MODEL PROOF
Claude Haiku 4.5
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
Muse Spark 1.3 · Δ score 93.8 points · same measured price · $2.00 / 1M tokens
MiMo-V2.6-Pro is a further stored option with these losses: no file input
- Independent LMArena score
- 1,396.1 ± 2.43 · 143,402 votes
- Context window
- 200K
- Maximum output
- 64K
- Input modalities
- text, image, file
- Output modalities
- text
- Published input price
- $1.00 / 1M tokens
- Published output price
- $5.00 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Anthropic: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate.
Every price dimension · USD per million tokens
| Input | $1.00/M |
|---|---|
| Output | $5.00/M |
| Cached input | $0.100/M |
| Cache write | $1.25/M |
| Cache write 1h | $2.00/M |
| Reasoning | Unknown/M |
| Web search | $0.01/call |
| Batch discount | 50% |
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
8 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Azureazure/global Endpoint terms
| $1.00 | $5.00 | undeclared | 99.93% |
| Amazon Bedrockamazon-bedrock/global Endpoint terms
| $1.00 | $5.00 | undeclared | 99.95% |
| Googlegoogle-vertex/global Endpoint terms
| $1.00 | $5.00 | undeclared | 99.66% |
| Anthropicanthropic Endpoint terms
| $1.00 | $5.00 | undeclared | 99.96% |
| Amazon Bedrockamazon-bedrock/us Endpoint terms
| $1.10 | $5.50 | undeclared | 99.96% |
| Googlegoogle-vertex/us-east5 Endpoint terms
| $1.10 | $5.50 | undeclared | 100.00% |
| Amazon Bedrockamazon-bedrock/eu-west-1 Endpoint terms
| $1.10 | $5.50 | undeclared | 99.56% |
| Googlegoogle-vertex/europe Endpoint terms
| $1.10 | $5.50 | undeclared | 100.00% |
Independent scores
| LMArena Elo | 1396.1default |
|---|
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- ASCII art #44 1151
- SVG #79 1025
- Game development #84 1110
- Data visualisation #85 1131
- UI components #86 1107
- Code categories #87 1119
- Websites #89 1129
- 3D #90 1080
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 200K |
|---|---|
| Max output | 64K |
| Input modes | text, image, file |
| Tool use | yes |
| Reasoning | optional |
| Open weights | no |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | verified |
| Cross-checked | vendor page |
Our take
editorial — not a measurementHaiku is a candidate for classification, extraction and routing within a Claude-based stack. Check the exact context and output limits in the specification table before using it for large documents. Neither the family name nor an unsourced latency superlative establishes that it is the fastest or the right choice for a general assistant.
Strengths
- Tool use and reasoning support are listed
- Cache and batch pricing are recorded
Weaknesses
- Check both the context window and the output ceiling against the workload
- Safety behaviour and latency need task-specific evaluation
Reach for it when
- Classification and extraction evaluations
- Routing or triage ahead of a larger model
Avoid it if
- The required prompt or output exceeds the recorded limits
- The decision depends on a latency claim you have not tested
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...
Questions this page answers
What does Claude Haiku 4.5 cost?
$1.00/M in, $5.00/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Claude Haiku 4.5 have an independent quality score?
Claude Haiku 4.5 has an LMArena score in this catalogue.
What beats Claude Haiku 4.5?
Muse Spark 1.3 has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for Claude Haiku 4.5?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
MODEL MONUMENT
Save or share this proof
Badge
The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.
[](https://undominated.ai/models/anthropic__claude-haiku-4.5/)<a href="https://undominated.ai/models/anthropic__claude-haiku-4.5/"><img src="https://undominated.ai/badge/anthropic__claude-haiku-4.5.svg" alt="Claude Haiku 4.5 — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/anthropic__claude-haiku-4.5.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never
older than the last deploy.
