One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $1 = $1.00
- Output0.1M x $5 = $0.50
$1.50per session
Anthropic - Closed weights
Claude Haiku 4.5 pricing and specs
Claude Haiku 4.5 is a closed-weights model from Anthropic that costs $1 per 1M input tokens and $5 per 1M output tokens on the first-party API, with a 200K-token context window.
Last verified from platform.claude.com. All sources
- Input / 1M
- $1
- Output / 1M
- $5
- Context
- 200K tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $1 |
| Output | $5 |
| Cache read | $0.10 |
| Cache write (5 minutes) | $1.25 |
| Cache write (1 hour) | $2 |
| Batch inputBatch requests | $0.50 |
| Batch outputBatch requests | $2.50 |
Note: Legacy model, still sold. Claude API alias is claude-haiku-4-5. 200K context window. Retirement not sooner than 2026-10-15 per the deprecations page (that date has passed; the model is still listed Active and priced on 2026-10-17).
Specs
- Context window
- 200,000 tokens
- Max output
- 64,000 tokens
- Release date
- Provider
- Anthropic
- API model id
claude-haiku-4-5-20251001- Vercel AI Gateway id
anthropic/claude-haiku-4.5- Weights
- Closed weights
What Claude Haiku 4.5 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $1 = $20.00
- Output5M x $5 = $25.00
$45.00per day
$1,350.00 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 $0.10 = $0.09
- Uncached input0.1M x $1 = $0.10
- Output0.1M x $5 = $0.50
$0.69per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Claude Haiku 4.5 (this page) | $1 | $5 |
| Gemini Robotics ER 2 PreviewGoogle | $1 | $5 |
| GPT-5.4 MiniOpenAI | $0.75 | $4.50 |
| GLM-5.1Z.ai | $1.40 | $4.40 |
| GLM-5.2Z.ai | $1.40 | $4.40 |
| Claude Haiku 5.5Anthropic | $0.10 | $0.50 |
| Claude Sonnet 5Anthropic | $2 | $10 |
| Claude Sonnet 5.5Anthropic | $2 | $10 |
| Claude Sonnet 4.5Anthropic | $3 | $15 |
| Claude Sonnet 4.6Anthropic | $3 | $15 |
| Claude Opus 5.5Anthropic | $4 | $20 |
Compare
Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.
Related reading
- Claude Haiku 4.5: Near-Frontier Intelligence at a Fraction of the CostAnthropic's Claude Haiku 4.5 delivers Sonnet 4-level coding performance at one-third the cost and twice the speed. Here is what developers need to know.
- Claude Agent SDK in Late 2026: What Is New and How to Use ItWhat changed in the Claude Agent SDK by October 2026: nested subagents with caps, SessionStore, skills, plugins, structured outputs and permission defaults.
- Claude API OpenTelemetry Tracing: How to Set It Up (Beta)The Claude API now exports OpenTelemetry traces in beta. Set up SDK spans in code, add a Console destination for API spans, and count tokens once.
- Claude Code Idle Compaction: What It Does and How to Turn It OffClaude Code 2.1.299 compacts sessions over 200K tokens after about 54 idle minutes. How the cache math works, the setting to turn it off, and when to keep it.
- Tool Calling Under the Hood: Claude Messages vs OpenAI ResponsesHow tool calling works on the wire: JSON schema tools, parallel calls, tool_choice, strict mode and streaming deltas in Claude Messages vs OpenAI Responses.
- Claude Code Desktop SneakPeek Flaw: Fixed Version and What To DoSneakPeek (CVSS 8.7) let a poisoned HTML file read SSH keys and cloud credentials via the Claude Code Desktop preview pane. Fixed in Claude Desktop 1.30096.1.
FAQ
How much does Claude Haiku 4.5 cost per million tokens?
Claude Haiku 4.5 costs $1 per 1M input tokens and $5 per 1M output tokens on Anthropic's first-party API, per platform.claude.com on October 17, 2026. Per 1M tokens, cache reads cost $0.10, and the batch rate is $0.50 input and $2.50 output.
What is Claude Haiku 4.5's context window?
Claude Haiku 4.5 has a 200,000-token context window and returns up to 64,000 output tokens per response.
Are Claude Haiku 4.5's weights open?
No. Claude Haiku 4.5 is a closed-weights model. You call it through Anthropic's API as claude-haiku-4-5-20251001 or through Vercel AI Gateway as anthropic/claude-haiku-4.5.
When was Claude Haiku 4.5 released?
Anthropic released Claude Haiku 4.5 on October 15, 2025.
Sources
Last verified from platform.claude.com.
- https://platform.claude.com/docs/en/about-claude/pricing
- https://platform.claude.com/docs/en/models/haiku-4-5/overview
- https://platform.claude.com/docs/en/about-claude/models/overview
- https://platform.claude.com/docs/en/release-notes/overview
- https://platform.claude.com/docs/en/about-claude/model-deprecations
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.