Capabilities
7-day heat trend
+2.2%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 43% of tracked models
- Faster than 48% of tracked models
- Efficiency rank: #143 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About anthropic/claude-3-5-haiku-latest
Vercel AI Gateway route for Claude 3.5 Haiku, preserving upstream provider and model identity for supplier catalog prefill.
anthropic/claude-3-5-haiku-latest is a Text model from Vercel AI Gateway (US). HotON.ai tracks it at $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 200K-token context window, ~147 tokens/sec throughput and 99.8% availability. Its composite efficiency score is 90/100 at an estimated $0.000 per successful task.
Compare anthropic/claude-3-5-haiku-latest
Related market news
Frequently asked questions
How much does anthropic/claude-3-5-haiku-latest cost per 1M tokens?+
anthropic/claude-3-5-haiku-latest is tracked at $0.00 per 1M input tokens and $0.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.00 per 1M tokens. Figures are illustrative demo data.
What is anthropic/claude-3-5-haiku-latest best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is anthropic/claude-3-5-haiku-latest?+
anthropic/claude-3-5-haiku-latest delivers about 147 tokens/sec with 99.8% tracked availability, suitable for latency-sensitive, real-time applications.
Is anthropic/claude-3-5-haiku-latest cheaper than other AI models?+
Within the HotON.ai tracked set, anthropic/claude-3-5-haiku-latest is cheaper than 43% of models on input price and ranks #143 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.