.00 | $20.00 | 1M tokens | Complex analysis, agents, demanding coding |
| Claude Sonnet 5.5 | $2.00 | $10.00 | 1M tokens | Production default for coding, agents and enterprise work |
| Claude Haiku 5.5 | $0.10* | $0.50* | 1M tokens | Classification, extraction, routing, high-volume chat |
What changed in 2026: Opus 5.5 costs $4/$20 per million tokens — less than Opus 4.6 ($5/$25) — and Sonnet 5.5 costs $2/$10, down from Sonnet 4.6's $3/$15. Claude Mythos 5.1 shares Fable 5.1's pricing but is available only to approved organizations, so it is not listed here.
Previous-Generation Claude Models Still on the API
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Claude Fable 5 | $10.00 | $50.00 | 1M |
| Claude Opus 5 | $5.00 | $25.00 | 1M |
| Claude Opus 4.8 / 4.7 / 4.6 | $5.00 | $25.00 | 1M |
| Claude Sonnet 5 | $2.00 | $10.00 | 1M |
| Claude Sonnet 4.6 | $3.00 | $15.00 | 1M |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K |
For new projects, Opus 5.5, Sonnet 5.5 and Haiku 5.5 are cheaper than the models they replace — Haiku 5.5 costs a tenth of Haiku 4.5 for prompts up to 100K tokens, so migrating usually lowers the bill as well as improving quality.
Prompt Caching Pricing
Prompt caching bills repeated prompt prefixes — system prompts, tool definitions, shared documents — at a fraction of the normal input price. Cache reads cost:
| Model | Standard input / 1M | Cache read / 1M | Discount |
|---|---|---|---|
| Claude Fable 5.1 | $10.00 | $0.25 | 97.5% |
| Claude Opus 5.5 | $4.00 | $0.20 | 95% |
| Claude Sonnet 5.5 | $2.00 | $0.10 | 95% |
| Claude Haiku 5.5 (≤100K prompt) | $0.10 | $0.01 | 90% |
Writing a prompt into the cache costs more than a normal input token (1.25× for the 5-minute cache, 2× for the 1-hour cache), so caching pays off when the same prefix is reused across many requests. The minimum cacheable prefix is 512 tokens on the current models; on the legacy Haiku 4.5 it is 4,096 tokens.
Batch API Pricing
Anthropic's Message Batches API gives a 50% discount for non-real-time workloads (classification, data processing, evals). Batches complete within 24 hours.
| Model | Batch Input / 1M | Batch Output / 1M |
|---|---|---|
| Claude Fable 5.1 | $5.00 | $25.00 |
| Claude Opus 5.5 | $2.00 | $10.00 |
| Claude Sonnet 5.5 | $1.00 | $5.00 |
| Claude Haiku 5.5 (≤100K prompt) | $0.05 | $0.25 |
Claude vs OpenAI: Quick Price Comparison
| Tier | Claude model | Claude in / out per 1M | OpenAI model | OpenAI in / out per 1M |
|---|---|---|---|---|
| Budget | Haiku 5.5 | $0.10 / $0.50 | GPT-6 Luna | $0.10 / $0.50 |
| Balanced | Sonnet 5.5 | $2.00 / $10.00 | GPT-6.1 Sol | $2.00 / $10.00 |
| Premium | Opus 5.5 | $4.00 / $20.00 | GPT-6 Astra | $10.00 / $50.00 |
| Top tier | Fable 5.1 | $10.00 / $50.00 | GPT-6 Astra | $10.00 / $50.00 |
| Context | All current models | 1M | GPT-6 family | 1.05M |
Haiku 5.5 and GPT-6 Luna have the same list price for short prompts, and Sonnet 5.5 and GPT-6.1 Sol cost exactly the same. Opus 5.5 costs less than half of GPT-6 Astra. Long prompts change the picture: Haiku 5.5 rises to $0.50/$2.50 above 100K prompt tokens, and OpenAI doubles input prices above 272K input tokens.
Which Claude Model Should You Choose?
| Use case | Best model | Reason |
|---|---|---|
| High-volume chatbots, classification, routing | Haiku 5.5 | Lowest Claude cost and the fastest model; keep prompts under 100K tokens |
| Customer support, summarization | Sonnet 5.5 | Best quality-to-cost ratio, 1M context |
| Complex coding, content creation | Sonnet 5.5 | Production default for demanding tasks |
| Complex agentic workflows, research | Opus 5.5 | Higher accuracy on long, multi-step work at $4/M input |
| Hardest problems where quality outweighs cost | Fable 5.1 | Anthropic's most capable widely released model |
Real-World Cost Examples
Customer Support Bot — 50,000 conversations/month
- System prompt: 2,000 tokens (cached after the first call)
- Per conversation: 500 tokens fresh input + 300 tokens output
- Sonnet 5.5 without caching: 125M input × $2 + 15M output × $10 = ~$400/month
- Sonnet 5.5 with prompt caching: 100M cached × $0.10 + 25M × $2 + $150 output = ~$210/month
- Savings: about 47% overall — caching removes 95% of the system-prompt cost, and output tokens make up most of what remains
Document Analysis Pipeline — 10,000 docs/month
- Average: 5,000 tokens input + 800 tokens output (50M input, 8M output per month)
- Haiku 5.5: $5 input + $4 output = $9/month
- Sonnet 5.5: $100 input + $80 output = $180/month
- Opus 5.5: $200 input + $160 output = $360/month
API Access
- Sign up at console.anthropic.com — no approval process required
- Pay-as-you-go billing, no monthly minimum
- Enterprise: custom terms for high-volume spend — contact Anthropic sales
Frequently Asked Questions
Is Claude Sonnet 5.5 the best default production model?
For most teams, yes. It handles complex tasks at $2/M input and $10/M output, and its 1M-token context handles large documents without chunking. Haiku 5.5 is the better choice when volume is high, prompts are short and cost or latency is the main constraint.
Does Claude batch processing reduce cost?
Yes — Anthropic's Message Batches API gives a 50% discount on input and output tokens. Batches complete within 24 hours, which makes them a good fit for classification, evals and other pipelines that are not latency-sensitive.
Is Opus 5.5 more expensive than Opus 4.6?
No. Opus 5.5 is $4/M input and $20/M output, compared with $5/$25 for Opus 4.6, Opus 4.7, Opus 4.8 and Opus 5. Sonnet 5.5 is also cheaper than Sonnet 4.6 ($2/$10 vs $3/$15).
Haiku 5.5 or GPT-6 Luna?
For prompts up to 100K tokens they have the same list price: $0.10/M input and $0.50/M output. Cached input is $0.01/M on both. Above 100K prompt tokens Haiku 5.5 costs five times more ($0.50/$2.50), so for very long prompts Luna is cheaper. For short prompts, pick on quality and latency for your task and benchmark both on real traffic.
Is Haiku 4.5 still available?
Yes, as a legacy model at $1/M input and $5/M output with a 200K context window. Haiku 5.5 costs a tenth of that for prompts up to 100K tokens and has a 1M context window, so there is little reason to start a new project on Haiku 4.5.
Which Claude model is best for RAG or coding?
Sonnet 5.5 is the default for both. For RAG, its 1M context window can hold large document sets; for coding, it handles complex multi-file tasks and follows detailed instructions reliably. Opus 5.5 and Fable 5.1 are worth the premium for the longest, most complex reasoning or research tasks.
Calculate Your Claude API Costs
Get an accurate monthly cost estimate for your Claude API usage.
Open API Cost Calculator