Claude Haiku 4.5: API Pricing, Context Window & Benchmarks
Claude Haiku 4.5 is a language model from Anthropic, released in October 2025, with multimodal input, a 200K-token context window, and pricing from $1.00/M input and $5.00/M output.
Claude Haiku 4.5 is Anthropic's fastest, most cost-efficient model, matching Sonnet 4's performance on coding, computer use, and agent tasks. It offers similar performance to Sonnet 4 at one-third the cost and more than twice the speed,
Claude Haiku 4.5 benchmarks
Rankings
Quality Tracker
Claude Haiku 4.5 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sun Jul 19 2026Claude Haiku 4.5 pricing
Providers
Claude Haiku 4.5 starts at $1.00 per million input tokens and $5.00 per million output tokens via Anthropic. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|
 Anthropic | $1.00 | $5.00 | $1.50 | 200.0K/64.0K | 0.67/0.90 | 205/67 | 86.66%(4,304) | / |
 Vertex AI | $1.00 | $5.00 | $1.50 | 200.0K/64.0K | —/0.30 | 100/— | — | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
Claude Haiku 4.5 context window
Input and output token limits for Claude Haiku 4.5, plus how it ranks on long-context understanding.
Claude Haiku 4.5 API
Run a request to see the response
Use it in your code
Billed at $1.00 input / $5.00 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="claude-haiku-4-5-20251001",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
Claude Haiku 4.5 latency
Claude Haiku 4.5 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
Claude Haiku 4.5 examples
Recent arena outputs from Claude Haiku 4.5, picked from the highest-ranked matchups.
Claude Haiku 4.5 license
Claude Haiku 4.5 is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of February 2025.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- February 2025
Proprietary license - usage restrictions apply
Claude Haiku 4.5 resources
Official sources for Claude Haiku 4.5: api documentation, official playground, paper or system card, official launch post.
Claude Haiku 4.5 vs other models
The most-compared alternatives to Claude Haiku 4.5 are GPT OSS 120B High, Ministral 3 (8B Reasoning 2512), Qwen3 VL 32B Thinking. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Claude Haiku 4.5
Models ranked just above and below Claude Haiku 4.5 by LLM Stats score.
FAQ
Common questions about Claude Haiku 4.5.