Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
spend extra tokens thinking before answering hard problems
Image input
✓ Yes
—
read screenshots, charts and scanned pages
Audio input
—
—
take speech or audio directly
File / PDF input
—
—
accept documents without your own parsing step
Image output
—
—
generate images, not just text
Built-in web search
✓ Yes
—
answer from live web results
Seed (reproducible sampling)
—
—
repeat a generation for tests and evals
Log-probabilities
—
—
read token confidence for classification and scoring
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Price history
Anthropic: Claude 3.5 Haiku: price unchanged since we started tracking it on 2026-03-10.
Which should you choose?
Choose Anthropic: Claude 3.5 Haiku if…
you need tool / function calling — to call your APIs and run agent loops; sentence-transformers-testing/stsb-bert-tiny-safetensors does not advertise it
you need image input — to read screenshots, charts and scanned pages; sentence-transformers-testing/stsb-bert-tiny-safetensors does not advertise it
you need built-in web search — to answer from live web results; sentence-transformers-testing/stsb-bert-tiny-safetensors does not advertise it
No advantage on the data we track — pick it for provider preference or output quality on your own prompts.
Frequently asked questions
Is Anthropic: Claude 3.5 Haiku better than sentence-transformers-testing/stsb-bert-tiny-safetensors?
Anthropic: Claude 3.5 Haiku comes out ahead on the data we track: 3 advantages and none for sentence-transformers-testing/stsb-bert-tiny-safetensors.
Do Anthropic: Claude 3.5 Haiku and sentence-transformers-testing/stsb-bert-tiny-safetensors support function calling and JSON output?
Tool calling — Anthropic: Claude 3.5 Haiku: yes, sentence-transformers-testing/stsb-bert-tiny-safetensors: not advertised. JSON-schema structured output — Anthropic: Claude 3.5 Haiku: not advertised, sentence-transformers-testing/stsb-bert-tiny-safetensors: not advertised.
Can Anthropic: Claude 3.5 Haiku or sentence-transformers-testing/stsb-bert-tiny-safetensors read images?
Only Anthropic: Claude 3.5 Haiku accepts image input; sentence-transformers-testing/stsb-bert-tiny-safetensors is text-only for input.
Is Anthropic: Claude 3.5 Haiku or sentence-transformers-testing/stsb-bert-tiny-safetensors free to use?
No free variant is listed for either; both are pay-per-token.
Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.
This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.
This model is currently pointing to [Claude 3.5 Haiku (2024-10-22)](/anthropic/claude-3-5-haiku-20241022).