Claude 3 Haiku API Pricing
Anthropic · Budget · Proprietary · released 2024-03. Prices in USD per 1 million tokens. Data snapshot: 2026-09-06.
Deprecated. The vendor has announced retirement of this model's API · shutdown 2026-04-19. It still carries a price because resellers still serve it; treat it as a model to migrate off, not one to start on.
- Input: $0.25 per 1M tokens
- Output: $1.25 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.03
- Context window: 200K
- Arena ELO: 1261 (as of 2026-09-01)
- Available on: Direct API, AWS Bedrock, Google Vertex, OpenRouter (curated by hand, verify with the provider)
- AWS Bedrock regions: ap-northeast-1, ap-northeast-2, ap-south-1, ap-southeast-1, ap-southeast-2, eu-central-1, eu-west-1, eu-west-3, us-east-1, us-east-2, us-west-2
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.0010 | $0.000802 | $80 |
| Knowledge Q&A | 2,000 / 800 | $0.0015 | $0.0012 | $119 |
| Meeting Summary | 10,000 / 1,200 | $0.0040 | $0.0038 | $378 |
| Marketing Content | 2,500 / 1,800 | $0.0029 | $0.0028 | $277 |
| Coding Task | 3,000 / 2,000 | $0.0033 | $0.0029 | $292 |
| Invoice Processing | 1,500 / 600 | $0.0011 | $0.0010 | $103 |
| Call Summary | 2,000 / 700 | $0.0014 | $0.0013 | $133 |
| Agent Workflow | 6,000 / 3,000 | $0.0052 | $0.0043 | $433 |
Claude 3 Haiku pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 1 host. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-06 via OpenRouter — negotiated rates, committed-use discounts and provisioned capacity are not shown.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Amazon Bedrock (the price shown above) | $0.25 | $1.25 |
Models comparable to Claude 3 Haiku
The nearest Budget models on Arena ELO, so a substitution is compared on quality as well as price.
- Phi 4 (Microsoft) — $0.07 in / $0.14 out per 1M, Arena ELO 1256
- Gemma 2 27B (Google) — $0.65 in / $0.65 out per 1M, Arena ELO 1289
- Llama 3.1 70B Instruct (Meta) — $0.40 in / $0.40 out per 1M, Arena ELO 1293
- Llama 3.1 8B Instruct (Meta) — $0.05 in / $0.08 out per 1M, Arena ELO 1211
Common questions about Claude 3 Haiku pricing
- How much does Claude 3 Haiku cost?
- Claude 3 Haiku costs $0.25 per million input tokens and $1.25 per million output tokens on the API.
- Does Claude 3 Haiku offer batch or cached pricing?
- Prompt-cache reads cost $0.03/M input tokens. No batch pricing is published.
- What would Claude 3 Haiku cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, Claude 3 Haiku costs about $100 at list prices.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for Claude 3 Haiku in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server