Claude Haiku 4.5
Claude Haiku 4.5 is Anthropic's small, fast model, built for real-time chat assistants, pair programming, and cost-sensitive workloads where responsiveness matters.
input · usd / 1m tok
$1.00
output · usd / 1m tok
$5.00
context window
200ktokens
modalities · in → out
takes text and image in, gives text out
pricing
base api ratesusd per 1m tokens
- input
- $1.00
- output
- $5.00
- cache read
- $0.10
- cache write · default ttl
- $1.25
- cache write · 1h ttl
- $2.00
providers
Different companies host Claude Haiku 4.5. Impossibl routes your request intelligently and handles failover automatically when a provider is down.
- Azure AI Foundry
- Amazon Bedrock
- Anthropic
specifications
takes text and image in, gives text outanthropic/claude-haiku-4-5
- creatorAnthropic
- model typeText generation
- context window200,000 tokens
- maximum outputnot published
- input
takes text and image in, gives text out
- outputtext
- tool callingnot verified
- releasedoct 15, 2025
- endpoint
/v1/chat/completions
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
try it · your prompt, this model, live
# responses API
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["IMPOSSIBL_API_KEY"],
base_url="https://api.impossibl.com/v1",
)
resp = client.responses.create(
model="anthropic/claude-haiku-4-5",
input="",
)
print(resp.output_text)
edit the prompt, then run
benchmarks
intelligence index
15.4#89 of 113 models on the gateway
- omniscience-7.6#50 of 90
- gpqa64.6%#74 of 82
- humanity’s last exam4.2%#84 of 93
- GPQA64.6%
- MMMU-Pro55.1%
- LiveCodeBench51.1%
- AA-LCR49.7%
- IFBench42.0%
- AIME 202539.0%
- Tau232.5%
- Terminal-Bench Hard27.3%
- Humanity’s Last Exam4.2%
- CritPt0.0%
- Intelligence Index15.41
- Omniscience Index-7.57
- intelligence index (API)15.4
each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-22.
compare Claude Haiku 4.5 with other models
frontier labs and open weights, best-ranked firstusd / 1m tok · in / out
- moonshotai/kimi-k3.1-pro$2.00 / $10.00compare →
- openai/gpt-6-astra$10.00 / $50.00compare →
- google/gemini-4-argon$2.00 / $10.00compare →
- meta/muse-wonder$4.00 / $20.00compare →
frequently asked questions
What is Claude Haiku 4.5?
Claude Haiku 4.5 is Anthropic's small, fast model, built for real-time chat assistants, pair programming, and cost-sensitive workloads where responsiveness matters. It brings near-frontier coding and computer-use ability to the Haiku tier, supports extended thinking, and works well as a subagent handling parallel subtasks orchestrated by a larger Claude model.
How much does Claude Haiku 4.5 cost?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens through the Impossibl API. Cache reads cost $0.10 per million tokens; cache writes cost $1.25 per million tokens; cache writes with one-hour retention cost $2.00 per million tokens. All rates are in USD.
What is the context length of Claude Haiku 4.5?
Claude Haiku 4.5 has a 200,000-token context window through the Impossibl API.
What inputs and outputs does Claude Haiku 4.5 support?
Claude Haiku 4.5 accepts text and image as input. Claude Haiku 4.5 returns text.
How do I use Claude Haiku 4.5 through an API?
Claude Haiku 4.5 is available through the Impossibl API. Use anthropic/claude-haiku-4-5 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.
When was Claude Haiku 4.5 released?
Anthropic released Claude Haiku 4.5 on October 15, 2025.
this page describes Claude Haiku 4.5 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.
view the source catalog ↗model as markdown ↗report a correction →