Claude Haiku 4.5
Claude Haiku 4.5 is Anthropic's small, fast model delivering near-frontier intelligence at low cost, excelling at coding and agentic tasks. Access it through Velokey's unified endpoint with below-list pricing.
Use cases
Real-time coding & pair programming · Sub-agent orchestration
Input
Text
Output
Text
Billing
Per token
Start a conversation
Type a message below to begin
Sign up to get $0.5 in free credits — about 20 free images
Pricing details
Transparent usage-based pricing with no hidden fees.
Detailed Pricing
Usage-based pricing breakdown
| Spec | Price | Official | Savings |
|---|---|---|---|
| Input/1M tokens | 0.8 Credits≈$0.8 | 1 Credits | -20% |
| Output/1M tokens | 4 Credits≈$4 | 5 Credits | -20% |
| Cache Read/1M tokens | 0.08 Credits≈$0.08 | 0.1 Credits | -20% |
| Cache Write/1M tokens | 1 Credits≈$1 | 1.25 Credits | -20% |
Billing Rules
- Output price varies by model, resolution, quality, duration, or token usage.
- Uploaded reference files may be charged separately when supported.
- Add-on capabilities such as web search or image search may be billed per request.
- Token-based models are billed by input and output tokens.
- If the primary route is unavailable, Velokey may automatically switch to a stable fallback route when possible.
- Usage is pay-as-you-go with transparent credit deduction.
* Final cost depends on the generated result.
Related models
Explore other models in the same family.
AnthropicSave 20%Claude Fable 5
Anthropic's Mythos-class frontier model, state-of-the-art across coding, agentic work, vision, and scientific research.
- AnthropicSave 20%
Claude Sonnet 5
Anthropic's agentic mid-tier model approaching Opus 4.8 quality at lower cost, built for planning, tool use, and autonomous coding.
- AnthropicSave 20%
Claude Opus 4.8
Anthropic's high-end large language model, suitable for complex code, long-form tasks, research, and high-reliability workflows.
- AnthropicSave 20%
Claude Opus 4.7
Claude Opus 4.7 is Anthropic's flagship large language model, excelling in complex reasoning and long-form analysis.
Affordable Claude Haiku 4.5 API
Access Anthropic's Haiku 4.5 on Velokey — near-frontier intelligence at small-model speed and cost, with extended thinking, vision, and a unified endpoint with below-list pricing for production apps.
Meet Claude Haiku 4.5 and its API access
Claude Haiku 4.5 is Anthropic's small, fast model released on October 15, 2025, bringing near-frontier intelligence at a fraction of the cost. It matches the coding of Claude Sonnet 4 from five months earlier, scores 73.3% on SWE-bench Verified, and reaches about 90% of Sonnet 4.5's agentic coding performance — at one-third the cost and more than twice the speed of Sonnet 4, and 4-5x faster than Sonnet 4.5. It supports extended thinking and vision, and even surpasses Sonnet 4 on some tasks like computer use. Velokey provides an affordable, easy-to-integrate Claude Haiku 4.5 API: a unified chat endpoint, a clear request flow, and below-list pricing for real-time apps, agent pipelines, and automation tools.
Fast, near-Sonnet-4 coding
Matches the coding quality of Sonnet 4, scores 73.3% on SWE-bench Verified, and reaches ~90% of Sonnet 4.5's agentic coding performance — at one-third the cost, fast enough to run on every keystroke.
View Documentation →
Low-latency, real-time speed
Runs more than 2x faster than Sonnet 4 and 4-5x faster than Sonnet 4.5, making it ideal for real-time chat, customer service, and responsive pair-programming experiences.
View Documentation →
Strong computer use
Even surpasses Sonnet 4 on some tasks like computer use, and with vision and a 128K extended thinking budget it drives multi-step agentic workflows.
View Documentation →
Cheap sub-agent orchestration
Cheap and fast enough to run many parallel workers — the ideal sub-agent in multi-agent systems where a frontier model plans and Haiku 4.5 executes at scale.
View Documentation →
How to deploy the Claude Haiku 4.5 API on Velokey
Get started with just a few steps.
Sign up and get an API Key
Sign in to the Velokey console to generate an API Key that authenticates every request sent to Claude Haiku 4.5.
Configure request parameters
Set model to claude-haiku-4-5 and submit messages. Enable extended thinking for harder reasoning and pass images for vision tasks.
Integrate and start calling
Send requests to Velokey's unified /v1/chat/completions endpoint to power real-time assistants, sub-agents, and automation, with usage managed in one console.
Real-world use cases for Claude Haiku 4.5
From real-time apps to multi-agent systems, covering many latency-sensitive scenarios.
Agentic coding & pair programming
Near-Sonnet-4 coding at high speed and low cost — fit for responsive pair programming, code completion, and agentic coding loops.
Real-time chat & customer service
Low-latency responses — fit for real-time chat, support assistants, and any experience where speed matters.
Sub-agent orchestration
Cheap and fast enough to run many parallel workers — fit as the sub-agent in multi-agent systems where a frontier model plans.
Computer use & vision tasks
Surpasses Sonnet 4 on some computer-use tasks and is vision-capable — fit for operating interfaces and processing images.
Rapid prototyping & experimentation
Fast and affordable — fit for rapid prototyping of new features and high-iteration experimentation.
High-volume classification & extraction
Low cost per token — fit for high-throughput classification, extraction, and routing where volume is large.
Why choose Velokey for Claude Haiku 4.5
Discount on list price
Call Claude Haiku 4.5 at a lower price on Velokey — pay-as-you-go with no forced subscription, reducing upfront cost.
Unified API interface
One API Key accesses Claude Haiku 4.5 and other models — no juggling multiple accounts and keys, simplifying integration.
Complete docs and migration guidance
Endpoint references, parameter details, and examples help you adopt extended thinking, vision, and sub-agent orchestration smoothly.
Stable and highly available
Automatic failover and stable fallback routes maintain availability when the primary route is down, keeping production reliable.
API Reference
Complete API call examples and parameter descriptions
Endpoint
https://api.velokey.ai/v1/messagesAuthentication
Bearer YOUR_API_KEYRequest Example
curl https://api.velokey.ai/v1/messages \
-X POST \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-haiku-4-5-20251001",
"messages": [{"role": "user", "content": "Hello!"}],
"temperature": 0.7
}'Response Example
{
"id": "req_abc123",
"model": "claude-haiku-4-5-20251001",
"created": 1234567890,
"data": { ... }
}Claude Haiku 4.5 API FAQ
How capable is Haiku 4.5 compared to larger models?
It brings near-frontier intelligence: coding on par with Sonnet 4 from five months earlier, 73.3% on SWE-bench Verified, and about 90% of Sonnet 4.5's agentic coding performance. It even surpasses Sonnet 4 on some tasks like computer use.
How fast and cheap is it?
Pricing is $1 input / $5 output per million tokens — one-third the cost of Sonnet 4. It runs more than 2x faster than Sonnet 4 and 4-5x faster than Sonnet 4.5, making it ideal for real-time, low-latency apps.
Does it support extended thinking and vision?
Yes. Haiku 4.5 supports a 128K extended thinking budget for harder reasoning and is vision-capable, so it can process images alongside text.
What is it best for?
Real-time low-latency apps such as chat, customer service, and pair programming; sub-agent orchestration in multi-agent systems; rapid prototyping; computer use; and agentic coding.
How is it billed on Velokey?
Official pricing is $1 input / $5 output per million tokens. This page's pricing area shows the current Velokey price, billed by input and output tokens with a discount on list price.
Start building with Claude Haiku 4.5 today
Use one API key to access low-cost, stable AI models through Velokey.