New Sign up free, 10 calls on us. Up to $1, no card needed.

Claude Haiku 4.5

Released 2025-10-15

chatCodeTool callingVisionPrompt cachingReasoning

Claude Haiku 4.5 is the speed tier of the current Claude lineup; Anthropic describes it as "the fastest model with near-frontier intelligence."

Input
text image $1/M
Output
text $5/M
Cache read
$0.1/M
Context
200K
vs GPT-4o
~80% cheaper
Knowledge cutoff
2025-02

Benchmarks

Above average0 / 6
Claude Haiku 4.5 other models measured peer average no peer scored higher
SWE-Bench Pro
39.5%
OSWorld-Verified
50.7%
GDPval-AA v2 Elo · 642-1861
907
GDM-MRCR v2 (8-needle) 128k (average)
35.3%
CharXiv (RQ) no tools
61.7%

Vendor-published: Alibaba (Qwen) Anthropic ByteDance Google Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 60 comparable models

Input$1/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$5/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.1/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 200,000
Max output (vendor spec) 64,000
Knowledge cutoff 2025-02
Training data through 2025-07 knowledge cutoff 2025-02

Prompt caching

How it caches explicit (opt-in)
Min prefix 4,096 provider default is 1,024
Lifetime 5m default, 1h option
Write cost 1.25x (5m) / 2x (1h)

Thinking

Vendor control thinking.type "enabled" + budget_tokens
Accepted values budget_tokens at least 1,024 and below max_tokens; "adaptive" returns 400
Default off, with no thinking unless the request sets it applied when the request sets nothing
Can be turned off Yes
Thinking behaviour Extended thinking only, with no effort parameter; earlier turns' thinking blocks are stripped, keeping only the last; interleaved thinking is unsupported, and the beta header is accepted but ignored.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image → text
  • Fastest Claude with near-frontier intelligence
  • extended thinking supported (not adaptive)
  • 200k context / 64k max output

per Anthropic official docs ↗

One prompt, measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

Claude Haiku 4.5 passed · 3 sentences

# Why Your LLM Bill Doubled Reasoning models like o1 and o3 process queries through extended chains of thought before responding, consuming 5-10x more tokens internally than standard models while also charging higher per-token rates. This means both your input token usage and per-unit costs increased simultaneously—a compounding effect that easily doubles overall spend. Unless you've significantly reduced queries to other models or have very selective reasoning deployment, the math makes a doubling entirely predictable.

out 106 tok latency 2.8 s

Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

Claude Haiku 4.5 passed · 8/8 cases

# Fixed Function ```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` # Bug Explanation The original function has two related bugs stemming from incorrect initialization and loop logic. First, `best` and `cur` start at 0, which causes single-element lists to incorrectly return 0 instead of 1—a run of one identical element should have length 1. Second, `cur` is reset to 0 (not 1) when a mismatch occurs, causing the next matching pair to be undercounted. More critically, if the longest run ends at the last index, `best` is only updated *during* the loop when a mismatch is encountered; if no mismatch follows the final run, `best` never captures it. […]

out 310 tok latency 4.0 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

Claude Haiku 4.5 passed · 5/5 fields, guidance null

```json { "company": "Meridian Robotics", "quarter": "Q3", "revenue_usd_m": 412, "growth_pct": 11, "guidance": null } ```

out 63 tok latency 1.6 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

Claude Haiku 4.5 passed · 123 words, 0 banned, 1 question

# Introducing Prompt Cache Across Providers We're excited to announce our latest API gateway feature: intelligent prompt caching that works across multiple AI providers. This powerful capability stores frequently used prompts and their contexts, dramatically reducing latency and API costs for your applications. By intelligently managing cached prompts across providers like OpenAI, Anthropic, and others, you can optimize your infrastructure without changing your code. Why wait for responses when cached results can be delivered instantly? The system automatically handles cache invalidation and updates, ensuring your applications always access current information while maintaining performance gains. With support for complex multi-turn conversations and dynamic content, this feature scales seamlessly with your business needs. […]

out 165 tok latency 3.0 s

Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.

Use Claude Haiku 4.5 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="claude-haiku-4-5",
    messages=[{"role": "user", "content": "Summarize this diff"}],
)
print(resp.choices[0].message.content)

About Claude Haiku 4.5

  • It offers the lowest latency and lowest price of any current Claude model, with a 200K-token context window, up to 64K output tokens, extended thinking support, vision input, tool use, and prompt caching.
  • Anthropic's own selection guide names its workloads as real-time applications, high-volume intelligent processing, cost-sensitive deployments that still need strong reasoning, and sub-agent tasks, and it anchors an explicitly efficiency-first adoption path: begin here, then upgrade only where a specific capability gap forces it.
  • Its thinking model is the older one and this matters when porting prompts.
  • It supports extended thinking only, with an explicit token budget that must sit above 1,024 and below the response limit; the adaptive thinking type returns an error, and there is no effort parameter.
  • Interleaved thinking is not supported either.
  • The beta header is accepted and ignored.
  • Prompt caching requires a 4,096-token minimum prefix, the most restrictive in the family, and thinking blocks from earlier turns are stripped rather than preserved.
  • Structured outputs are generally available, and the context window is fixed at 200K with no long-context variant.
  • That profile suits high-volume chat, classification, and coding assistants where responsiveness matters most.
  • Synthorai serves Claude Haiku 4.5 through its OpenAI-compatible chat endpoint, so switching is just a model-name change.

FAQ

Is the Claude Haiku 4.5 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $1/M input tokens, that credit alone covers roughly 125 requests of ~8K tokens against Claude Haiku 4.5.

What is Claude Haiku 4.5 best at?

Fastest with near-frontier intelligence; lowest latency and price in the current lineup; extended thinking, vision input, and prompt caching. See the About section for the full picture from the vendor's own release notes.

How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 costs $1 per million input tokens and $5 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.1/M.

Does Claude Haiku 4.5 support prompt caching?

Yes, via opt-in: mark stable prefixes with cache_control breakpoints. Cached input tokens bill at $0.1/M vs $1/M uncached; prompts need a 4,096-token stable prefix to cache (TTL 5m default, 1h option). Prompt caching guide →

How do I get access to Claude Haiku 4.5?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="claude-haiku-4-5", and you're done. One API key covers every model on the gateway.

What is Claude Haiku 4.5's knowledge cutoff?

Claude Haiku 4.5's knowledge cutoff is 2025-02, per the vendor's official documentation (as of 2026-07-09).

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →