geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
anthropic

Claude Opus 4.5

AI model Released

API mode
Chat*
Context window
200,000 tokens
Maximum output
64,000 tokens
Open weights
No

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Claude Opus 4.5 1450.9 claude-opus-4-5-20251101 · 95% interval 1447.8–1454.0 · 72,899 votes · 2026-10-15

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Claude Opus 4.5

Radar task score

Unrated

3/4 core tests · not enough evidence

5 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Claude Opus 4.5 86.0*% Approx. 95% interval: 82.0–90.1% · Older result

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Claude Opus 4.5 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Claude Opus 4.5 34.4*% Approx. 95% interval: 28.9–39.9%

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Claude Opus 4.5 45.7*% Approx. 95% interval: 42.6–48.8%

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Claude Opus 4.5 86.1*% Approx. 95% interval: 77.8–94.5% · Older result

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

Claude Opus 4.5 4.9*% Approx. 95% interval: 0.0–11.6%

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,469.79 rating

Confidence interval: 1,461.31 – 1,478.27

5403 votes

Category
chinese
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,466.83 rating

Confidence interval: 1,455.95 – 1,477.72

3043 votes

Category
chinese
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,503.58 rating

Confidence interval: 1,496.42 – 1,510.74

7804 votes

Category
coding
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference

1,498.58 rating

Confidence interval: 1,493.29 – 1,503.86

17986 votes

Category
coding
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,444.76 rating

Confidence interval: 1,436.51 – 1,453.00

5688 votes

Category
creative_writing
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference

1,442.71 rating

Confidence interval: 1,436.38 – 1,449.04

11412 votes

Category
creative_writing
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,460.63 rating

Confidence interval: 1,456.29 – 1,464.97

31213 votes

Category
english
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,455.80 rating

Confidence interval: 1,450.20 – 1,461.40

14874 votes

Category
english
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,449.30 rating

Confidence interval: 1,445.14 – 1,453.45

54101 votes

Category
exclude_ties
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,446.49 rating

Confidence interval: 1,441.23 – 1,451.75

27099 votes

Category
exclude_ties
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,487.25 rating

Confidence interval: 1,479.00 – 1,495.50

5688 votes

Category
expert
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,480.97 rating

Confidence interval: 1,468.96 – 1,492.98

2426 votes

Category
expert
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,470.77 rating

Confidence interval: 1,456.24 – 1,485.30

2026 votes

Category
french
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,457.02 rating

Confidence interval: 1,435.89 – 1,478.15

846 votes

Category
french
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,449.44 rating

Confidence interval: 1,431.28 – 1,467.59

1134 votes

Category
german
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,440.23 rating

Confidence interval: 1,417.14 – 1,463.31

666 votes

Category
german
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,476.14 rating

Confidence interval: 1,472.21 – 1,480.08

43250 votes

Category
hard_prompts
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,473.39 rating

Confidence interval: 1,468.37 – 1,478.41

20323 votes

Category
hard_prompts
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,481.76 rating

Confidence interval: 1,476.53 – 1,486.99

18759 votes

Category
hard_prompts_english
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,476.95 rating

Confidence interval: 1,469.80 – 1,484.09

7850 votes

Category
hard_prompts_english
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,448.35 rating

Confidence interval: 1,442.63 – 1,454.08

14098 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,433.57 rating

Confidence interval: 1,426.08 – 1,441.06

7032 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,434.10 rating

Confidence interval: 1,428.30 – 1,439.89

14080 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,425.71 rating

Confidence interval: 1,418.22 – 1,433.21

6931 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,459.02 rating

Confidence interval: 1,450.56 – 1,467.48

5431 votes

Category
industry_legal_and_government
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,454.28 rating

Confidence interval: 1,443.01 – 1,465.55

2775 votes

Category
industry_legal_and_government
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,453.62 rating

Confidence interval: 1,447.50 – 1,459.74

11580 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,447.90 rating

Confidence interval: 1,439.89 – 1,455.90

6047 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,468.59 rating

Confidence interval: 1,458.65 – 1,478.53

3778 votes

Category
industry_mathematical
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,459.40 rating

Confidence interval: 1,445.13 – 1,473.67

1669 votes

Category
industry_mathematical
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,443.59 rating

Confidence interval: 1,434.72 – 1,452.47

4920 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,431.05 rating

Confidence interval: 1,418.76 – 1,443.34

2425 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,483.21 rating

Confidence interval: 1,478.64 – 1,487.78

26901 votes

Category
industry_software_and_it_services
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,482.35 rating

Confidence interval: 1,476.42 – 1,488.28

12662 votes

Category
industry_software_and_it_services
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,451.35 rating

Confidence interval: 1,445.92 – 1,456.77

16912 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,444.79 rating

Confidence interval: 1,437.82 – 1,451.75

8580 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,478.01 rating

Confidence interval: 1,471.39 – 1,484.64

9887 votes

Category
instruction_following
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference

1,472.47 rating

Confidence interval: 1,467.52 – 1,477.42

21834 votes

Category
instruction_following
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,417.11 rating

Confidence interval: 1,385.49 – 1,448.74

378 votes

Category
japanese
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference

1,411.78 rating

Confidence interval: 1,387.37 – 1,436.20

640 votes

Category
japanese
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,423.59 rating

Confidence interval: 1,405.43 – 1,441.75

1170 votes

Category
korean
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,377.42 rating

Confidence interval: 1,352.36 – 1,402.48

581 votes

Category
korean
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,479.09 rating

Confidence interval: 1,474.19 – 1,483.99

24254 votes

Category
longer_query
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,478.48 rating

Confidence interval: 1,471.89 – 1,485.07

9839 votes

Category
longer_query
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,462.59 rating

Confidence interval: 1,450.52 – 1,474.67

2345 votes

Category
math
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference

1,458.16 rating

Confidence interval: 1,449.20 – 1,467.12

4547 votes

Category
math
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,466.18 rating

Confidence interval: 1,460.19 – 1,472.17

12968 votes

Category
multi_turn
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,460.39 rating

Confidence interval: 1,452.59 – 1,468.19

6510 votes

Category
multi_turn
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,437.52 rating

Confidence interval: 1,433.64 – 1,441.41

41682 votes

Category
non_english
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,435.40 rating

Confidence interval: 1,430.61 – 1,440.18

22629 votes

Category
non_english
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,450.88 rating

Confidence interval: 1,447.77 – 1,453.98

72899 votes

Category
overall
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,448.19 rating

Confidence interval: 1,444.37 – 1,452.02

37509 votes

Category
overall
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,438.74 rating

Confidence interval: 1,425.17 – 1,452.31

1891 votes

Category
polish
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,438.10 rating

Confidence interval: 1,420.32 – 1,455.88

1097 votes

Category
polish
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,447.38 rating

Confidence interval: 1,440.65 – 1,454.10

9053 votes

Category
russian
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

1,437.07 rating

Confidence interval: 1,428.39 – 1,445.76

4822 votes

Category
russian
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Claude Opus 4.5

1,457.21 rating

Confidence interval: 1,439.55 – 1,474.88

1147 votes

Category
spanish
Evaluated configuration
claude-opus-4-5-20251101-high-32k
Evaluation type
human preference

1,452.53 rating

Confidence interval: 1,439.01 – 1,466.05

2162 votes

Category
spanish
Evaluated configuration
claude-opus-4-5-20251101
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude Opus 4.5

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Claude Opus 4.5

Claude Opus 4.5 / Pricing tiers 5
Provider / scopeRateCurrencyAmount / unit
AWS BedrockClaude Opus 4.5Batch Global cross-region InputUSD2.5 / 1M tokens
OutputUSD12.5 / 1M tokens
AWS BedrockClaude Opus 4.5Standard Global cross-region Cached inputUSD0.5 / 1M tokens
InputUSD5 / 1M tokens
OutputUSD25 / 1M tokens
Google Vertex AIClaude Opus 4.5Batch Token tier: 0 – 200,000 Cached inputUSD0.25 / 1M tokens
InputUSD2.5 / 1M tokens
OutputUSD12.5 / 1M tokens
Google Vertex AIClaude Opus 4.5Standard Token tier: 0 – 200,000 Cached inputUSD0.5 / 1M tokens
InputUSD5 / 1M tokens
OutputUSD25 / 1M tokens
Google Vertex AIClaude Opus 4.5Standard Token tier: 200,000 – No stated upper limit Cached inputUSD0.55 / 1M tokens
InputUSD5.5 / 1M tokens
OutputUSD27.5 / 1M tokens

Capabilities

Context window
200,000 tokens
Maximum input
200,000 tokens*
Maximum output
64,000 tokens
Reasoning
Yes
Tool calling
Yes
Structured output
Yes*
Open weights
No
Knowledge cutoff
2025-05
API mode
Chat*
Image input
Yes*
PDF input
Yes*
Prompt caching
Yes*
Tool choice
Yes*
Model license
Proprietary

Input modalities

  • text
  • image
  • pdf

Output modalities

  • text

System configuration

Detailed specifications

Specifications · 28 fields
cache creation input token cost
6.25e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache creation input token cost above 1hr
1.0e-5*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache creation input token cost batches
3.125e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost
5.0e-7*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost batches
2.5e-7*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
5.0e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token batches
2.5e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
anthropic*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
200,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max output tokens
64,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
64,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
2.5e-5*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token batches
1.25e-5*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
prompt cache min tokens
4,096*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
search context cost per query
search_context_size_high
0.01*
search_context_size_low
0.01*
search_context_size_medium
0.01*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports assistant prefill
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports computer use
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports native structured output
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports output config
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports pdf input
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports prompt caching
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports response schema
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports thinking cache preservation
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports tool choice
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*

* Provisional data