Anthropic's fastest model. Ultra-low latency for real-time applications and high-volume tasks.
Context Window
200K
tokens
Max Output
8K
tokens
Input Price
$0.8
per 1M tokens
Output Price
$4
per 1M tokens
Speed
172
tokens/sec
Released
Oct 2024
2024-10-22
Blended Cost
$2.40
per 1M tokens
Value Score
31.3
quality per $
Capabilities
ChatVisionCode GenerationFunction Calling
Benchmarks
Quality Index
75
MMLU Pro
84.2
HumanEval (Coding)
88.1
MATH
69.3
Arena ELO
1230
Price vs Quality
Cheaper is left, more capable is up. 21 of 69 priced models are both cheaper and score at least as high. Self-host models are left off the price axis — their cost depends on the hardware you run them on, not on tokens.
Context Window in Context
Codestral256K
▸ Claude 3.5 Haiku200K
o3 Mini200K
o3200K
Claude Opus 4200K
Claude Sonnet 4200K
Sonar Pro200K
GLM-5.1200K
Bar length is logarithmic — each full step is 10× the tokens. Shown against the models with the nearest context windows, not the directory extremes.
Claude 3.5 Haiku is a fast AI model by Anthropic, released on October 22, 2024. It supports a context window of 200K tokens and can generate up to 8K output tokens.
At $0.8 per million input tokens and $4 per million output tokens, its blended cost of $2.40/1M tokens puts it in the mid-range pricing tier. Its value score of 31.3 reflects the balance of quality and cost.
Using Claude 3.5 Haiku with Swfte
Access Claude 3.5 Haiku through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Claude 3.5 Haiku in our AI Playground before integrating.
Deploy a model with Swfte Connect
One gateway, every provider, per-token cost visibility. Swap models without touching your code.