Anthropic model product
Claude Haiku 4.5
5 is Anthropic's fastest and most cost-efficient model, with performance matching Sonnet 4 on coding, computer use, and agent tasks.
Updated Oct 23, 2026. Default version: Claude Haiku 4.5
LLMBoard Score43.8Claude Haiku 4.5
Coverage0%12 benchmark families
Context window200KTokens
Official input price$1Anthropic API
Claude Haiku 4.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Haiku 4.5 Benchmark Results
Benchmark scores for Claude Haiku 4.5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkCybersecurity CTFs | Score46.88% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMMMU (validation) | Score73.20% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkTau2 Retail | Score83.20% | Rank06 | Participants28 | Percentile81.48% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score41.00% | Rank07 | Participants25 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld | Score50.70% | Rank10 | Participants21 | Percentile55.00% | EvidenceC | Evaluated |
| BenchmarkTau2 Airline | Score63.60% | Rank12 | Participants26 | Percentile56.00% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score83.00% | Rank22 | Participants37 | Percentile41.67% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score31.01% | Rank26 | Participants29 | Percentile10.71% | EvidenceB | Evaluated |
| BenchmarkLM Arena Document | Score1,419.97 rating | Rank32 | Participants38 | Percentile16.22% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,418.73 rating | Rank36 | Participants38 | Percentile5.41% | EvidenceA | Evaluated |
| BenchmarkMMMLU | Score83.00% | Rank37 | Participants51 | Percentile28.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score73.30% | Rank52 | Participants120 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score80.70% | Rank75 | Participants122 | Percentile38.84% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,330.37 rating | Rank90 | Participants107 | Percentile16.04% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,418.40 rating | Rank101 | Participants131 | Percentile23.08% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,414.63 rating | Rank104 | Participants218 | Percentile52.53% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,396.98 rating | Rank116 | Participants218 | Percentile47.00% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score73.00% | Rank138 | Participants256 | Percentile46.27% | EvidenceC | Evaluated |
Claude Haiku 4.5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenadocument | Categoryoverall | Rank32 | Rating / score1,419.97 | Votes34,677 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank36 | Rating / score1,418.73 | Votes34,677 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank36 | Rating / score1,383.69 | Votes776 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank40 | Rating / score1,374.68 | Votes1,202 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank41 | Rating / score1,369.68 | Votes1,193 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank50 | Rating / score1,357.84 | Votes1,932 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank59 | Rating / score1,426.90 | Votes3,004 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank64 | Rating / score1,492.99 | Votes31,685 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank66 | Rating / score1,433.86 | Votes5,702 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank67 | Rating / score1,431.90 | Votes3,123 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank68 | Rating / score1,463.32 | Votes10,423 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank71 | Rating / score1,449.58 | Votes49,928 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank72 | Rating / score1,443.31 | Votes13,942 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank73 | Rating / score1,453.64 | Votes38,877 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank74 | Rating / score1,414.41 | Votes48,438 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank76 | Rating / score1,427.06 | Votes57,374 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank77 | Rating / score1,428.31 | Votes40,381 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank80 | Rating / score1,412.73 | Votes5,682 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank81 | Rating / score1,433.22 | Votes7,964 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank81 | Rating / score1,481.78 | Votes38,877 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank81 | Rating / score1,430.39 | Votes4,444 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank82 | Rating / score1,449.83 | Votes7,004 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank82 | Rating / score1,465.62 | Votes33,835 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank84 | Rating / score1,469.95 | Votes49,207 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank84 | Rating / score1,452.53 | Votes13,942 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank84 | Rating / score1,326.21 | Votes16,000 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank85 | Rating / score1,434.60 | Votes7,169 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank86 | Rating / score1,421.42 | Votes4,444 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank86 | Rating / score1,397.05 | Votes26,375 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank86 | Rating / score1,464.89 | Votes56,889 | ObservationsN/A | Result date |
Claude Haiku 4.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1 input, $5 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $0.14 input, $0.71 output per 1M via QiHang
- Tracked offerings
- 51
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderQiHang | Provider model IDclaude-haiku-4-5-20251001 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.71 | Context200K | Updated |
| ProviderXpersona | Provider model IDclaude-haiku-4-5 | Regionglobal | Input / 1M$0.60 | Output / 1M$3.7 | Context200K | Updated |
| ProviderPoe | Provider model IDanthropic/claude-haiku-4.5 | Regionglobal | Input / 1M$0.8586 | Output / 1M$4.29 | Context192K | Updated |
| ProviderCortecs | Provider model IDclaude-haiku-4-5 | Regionglobal | Input / 1M$0.996 | Output / 1M$4.98 | Context200K | Updated |
| ProviderOrcaRouter | Provider model IDanthropic/claude-haiku-4.5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderVertex | Provider model IDclaude-haiku-4-5@20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderImpossibl | Provider model IDanthropic/claude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderJiekou.AI | Provider model IDclaude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-haiku-4.5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-haiku-4-5@20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderDaoXE | Provider model IDclaude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderSnowflake Cortex | Provider model IDclaude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderAnthropic | Provider model IDclaude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderAnthropic | Provider model IDclaude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderDatabricks | Provider model IDdatabricks-claude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-haiku-4-5-20251001-v1:0 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderNEAR AI Cloud | Provider model IDanthropic/claude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-haiku-4.5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-haiku-4.5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderPerplexity Agent | Provider model IDanthropic/claude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderFreeModel | Provider model IDclaude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderOfox | Provider model IDanthropic/claude-haiku-4.5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderHelicone | Provider model IDclaude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderNeon | Provider model IDclaude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-haiku-4-5 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
| Provider302.AI | Provider model IDclaude-haiku-4-5-20251001 | Regionglobal | Input / 1M$1 | Output / 1M$5 | Context200K | Updated |
Claude Haiku 4.5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Haiku 4.5. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed100.00 tok/s | Catalog Latency0.30 s | Max Input200K | Max Output64K | Updated |
| ProviderVertex AI | Output Speed100.00 tok/s | Catalog Latency0.30 s | Max Input200K | Max Output64K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Haiku 4.5 Specifications
Technical details for the model's default version.
- Version
- Claude Haiku 4.5
- Released
- Oct 15, 2025
- Knowledge cutoff
- Feb 1, 2025
- Parameters
- N/A
- Context window
- 200K
- Max output
- 200K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Haiku 4.5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude Haiku 4.5 | Released | LLMBoard43.84 | ParametersN/A | Context200K | Max output200K | Open weightsNo | LicenseProprietary |
Models similar to Claude Haiku 4.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Opus 4
Anthropic
AN
Claude Sonnet 4
Anthropic
AN
Claude Opus 4.1
Anthropic
AN
Claude Sonnet 3.7
Anthropic
AN
Claude Sonnet 4.5
Anthropic
AN
Claude Sonnet 3.5
Anthropic
What is Claude Haiku 4.5?
Key information about Claude Haiku 4.5 and its available data.
5 is an Anthropic large language model. It offers performance similar to Sonnet 4 at one-third the cost and more than twice the speed.
Data as of 2026-10-22.
FAQ
Common questions about Claude Haiku 4.5.
When was Claude Haiku 4.5 released?
Claude Haiku 4.5's default version was released on Oct 15, 2025.
How much does Claude Haiku 4.5 cost?
Claude Haiku 4.5's official API price is $1 per million input tokens and $5 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.14 input and $0.71 output via QiHang.
Who created Claude Haiku 4.5?
Claude Haiku 4.5 was created by Anthropic.
What is the context window for Claude Haiku 4.5?
The default version has a 200K token context window.
Is Claude Haiku 4.5 open weight?
No. The default version is not marked as having publicly available weights.