Claude Haiku 4.5
Claude Haiku 4.5 matches Claude Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds, making it a high-capability model in the Haiku line for high-throughput agentic deployments.
import { streamText } from 'ai'
const result = streamText({ model: 'anthropic/claude-haiku-4.5', prompt: 'Why is the sky blue?'})Playground
Try out Claude Haiku 4.5 by Anthropic. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
| 200K | 0.4s | 99tps | $1.00/M | $5.00/M | Read:$0.1/M Write: $1.25/M | $10.00/K + input costs | — | 10/15/2025 | ||||
| 200K | 0.9s | 115tps | $1.00/M | $5.00/M | Read:$0.1/M Write: $1.25/M | — | — | 10/15/2025 | ||||
| 200K | 1.0s | 99tps | $1.00/M | $5.00/M | Read:$0.1/M Write: $1.25/M | $10.00/K + input costs | — | 10/15/2025 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Anthropic
| Model |
|---|
| 1M | 0.8s | 97tps | $5.00/M | $25.00/M | Read:$0.5/M Write: $6.25/M | $10/K + input costs | — |    | 04/16/2026 | ||||
| 1M | 0.6s | 52tps | $3.00/M | $15.00/M | Read:$0.3/M Write: $3.75/M | $10/K + input costs | — | | 02/17/2026 | ||||
| 1M | 0.8s | 52tps | $5.00/M | $25.00/M | Read:$0.5/M Write: $6.25/M | $10/K + input costs | — | | 02/05/2026 | ||||
| 1M | 0.7s | 55tps | $3.00/M | $15.00/M | Read: $0.3/M Write: $3.75/M | $10.00/K + input costs | — | | 09/29/2025 | ||||
| 1M | 0.7s | 75tps | $3.00/M | $15.00/M | Read: $0.3/M Write: $3.75/M | $10.00/K + input costs | — | | 05/22/2025 | ||||
| 200K | 0.7s | 48tps | $5.00/M | $25.00/M | Read:$0.5/M Write: $6.25/M | $10.00/K + input costs | — | | 11/24/2024 |
About Claude Haiku 4.5
Claude Haiku 4.5 became available on Vercel AI Gateway on October 15, 2025. It matches Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds. Earlier Haiku generations told a similar story relative to their era's highest-tier release; Haiku 4.5 applies it to the Claude 4 generation.
Workloads that previously required a Sonnet 4 deployment can now be evaluated against Haiku 4.5. For organizations running large agent fleets or high-frequency pipelines, the cost differential between Haiku and Sonnet tiers compounds significantly at scale.
Access the model by setting the model string to anthropic/claude-haiku-4.5 in the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Through AI Gateway, you get built-in observability for tracking usage and cost, bring-your-own-key support, and intelligent provider routing across anthropic, bedrock, vertexAnthropic.
Haiku 4.5 inherits the Claude 4 generation's improvements in agentic task execution and instruction following. For teams building with the AI SDK v5, the integration requires only the model string update. No other code changes are needed for the common case.
What To Consider When Choosing a Provider
- Configuration: For agentic pipelines deploying Haiku 4.5 as a sub-agent alongside a larger orchestrating model, AI Gateway's per-request observability helps attribute token costs accurately across each pipeline stage.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Claude Haiku 4.5
Best For
- High-volume agentic pipelines: Cost per agent step is a primary architecture constraint and Sonnet 4-level capability is required at scale
- Computer use tasks: At throughput that Sonnet 4 pricing makes impractical
- Sub-agent roles: In multi-model pipelines, fast, capable, low-latency handling of defined subtasks
- Real-time user-facing features: Code completion, inline suggestions, and live chat where latency sensitivity rules out slower models
- Coding workflows: The benchmark parity with Sonnet 4 on coding tasks means no capability sacrifice
Consider Alternatives When
- Deepest reasoning tasks: Claude Sonnet 4.5 or Opus 4-tier models handle the most complex multi-step problem solving
- Extended or adaptive thinking: Thinking modes are essential in use cases beyond Haiku's scope
- Maximum context window: Check Haiku 4.5's context specs against tasks processing extremely large inputs
- Haiku-tier ceiling: Task profiles that exceed what a Haiku-tier model handles even with 4.5's improvements require a larger model
Conclusion
Haiku 4.5 changes the speed-cost tradeoff in agentic deployments. It matches a substantially more capable baseline (Sonnet 4) rather than serving as just the affordable option. If you run agent infrastructure at scale, benchmark this model against Sonnet-tier deployments you run in production before assuming you need an upgrade tier.
Frequently Asked Questions
What does it mean that Haiku 4.5 matches Sonnet 4 performance on coding and agent tasks?
Claude Haiku 4.5 delivers equivalent performance to Sonnet 4 on coding, computer use, and agent tasks at lower cost and faster speeds. Run your own benchmarks against your specific workloads to validate this for your use case.
How do I use Claude Haiku 4.5 in the AI SDK?
Set the model to
anthropic/claude-haiku-4.5in your AI SDK v5 integration. No other code changes are required for the common case.Which providers back Claude Haiku 4.5 on AI Gateway?
AI Gateway routes Haiku 4.5 through anthropic, bedrock, vertexAnthropic, with automatic failover for higher-than-provider-average uptime.
Does Claude Haiku 4.5 support computer use?
Yes. Claude Haiku 4.5 matches Sonnet 4's performance on computer use tasks.
What is the latency profile for Haiku 4.5 through AI Gateway?
AI Gateway surfaces live performance data on this page, including throughput and time-to-first-token metrics that update based on actual traffic.
Can I use Haiku 4.5 as a drop-in replacement for Sonnet 4 in my agent pipeline?
For coding, computer use, and agent tasks where benchmarks align, it may function as a drop-in with cost savings. Test against your specific workflows. General benchmark parity doesn't guarantee equivalent performance on every task profile.
What observability does AI Gateway provide for Haiku 4.5 usage?
AI Gateway tracks usage and cost per request, enabling cost attribution across pipeline stages and budget management without additional instrumentation.