Claude Haiku 4.5 pricing
Claude Haiku 4.5, Small-tier from inference.net, costs $1.00 per 1M input tokens and $5.00 per 1M output tokens.
Input$1.00per 1M tokens
Output$5.00per 1M tokens
Context window200Ktokens
TierSmallinference.net
Price your own workload against Claude Haiku 4.5 in the calculator →
Specs and pricing
| Provider | inference.net |
| Tier | Small |
| Context window | 200K tokens |
| Max output | 64K tokens |
| Input price | $1.00 / 1M tokens |
| Output price | $5.00 / 1M tokens |
| Cache read | $0.10 / 1M tokens |
| Modalities | text |
Note. Inference.net gateway price for Claude Haiku 4.5 (Anthropic), converted from the site's published per-token rate (costInputPerToken=0.000001, costOutputPerToken=0.000005 USD/token) to USD per 1M tokens: $1.0/1M input, $5.0/1M output, $0.1/1M cache read.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $1.00 | $1.25 | $2.25 |
| 10,000,000 in / 2,500,000 out | $10.00 | $12.50 | $22.50 |
| 100,000,000 in / 25,000,000 out | $100.00 | $125.00 | $225.00 |
Cheaper alternatives
Same tier (Small), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct-Turbo | DeepInfra | $0.02 | $0.04 | 98.7% cheaper blended |
| Solar Pro 4 | OpenRouter | $0.03 | $0.12 | 97.3% cheaper blended |
| GPT-OSS 20B | OpenRouter | $0.03 | $0.13 | 97.2% cheaper blended |
| Amazon Nova Micro | Amazon (Nova) | $0.035 | $0.14 | 96.9% cheaper blended |
| Llama 3.1 8B | OpenRouter | $0.05 | $0.08 | 96.9% cheaper blended |