Claude Haiku 4.5 API pricing
9 providers serve Claude Haiku 4.5. Claude Haiku 4.5 is a proprietary API model, up to 200K context. Prices below are per 1M tokens, cheapest input first.
Refreshed 2026-08-23 · list prices from provider APIs| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context | |
|---|---|---|---|---|---|
| AWS Bedrock | $1.00 | $5.00output floor | $0.100 | 200K | Use |
| Azure AI Foundry | $1.00 | $5.00 | $0.100 | 200K | Use |
| Anthropic | $1.00 | $5.00 | $0.100 | 200K | Use |
| Databricks | $1.00 | $5.00 | - | 200K | Use |
| OpenRouter | $1.00 | $5.00 | $0.100 | 200K | Use |
| Replicate | $1.00 | $5.00 | - | - | Use |
| Vercel AI Gateway | $1.00 | $5.00 | $0.100 | 200K | Use |
| Google Vertex AI | $1.00 | $5.00 | $0.100 | 200K | Use |
| Snowflake | $1.00 | $5.00 | $0.100 | 200K | Use |
The cheapest way to run Claude Haiku 4.5
On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $220/month — the same at AWS Bedrock, Azure AI Foundry, Anthropic and 6 more. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.
Your actual monthly cost
Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.
Related models
| Model | Cheapest in $/1M | Cheapest out $/1M | Providers |
|---|---|---|---|
| Claude-3.7-Sonnet | $3.00 | $15.00 | 10 |
| Claude Sonnet 4 | $3.00 | $15.00 | 10 |
| Claude Sonnet 4.5 | $3.00 | $15.00 | 10 |
| Claude Opus 4 | $5.00 | $25.00 | 9 |
| Claude Opus 4.5 | $5.00 | $25.00 | 8 |
| Claude-3.5-Sonnet | $3.00 | $15.00 | 7 |
FAQ
What is the cheapest API for Claude Haiku 4.5?
As of 2026-08-23, the lowest input price for Claude Haiku 4.5, $1.00 per 1M tokens, is the same list price at AWS Bedrock, Azure AI Foundry, Anthropic and 6 more. The lowest output price, $5.00 per 1M tokens, is likewise shared by the same providers. The cheapest provider for a real workload depends on its input/output mix.
← All models · GPU rental prices · Breakeven calculator · Get this data as JSON