Claude 3.5 Haiku is a retired model. This page preserves historical API pricing and specifications. For new integrations, consider Claude Haiku 4.5. (2026-02-19)
Claude 3.5 Haiku API pricing
Retired fast and affordable Anthropic model. This page preserves its historical API pricing and specifications.
How much does Claude 3.5 Haiku API cost?
The historical price recorded for Claude 3.5 Haiku is $0.80 per 1 million input tokens and $4.00 per 1 million output tokens. It is not a current TokenGate price.
| Model | Input tokens / 1M | Cached input / 1M | Output tokens / 1M |
|---|---|---|---|
| Claude 3.5 Haiku | $0.80 | — | $4.00 |
Model specifications
- Provider
- Anthropic
- API model identifier
- claude-3-5-haiku-20241022
- Generation
- 3.5
- Provider lifecycle
- Retired
- Context window
- 200K
- Maximum output tokens
- 8K
- Input modalities
- Text, Image
- Output modalities
- Text
- Capabilities
- Streaming, Function calling, Vision, JSON mode
Best for
- High volume
- Cost sensitive
Looking for the current replacement?
Claude 3.5 Haiku → Claude Haiku 4.5
Anthropic's fast and cost-efficient Haiku model for high-volume workloads and lightweight agentic tasks.
View replacement pricingFrequently asked questions
Related models
Claude Haiku 4.5
Anthropic's fast and cost-efficient Haiku model for high-volume workloads and lightweight agentic tasks.
- Input / 1M
- $1.00
- Output / 1M
- $5.00
- Context
- —
- Generation
- 4.5
Streaming · Function calling · Vision
Claude Haiku 4.5 API pricingGPT-5.6 Luna
Cost-focused GPT-5.6 model for high-volume workloads, routine automation and applications where API efficiency matters.
- Input / 1M
- $0.20
- Output / 1M
- $1.20
- Context
- 1.05M
- Generation
- 5.6
Streaming · Function calling · Structured outputs
GPT-5.6 Luna API pricingGemini 3.5 Flash-Lite
Google's cost-efficient model for high-volume agentic tasks, translation and simple data processing.
- Input / 1M
- $0.30
- Output / 1M
- $2.50
- Context
- —
- Generation
- 3.5
Streaming · Function calling · Structured outputs
Gemini 3.5 Flash-Lite API pricingTokenGate