AnthropicFastReleased 15 October 2025
Claude Haiku 4.5 pricing, context and benchmark
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.
200K
Input context
64K
Output context
$1
Official input
$5
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Claude Haiku 4.5 |
| Model ID | anthropic/claude-haiku-4.5 |
| Provider | Anthropic |
| Release date | 15 October 2025 |
| Status | Generally available |
| Input context | 200,000 tokens |
| Output context | 64,000 tokens |
| Official input pricing | $1 per 1M tokens |
| Official output pricing | $5 per 1M tokens |
| Cache read pricing | $0.1 per 1M tokens |
| Market input pricing | $1 per 1M (cheapest route) |
| Market output pricing | $5 per 1M (cheapest route) |
| Reasoning tokens | Billed as output at $5 per 1M |
| Input modalities | text · image · file |
| Output modalities | text |
| Reasoning control | Yes, effort levels exposed |
| Tool support | Functions, tool choice, structured outputs |
| Tokenizer | Claude |
| Provider routes | 8 endpoints |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $1 in |
| Image | ✓ yes | no | $1 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | ✓ yes | no | $1 in |
02 · Overview
What is Claude Haiku 4.5?
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.
Matching Claude Sonnet 4’s performance...
Claude Haiku 4.5 carries a 200K token window, uses the Claude tokenizer and is served by Anthropic. On Hoodgen it sits in the Fast tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released15 October 2025
| Property | Claude Sonnet 4.5 | Claude Haiku 4.5 | Change |
|---|---|---|---|
| Released | 2025 | 2025 | Same release window |
| Context | 1M | 200K | Changed |
| Max output | 64K | 64K | Unchanged |
| Input price | $3 | $1 | Cheaper |
| Output price | $15 | $5 | Cheaper |
| Input modalities | text, image, file | text, image, file | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◈
Thinking control
Reasoning effort can be dialled per request, so one model covers deep analysis and fast chat.
⚙
Function calling
Tools, tool choice and parallel calls, which is what agent loops need to act on results.
{ }
Structured outputs
Schema constrained JSON with response_format, so no parse and retry loop in your code.
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
▤
Files and PDFs
Documents go in as files rather than pasted text, keeping layout and tables intact.
⚡
Prompt caching
Cached input costs $0.1 per million instead of $1, so stable prefixes get cheaper.
05 · Reasoning
Thinking and reasoning capabilities
Claude Haiku 4.5 can think before answering and exposes the effort level per request. Reasoning tokens bill as output at $5 per million, and the trace can be returned with include_reasoning.
| Level | First token | Cost per task | Best for |
|---|---|---|---|
| Measured | n/a | n/a | Artificial Analysis measures the default reasoning configuration |
| Low effort | Faster | Lower | Chat, autocomplete, classification |
| High effort | Slower | Higher | Debugging, planning, multi step agents |
07 · Use cases
What can you do with Claude Haiku 4.5?
High volume drafts
Captions, titles, product blurbs and rewrite passes where cost per call dominates.
Inline assistants
Autocomplete, quick replies and menu helpers that must answer inside a second.
Batch classification
Tagging, routing and extraction across thousands of short inputs.
Cheap agent loops
Tool calling loops that do not need frontier grade reasoning.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.1 per million instead of $1. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Claude Haiku 4.5 pricing
Official pricing
List price
$1 / 1M in
$5 / 1M out
- $0.1 cached input
- 200K context
- text, image, file input
Cheapest route
$1 / 1M in
$5 / 1M out
- 8 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Azure | standard | $1 | $5 | $0.1 | 100.0% |
| Amazon Bedrock | standard | $1 | $5 | $0.1 | 100.0% |
| standard | $1 | $5 | $0.1 | 100.0% | |
| Anthropic | standard | $1 | $5 | $0.1 | 100.0% |
| Amazon Bedrock | standard | $1.1 | $5.5 | $0.11 | n/a |
| standard | $1.1 | $5.5 | $0.11 | 100.0% | |
| Amazon Bedrock | standard | $1.1 | $5.5 | $0.11 | 100.0% |
| standard | $1.1 | $5.5 | $0.11 | n/a |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0167 | $8.35 | 7933 |
| List price | $0.0167 | $8.35 | 7933 |
10 · Developers
API and developer information
| Model ID | anthropic/claude-haiku-4.5 |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | include_reasoning · max_completion_tokens · max_tokens · reasoning · response_format · stop · structured_outputs · temperature · tool_choice · tools · top_k · top_p |
| Streaming | Yes, server sent events |
| Modality string | text+image+file->text |
| Max prompt tokens | 200,000 |
| Max completion tokens | 64,000 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-haiku-4.5",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 64,000 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
| Depth ceiling | Fast tier: strong on throughput, weaker than flagship tiers on long multi step reasoning. |
12 · Comparison
Claude Haiku 4.5 vs other Anthropic models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Claude Haiku 4.5 | 200K | $1 | $5 | n/a | 2025 |
| Claude Opus 4.1 | 200K | $15 | $75 | n/a | 2025 |
| Claude Fable 5 | 1M | $10 | $50 | n/a | 2026 |
| Claude Fable 5.1 | 1M | $10 | $50 | 49 | Sep 2026 |
| Claude Fable 5.2 | 1M | $8 | $40 | n/a | 2026 |
| Claude Opus 4.5 | 200K | $5 | $25 | n/a | 2025 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Anthropic and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Claude Haiku 4.5 questions, answered
Claude Haiku 4.5 is a fast model from Anthropic, released 15 October 2025. Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.
✦
Start chatting with Claude Haiku 4.5
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.