RentGPU RentGPU
GPU finden →
by Anthropic

Anthropic: Claude 3 Haiku.

multimodal closed 200K ctx
Cheapest input
$0.25/M
on Anthropic API
Cheapest output
$1.25/M
on Anthropic API
Fastest
65 tok/s
on OpenRouter
Hosted equiv.
~$0.45/hr
@ 100 tok/s on Anthropic API

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/n

Hosted API only

No self-host path — closed weights.

Anthropic: Claude 3 Haiku's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Anthropic API api direct $0.25 $1.25 Launch ↗
OpenRouter api aggregator $0.25 $1.25 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 64.7 632 ms 2334 ms
FAQ

Frequently asked.

How do I run Anthropic: Claude 3 Haiku?
Anthropic: Claude 3 Haiku is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Anthropic: Claude 3 Haiku?
Anthropic: Claude 3 Haiku is available via Anthropic API, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Anthropic: Claude 3 Haiku?
API pricing starts at $0.25/M input tokens and $1.25/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Anthropic: Claude 3 Haiku open-source or proprietary?
Anthropic: Claude 3 Haiku is a proprietary model from Anthropic. Access is API-only — there are no public weights to download.