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.
Workload (per month)
Anthropic: Claude Haiku 4.5
Pareto 26.9
Difference
Customer-support chatbot
50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens)
$175
$338
Anthropic: Claude Haiku 4.5 saves $163
RAG search over documents
20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens)
$170
$375
Anthropic: Claude Haiku 4.5 saves $205
Coding / tool-using agent
2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens)
$180
$390
Anthropic: Claude Haiku 4.5 saves $210
Batch summarisation
10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens)
$110
$245
Anthropic: Claude Haiku 4.5 saves $135
Long-document analysis
500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens)
$55.00
$133
Anthropic: Claude Haiku 4.5 saves $77.50
Capabilities side by side
Capability
Anthropic: Claude Haiku 4.5
Pareto 26.9
What it lets you do
Tool / function calling
✓ Yes
✓ Yes
call your APIs and run agent loops
Structured output (JSON schema)
✓ Yes
✓ Yes
return JSON that validates against your schema
Reasoning / thinking mode
✓ Yes
—
spend extra tokens thinking before answering hard problems
Image input
✓ Yes
✓ Yes
read screenshots, charts and scanned pages
Audio input
—
—
take speech or audio directly
File / PDF input
✓ Yes
—
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 Haiku 4.5: price unchanged since we started tracking it on 2026-03-10.
Pareto 26.9: price unchanged since we started tracking it on 2026-10-14.
Which should you choose?
Choose Anthropic: Claude Haiku 4.5 if…
cost matters at scale — it is 47% cheaper on a typical 3:1 input/output mix ($175 vs $338 a month for 50,000 support chats)
you need reasoning / thinking mode — to spend extra tokens thinking before answering hard problems; Pareto 26.9 does not advertise it
you need file / PDF input — to accept documents without your own parsing step; Pareto 26.9 does not advertise it
you need built-in web search — to answer from live web results; Pareto 26.9 does not advertise it
Choose Pareto 26.9 if…
you generate long outputs in one go — up to 131K tokens (about 98,300 words) per response
you want the newer model — released 2026-10-13, 12 months after the other
Frequently asked questions
Is Anthropic: Claude Haiku 4.5 better than Pareto 26.9?
Neither wins outright: Anthropic: Claude Haiku 4.5 is the pick when cost matters at scale, Pareto 26.9 when you generate long outputs in one go. In short: Anthropic: Claude Haiku 4.5 when cost matters at scale, you need reasoning / thinking mode, you need file / PDF input, you need built-in web search; Pareto 26.9 when you generate long outputs in one go, you want the newer model.
Which is cheaper, Anthropic: Claude Haiku 4.5 or Pareto 26.9?
Anthropic: Claude Haiku 4.5 is cheaper: $2.00 vs $3.75 per 1M tokens at a typical 3:1 input/output mix, 47% less. For 50,000 support conversations a month that is $175 against $338.
How much do Anthropic: Claude Haiku 4.5 and Pareto 26.9 cost per million tokens?
Anthropic: Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens; Pareto 26.9 costs $2.50 input and $7.50 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, Anthropic: Claude Haiku 4.5 or Pareto 26.9?
Pareto 26.9: 262K tokens, about 393 pages, against 200K (about 300 pages) for Anthropic: Claude Haiku 4.5.
Do Anthropic: Claude Haiku 4.5 and Pareto 26.9 support function calling and JSON output?
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.