Claude Haiku 4.5

anthropic/claude-4.5-haiku-20251001

Claude Haiku 4.5 is an Anthropic model that accepts text, image, and file inputs and produces text output. It supports tool use and reasoning, offers a context window of 200 000 tokens, and is priced at $1 per million input tokens and $5 per million output tokens. The model is not open‑weights and was released on 2025‑10‑15.

  • tool use
  • structured outputs
  • reasoning

At a glance

provideranthropic
releasedOct 1, 2025
context200K
input / M$1

Specifications

What the API gives you

Context window
200K tokens
Max output
64K tokens
Input price
$1 / 1M tokens
Output price
$5 / 1M tokens
Cache read
$0.100 / 1M tokens
Modalities
text, image, file → text
Knowledge cutoff
Released
Oct 1, 2025

Measured evidence

Public benchmark record

BFCL
68.7%2026-07-28
BFCL
68.7%2026-07-27
BFCL
68.7%2026-07-29
BFCL
68.7%2026-07-31
BFCL
68.7%2026-07-30
BFCL
68.7%2026-08-02
BFCL
68.7%2026-08-01
BFCL
68.7%2026-08-05
BFCL
68.7%2026-08-03
BFCL
68.7%2026-08-09
BFCL
68.7%2026-08-04
BFCL
68.7%2026-08-06
BFCL
68.7%2026-08-07
BFCL
68.7%2026-08-14
BFCL
68.7%2026-08-10
BFCL
68.7%2026-08-08
BFCL
68.7%2026-08-18
BFCL
68.7%2026-08-11
BFCL
68.7%2026-08-15
BFCL
68.7%2026-08-12
BFCL
68.7%2026-08-13
BFCL
68.7%2026-08-19
BFCL
68.7%2026-08-16
BFCL
68.7%2026-08-20
BFCL
68.7%2026-08-27
BFCL
68.7%2026-08-17
BFCL
68.7%2026-08-21
BFCL
68.7%2026-08-22
BFCL
68.7%2026-08-23
BFCL
68.7%2026-08-24
BFCL
68.7%2026-09-05
BFCL
68.7%2026-08-28
BFCL
68.7%2026-08-25
BFCL
68.7%2026-08-26
BFCL
68.7%2026-09-06
BFCL
68.7%2026-08-29
BFCL
68.7%2026-08-30
BFCL
68.7%2026-08-31
BFCL
68.7%2026-09-01
BFCL
68.7%2026-09-02
BFCL
68.7%2026-09-03
BFCL
68.7%2026-09-04
Design Arena Coding
1145 Elo2026-07-28
Design Arena Coding
1145 Elo2026-07-27
Design Arena Coding
1145 Elo2026-07-30
Design Arena Coding
1145 Elo2026-07-29
Design Arena Coding
1145 Elo2026-07-31
Design Arena Coding
1144 Elo2026-08-02
Design Arena Coding
1143 Elo2026-08-05
Design Arena Coding
1144 Elo2026-08-01
Design Arena Coding
1142 Elo2026-08-09
Design Arena Coding
1144 Elo2026-08-03
Design Arena Coding
1144 Elo2026-08-04
Design Arena Coding
1140 Elo2026-08-14
Design Arena Coding
1143 Elo2026-08-06
Design Arena Coding
1142 Elo2026-08-10
Design Arena Coding
1144 Elo2026-08-07
Design Arena Coding
1134 Elo2026-08-18
Design Arena Coding
1143 Elo2026-08-08
Design Arena Coding
1134 Elo2026-08-15
Design Arena Coding
1142 Elo2026-08-11
Design Arena Coding
1141 Elo2026-08-12
Design Arena Coding
1140 Elo2026-08-13
Design Arena Coding
1133 Elo2026-08-19
Design Arena Coding
1139 Elo2026-08-27
Design Arena Coding
1133 Elo2026-08-20
Design Arena Coding
1134 Elo2026-08-16
Design Arena Coding
1131 Elo2026-09-05
Design Arena Coding
1134 Elo2026-08-17
Design Arena Coding
1139 Elo2026-08-21
Design Arena Coding
1139 Elo2026-08-22
Design Arena Coding
1140 Elo2026-08-23
Design Arena Coding
1139 Elo2026-08-28
Design Arena Coding
1140 Elo2026-08-24
Design Arena Coding
1140 Elo2026-08-25
Design Arena Coding
1140 Elo2026-08-26
Design Arena Coding
1131 Elo2026-09-06
Design Arena Coding
1139 Elo2026-08-29
Design Arena Coding
1138 Elo2026-08-30
Design Arena Coding
1138 Elo2026-08-31
Design Arena Coding
1139 Elo2026-09-01
Design Arena Coding
1137 Elo2026-09-02
Design Arena Coding
1135 Elo2026-09-03
Design Arena Coding
1134 Elo2026-09-04
Design Arena UI
1135 Elo2026-07-28
Design Arena UI
1136 Elo2026-07-27
Design Arena UI
1136 Elo2026-07-30
Design Arena UI
1136 Elo2026-07-29
Design Arena UI
1135 Elo2026-07-31
Design Arena UI
1136 Elo2026-08-02
Design Arena UI
1136 Elo2026-08-01
Design Arena UI
1135 Elo2026-08-05
Design Arena UI
1132 Elo2026-08-09
Design Arena UI
1136 Elo2026-08-03
Design Arena UI
1136 Elo2026-08-04
Design Arena UI
1131 Elo2026-08-14
Design Arena UI
1135 Elo2026-08-06
Design Arena UI
1135 Elo2026-08-07
Design Arena UI
1133 Elo2026-08-10
Design Arena UI
1133 Elo2026-08-08
Design Arena UI
1129 Elo2026-08-18
Design Arena UI
1133 Elo2026-08-11
Design Arena UI
1130 Elo2026-08-15
Design Arena UI
1133 Elo2026-08-12
Design Arena UI
1133 Elo2026-08-13
Design Arena UI
1129 Elo2026-08-19
Design Arena UI
1130 Elo2026-08-16
Design Arena UI
1129 Elo2026-08-20
Design Arena UI
1126 Elo2026-08-27
Design Arena UI
1129 Elo2026-08-17
Design Arena UI
1122 Elo2026-09-05
Design Arena UI
1126 Elo2026-08-21
Design Arena UI
1127 Elo2026-08-22
Design Arena UI
1127 Elo2026-08-23
Design Arena UI
1127 Elo2026-08-24
Design Arena UI
1126 Elo2026-08-28
Design Arena UI
1127 Elo2026-08-25
Design Arena UI
1127 Elo2026-08-26
Design Arena UI
1123 Elo2026-09-06
Design Arena UI
1126 Elo2026-08-29
Design Arena UI
1126 Elo2026-08-30
Design Arena UI
1126 Elo2026-08-31
Design Arena UI
1126 Elo2026-09-01
Design Arena UI
1125 Elo2026-09-02
Design Arena UI
1123 Elo2026-09-03
Design Arena UI
1122 Elo2026-09-04
Design Arena Website
1147 Elo2026-07-28
Design Arena Website
1147 Elo2026-07-30
Design Arena Website
1147 Elo2026-07-27
Design Arena Website
1147 Elo2026-07-29
Design Arena Website
1147 Elo2026-07-31
Design Arena Website
1146 Elo2026-08-02
Design Arena Website
1146 Elo2026-08-01
Design Arena Website
1146 Elo2026-08-05
Design Arena Website
1146 Elo2026-08-03
Design Arena Website
1145 Elo2026-08-09
Design Arena Website
1146 Elo2026-08-04
Design Arena Website
1142 Elo2026-08-14
Design Arena Website
1145 Elo2026-08-06
Design Arena Website
1146 Elo2026-08-07
Design Arena Website
1144 Elo2026-08-10
Design Arena Website
1145 Elo2026-08-08
Design Arena Website
1133 Elo2026-08-18
Design Arena Website
1145 Elo2026-08-11
Design Arena Website
1133 Elo2026-08-15
Design Arena Website
1144 Elo2026-08-12
Design Arena Website
1142 Elo2026-08-13
Design Arena Website
1133 Elo2026-08-19
Design Arena Website
1133 Elo2026-08-16
Design Arena Website
1133 Elo2026-08-20
Design Arena Website
1142 Elo2026-08-27
Design Arena Website
1133 Elo2026-08-17
Design Arena Website
1138 Elo2026-09-05
Design Arena Website
1142 Elo2026-08-21
Design Arena Website
1142 Elo2026-08-22
Design Arena Website
1142 Elo2026-08-23
Design Arena Website
1142 Elo2026-08-24
Design Arena Website
1142 Elo2026-08-28
Design Arena Website
1142 Elo2026-08-25
Design Arena Website
1143 Elo2026-08-26
Design Arena Website
1135 Elo2026-09-06
Design Arena Website
1142 Elo2026-08-29
Design Arena Website
1141 Elo2026-08-30
Design Arena Website
1141 Elo2026-08-31
Design Arena Website
1142 Elo2026-09-01
Design Arena Website
1140 Elo2026-09-02
Design Arena Website
1139 Elo2026-09-03
Design Arena Website
1138 Elo2026-09-04
LMArena Creative Writing
1372 Elo2026-07-21
LMArena Creative Writing
1371 Elo2026-07-27
LMArena Creative Writing
1371 Elo2026-07-30
LMArena Creative Writing
1372 Elo2026-08-02
LMArena Creative Writing
1372 Elo2026-08-03
LMArena Creative Writing
1372 Elo2026-08-06
LMArena Creative Writing
1373 Elo2026-08-12
LMArena Creative Writing
1373 Elo2026-08-21
LMArena Creative Writing
1372 Elo2026-09-02
LMArena Creative Writing
1372 Elo2026-08-27
LMArena Creative Writing
1372 Elo2026-09-01
LMArena Long Query
1427 Elo2026-07-21
LMArena Long Query
1427 Elo2026-07-27
LMArena Long Query
1427 Elo2026-07-30
LMArena Long Query
1427 Elo2026-08-02
LMArena Long Query
1427 Elo2026-08-03
LMArena Long Query
1427 Elo2026-08-06
LMArena Long Query
1427 Elo2026-08-12
LMArena Long Query
1428 Elo2026-08-21
LMArena Long Query
1427 Elo2026-09-02
LMArena Long Query
1427 Elo2026-08-27
LMArena Long Query
1428 Elo2026-09-01
LMArena Math
1393 Elo2026-07-21
LMArena Math
1393 Elo2026-07-27
LMArena Math
1393 Elo2026-07-30
LMArena Math
1393 Elo2026-08-02
LMArena Math
1393 Elo2026-08-03
LMArena Math
1393 Elo2026-08-06
LMArena Math
1393 Elo2026-08-12
LMArena Math
1393 Elo2026-08-21
LMArena Math
1393 Elo2026-09-01
LMArena Math
1393 Elo2026-08-27
LMArena Text
1412 Elo2026-07-21
LMArena Text
1412 Elo2026-07-27
LMArena Text
1412 Elo2026-07-30
LMArena Text
1412 Elo2026-08-10
LMArena Text
1412 Elo2026-08-02
LMArena Text
1412 Elo2026-08-06
LMArena Text
1412 Elo2026-08-03
LMArena Text
1413 Elo2026-08-21
LMArena Text
1413 Elo2026-08-12
LMArena Text
1413 Elo2026-09-01
LMArena Text
1413 Elo2026-09-02
LMArena Text
1413 Elo2026-08-27
LMArena WebDev
1327 Elo2026-07-16
LMArena WebDev
1327 Elo2026-07-21
LMArena WebDev
1327 Elo2026-07-20
LMArena WebDev
1324 Elo2026-07-27
LMArena WebDev
1324 Elo2026-07-24
LMArena WebDev
1325 Elo2026-07-28
LMArena WebDev
1325 Elo2026-07-30
LMArena WebDev
1325 Elo2026-08-01
LMArena WebDev
1325 Elo2026-07-31
LMArena WebDev
1325 Elo2026-08-06
LMArena WebDev
1325 Elo2026-08-02
LMArena WebDev
1326 Elo2026-08-12
LMArena WebDev
1326 Elo2026-08-10
LMArena WebDev
1326 Elo2026-08-14
LMArena WebDev
1329 Elo2026-09-01
LMArena WebDev
1329 Elo2026-09-05
LMArena WebDev
1327 Elo2026-08-21
LMArena WebDev
1328 Elo2026-08-30

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Frontend & UIEstablished evidence

    90% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    42% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.

  • 40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Search. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • 30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    26% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.

  • 20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.

  • 13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Reasoning or LMArena Vision. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsProvisional evidence

    5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

  1. #3Best LLM for Tool & Function Calling

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.