Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance.
See the launch announcement and benchmark results hereOpens in new tab
#multimodal
Modalities
In / Out Price
$0.25 / $1.25per 1M
Context
200K
Released
Mar 13, 2024
Knowledge Cutoff
Aug 2023
This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | Claude 3 Haiku GPQA Diamond | 37.4% |
| Artificial Analysis | Claude 3 Haiku HLE | 4.1% |
| Artificial Analysis | Claude 3 Haiku IFBench | 36.1% |
| Artificial Analysis | Claude 3 Haiku τ²-Bench Telecom | 21.1% |
| Artificial Analysis | Claude 3 Haiku AA-LCR | 27.7% |
| Artificial Analysis | Claude 3 Haiku CritPt | 0.0% |
| Artificial Analysis | Claude 3 Haiku Terminal-Bench Hard | 0.8% |
| Artificial Analysis | Claude 3 Haiku AA-Omniscience Accuracy | 17.6% |
| Artificial Analysis | Claude 3 Haiku AA-Omniscience Non-Hallucination Rate | 19.5% |
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Token volume and request traffic to this model over time.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
| $0.25 | $1.25 | $0.03 | 0.43s | 56 tps |
Throughput
56tok/s
P50, best across providers
Latency
0.43s
P50, best provider
100.00%
99.95%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results here #multimodal
Claude 3 Haiku costs $0.25/M input tokens and $1.25/M output tokens, with separate rates for Cache Read at $0.03/M tokens, Cache Write at $0.30/M tokens, and Cache Write (1h) at $0.50/M tokens.
Claude 3 Haiku has a 200,000 token context window. It supports up to 4,096 completion tokens.
Yes. Claude 3 Haiku accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.
Claude 3 Haiku accepts text and images as input and returns text.
Claude Fable 5.1, Claude Opus 5, Claude Sonnet 5 and 11 more are other text models from Anthropic.
Claude 3 Haiku was released on March 13, 2024. Its knowledge cutoff is August 31, 2023.
