by Anthropic
Claude 3.5 Haiku.
text
closed
200K ctx
Cheapest input
$0.8/M
on OpenRouter
Cheapest output
$4.0/M
on OpenRouter
Hosted equiv.
~$1.44/hr
@ 100 tok/s on OpenRouter
Fast/cheap Claude 3.5 variant — production fallback for Haiku 4.5.
Hosted API only
No self-host path — closed weights.
Claude 3.5 Haiku's weights aren't published. Use it via the access providers below.
Where to use it
Cheapest hosted endpoints.
Family
Claude Opus 4.7
Claude Sonnet 4.6
Claude 3.5 Sonnet
Claude Haiku 4.5
Variants in the Claude family.
closed
proprietary
Frontier reasoning and long-form coding from Anthropic.
closed
proprietary
Best price-performance from Anthropic. Default for production agents.
closed
proprietary
Anthropic's 3.5 generation — still in active production.
closed
proprietary
Fast, cheap Claude variant for high-throughput inference.
FAQ
Frequently asked.
How do I run Claude 3.5 Haiku?
Claude 3.5 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 Claude 3.5 Haiku?
Claude 3.5 Haiku is available via Anthropic API, AWS Bedrock, Google Vertex AI, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Claude 3.5 Haiku?
API pricing starts at $1.0/M input tokens and $5.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Claude 3.5 Haiku open-source or proprietary?
Claude 3.5 Haiku is a proprietary model from Anthropic. Access is API-only — there are no public weights to download.
API pricing
Per provider
What it costs per month across providers.
Estimate your monthly bill for Claude 3.5 Haiku across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest
$16.0
OpenRouter
Most expensive
$20.0
Google Vertex AI
Spread
$4.0
max − min
Providers
4
with priced rows
Monthly bill
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Loading...
Bill breakdown.
Full calculator
Want to compare token volumes across other models too?
Open the standalone API pricing tool →
Context window
How much it can remember.
200K tokens
≈ 150,000 English words
4K
32K
128K
1M
Max output per call: 8K tokens
Capabilities
What it can do.
·
Vision input
·
Audio input
·
Video input
✓
Function calling
✓
Tool use
·
JSON mode
✓
Streaming
·
Fine-tuning