One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.10 = $0.10
- Output0.1M x $0.50 = $0.05
$0.15per session
Anthropic - Closed weights
Claude Haiku 5.5 pricing and specs
Claude Haiku 5.5 is a closed-weights model from Anthropic that costs $0.10 per 1M input tokens and $0.50 per 1M output tokens on the first-party API, with a 1M-token context window.
Last verified from platform.claude.com. All sources
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Context
- 1M tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| InputPrompts up to 100,000 tokens | $0.10 |
| OutputPrompts up to 100,000 tokens | $0.50 |
| Cache readPrompts up to 100,000 tokens | $0.01 |
| Cache write (5 minutes)Prompts up to 100,000 tokens | $0.125 |
| Cache write (1 hour)Prompts up to 100,000 tokens | $0.20 |
| Batch inputBatch requests, prompts up to 100,000 tokens | $0.05 |
| Batch outputBatch requests, prompts up to 100,000 tokens | $0.25 |
| Long-context inputPrompts over 100,000 tokens | $0.50 |
| Long-context outputPrompts over 100,000 tokens | $2.50 |
| Long-context cache readPrompts over 100,000 tokens | $0.05 |
| Long-context cache write (5 minutes)Prompts over 100,000 tokens | $0.625 |
| Long-context cache write (1 hour)Prompts over 100,000 tokens | $1 |
| Long-context batch inputBatch requests, prompts over 100,000 tokens | $0.25 |
| Long-context batch outputBatch requests, prompts over 100,000 tokens | $1.25 |
Note: Priced by prompt length: a request whose prompt (including cache reads and writes) is over 100,000 tokens pays the long-context rates for the whole request.
Specs
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Release date
- Provider
- Anthropic
- API model id
claude-haiku-5-5- Vercel AI Gateway id
anthropic/claude-haiku-5.5- Weights
- Closed weights
What Claude Haiku 5.5 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts. These use the base rates, which apply while each request's prompt stays at or under 100,000 tokens; above that, Claude Haiku 5.5 bills $0.50 input and $2.50 output for the whole request.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.10 = $2.00
- Output5M x $0.50 = $2.50
$4.50per day
$135.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.01 = $0.009
- Uncached input0.1M x $0.10 = $0.01
- Output0.1M x $0.50 = $0.05
$0.069per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Claude Haiku 5.5 (this page) | $0.10 | $0.50 |
| GLM-5.3Z.ai | $1.40 | $4.40 |
| Claude Sonnet 5.5Anthropic | $2 | $10 |
| Claude Opus 5.5Anthropic | $4 | $20 |
| Claude Fable 5.1Anthropic | $10 | $50 |
Related reading
- Claude Code Subagent Model: Put Explore on Haiku 5.5Claude Code's Explore subagent runs on your main model, and CLAUDE_CODE_SUBAGENT_MODEL alone won't move it. Three ways to put it on Haiku 5.5, with test runs.
- Cheapest Subagent Model: Haiku 5.5 or GPT-6 Luna? Routing, Compaction and Cost per TaskWhich cheap model belongs under your orchestrator? Haiku 5.5 vs GPT-6 Luna as a subagent or worker: routing by prompt length, compaction, tool-call gotchas and cost per agent task.
- Opus 5.5 vs Sonnet 5.5 vs Haiku 5.5: Which Claude Model to UseSonnet 5.5 is the default, Opus 5.5 is for open-ended long-horizon work, and Haiku 5.5 is for bounded steps and subagents. Prices, benchmarks, cost math.
- Claude Haiku 5.5: Pricing, Migration Changes, and When to Use ItClaude Haiku 5.5 pricing, the cliff above 100K-token prompts, the tokenizer catch, the migration steps from Haiku 4.5, and when to use it instead of Sonnet.
- Budget AI Coding Models, October 2026: Haiku 5.5 vs GPT-6 LunaClaude Haiku 5.5 and GPT-6 Luna both list at $0.10/$0.50 per MTok. The price tie breaks at Haiku's 100K cliff, and Anthropic's benchmarks favor Haiku. Checked Oct 8, 2026.
- Claude Effort Levels Explained: Fable 5, Opus 5.5, Haiku 5.5Claude effort levels explained: what low, medium, high, xhigh and max change on Fable 5, Opus 5.5 and Haiku 5.5, each default, and what a level costs.
FAQ
How much does Claude Haiku 5.5 cost per million tokens?
Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens on Anthropic's first-party API, per platform.claude.com on October 9, 2026. Per 1M tokens, cache reads cost $0.01, and the batch rate is $0.05 input and $0.25 output. Prompts over 100,000 tokens are billed at $0.50 input and $2.50 output for the whole request.
What is Claude Haiku 5.5's context window?
Claude Haiku 5.5 has a 1,000,000-token context window and returns up to 128,000 output tokens per response.
Are Claude Haiku 5.5's weights open?
No. Claude Haiku 5.5 is a closed-weights model. You call it through Anthropic's API as claude-haiku-5-5 or through Vercel AI Gateway as anthropic/claude-haiku-5.5.
When was Claude Haiku 5.5 released?
Anthropic released Claude Haiku 5.5 on October 7, 2026.
Sources
Last verified from platform.claude.com.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.