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 4.7

AI model Released

API mode
Chat*
Context window
1,000,000 tokens
Maximum output
128,000 tokens
Open weights
No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Claude Opus 4.7 156.7* Claude Opus 4.7 · 95% interval 155.0–158.9

Human preference · Arena

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

Claude Opus 4.7 1483.0 Claude Opus 4.7 · 95% interval 1479.2–1486.7 · 66,140 votes · 2026-10-28

Model performance

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

Claude Opus 4.7

Radar task score

Unrated

3/4 core tests · not enough evidence

6 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

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

Claude Opus 4.7 86.4*% Approx. 95% interval: 81.6–91.2%

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 4.7 28.0*% Approx. 95% interval: 19.2–36.8%

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Claude Opus 4.7 70.2*% Approx. 95% interval: 64.9–75.5%

Factual answers

SimpleQA Verified · 25%

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

Claude Opus 4.7 Not available

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 4.7 86.7*% Approx. 95% interval: 76.6–96.7%

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 4.7 31.7*% Approx. 95% interval: 17.3–46.1%

Visual spatial reasoning

Furniture Assembly · Separate result

Assembly-error detection from photos and manuals, with zoom and Python tools. Uses model-assisted grading; not a general vision score.

Claude Opus 4.7 33.3*% Approx. 95% interval: 21.3–45.4%

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 · 2026-10-28 · rating

Claude Opus 4.7

1,531.27 rating

Confidence interval: 1,521.45 – 1,541.10

4172 votes

Category
chinese
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,530.99 rating

Confidence interval: 1,520.98 – 1,540.99

4117 votes

Category
chinese
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,518.73 rating

Confidence interval: 1,512.92 – 1,524.53

18587 votes

Category
coding
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,514.78 rating

Confidence interval: 1,509.01 – 1,520.54

18788 votes

Category
coding
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,486.03 rating

Confidence interval: 1,479.15 – 1,492.91

11769 votes

Category
creative_writing
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,480.11 rating

Confidence interval: 1,473.28 – 1,486.95

11982 votes

Category
creative_writing
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,496.21 rating

Confidence interval: 1,491.32 – 1,501.10

30177 votes

Category
english
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,487.00 rating

Confidence interval: 1,482.15 – 1,491.86

30510 votes

Category
english
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,501.67 rating

Confidence interval: 1,496.78 – 1,506.56

49624 votes

Category
exclude_ties
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,492.06 rating

Confidence interval: 1,487.21 – 1,496.91

50617 votes

Category
exclude_ties
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,519.74 rating

Confidence interval: 1,511.76 – 1,527.72

7075 votes

Category
expert
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference

1,519.17 rating

Confidence interval: 1,511.16 – 1,527.17

6918 votes

Category
expert
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,502.88 rating

Confidence interval: 1,488.68 – 1,517.08

2292 votes

Category
french
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,497.46 rating

Confidence interval: 1,483.39 – 1,511.53

2367 votes

Category
french
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,496.51 rating

Confidence interval: 1,477.64 – 1,515.38

1022 votes

Category
german
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,485.59 rating

Confidence interval: 1,466.54 – 1,504.64

1043 votes

Category
german
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,505.65 rating

Confidence interval: 1,501.22 – 1,510.08

43653 votes

Category
hard_prompts
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,499.53 rating

Confidence interval: 1,495.07 – 1,503.98

44330 votes

Category
hard_prompts
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,508.14 rating

Confidence interval: 1,502.52 – 1,513.75

20836 votes

Category
hard_prompts_english
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,500.61 rating

Confidence interval: 1,495.05 – 1,506.16

21134 votes

Category
hard_prompts_english
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,490.30 rating

Confidence interval: 1,483.88 – 1,496.71

13043 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,477.62 rating

Confidence interval: 1,471.23 – 1,484.02

13228 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,473.74 rating

Confidence interval: 1,467.41 – 1,480.06

15117 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,466.62 rating

Confidence interval: 1,460.41 – 1,472.83

15527 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,504.40 rating

Confidence interval: 1,495.42 – 1,513.39

5251 votes

Category
industry_legal_and_government
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,489.09 rating

Confidence interval: 1,480.26 – 1,497.93

5430 votes

Category
industry_legal_and_government
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,507.58 rating

Confidence interval: 1,500.87 – 1,514.30

11046 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,497.47 rating

Confidence interval: 1,490.75 – 1,504.19

11184 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,509.69 rating

Confidence interval: 1,499.12 – 1,520.25

3661 votes

Category
industry_mathematical
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,495.39 rating

Confidence interval: 1,485.11 – 1,505.67

3840 votes

Category
industry_mathematical
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,495.33 rating

Confidence interval: 1,486.10 – 1,504.56

4955 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,490.44 rating

Confidence interval: 1,481.20 – 1,499.68

4995 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,516.19 rating

Confidence interval: 1,511.07 – 1,521.30

26193 votes

Category
industry_software_and_it_services
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,506.00 rating

Confidence interval: 1,500.88 – 1,511.13

26493 votes

Category
industry_software_and_it_services
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,492.47 rating

Confidence interval: 1,486.44 – 1,498.49

16555 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,479.39 rating

Confidence interval: 1,473.42 – 1,485.36

16953 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,497.87 rating

Confidence interval: 1,492.47 – 1,503.27

22726 votes

Category
instruction_following
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,488.47 rating

Confidence interval: 1,483.14 – 1,493.81

23274 votes

Category
instruction_following
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,472.86 rating

Confidence interval: 1,448.80 – 1,496.92

720 votes

Category
japanese
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,461.74 rating

Confidence interval: 1,439.11 – 1,484.38

814 votes

Category
japanese
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,463.74 rating

Confidence interval: 1,445.12 – 1,482.37

1147 votes

Category
korean
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference

1,451.32 rating

Confidence interval: 1,432.25 – 1,470.39

1110 votes

Category
korean
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,505.17 rating

Confidence interval: 1,500.04 – 1,510.30

30080 votes

Category
longer_query
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,498.95 rating

Confidence interval: 1,493.83 – 1,504.07

30788 votes

Category
longer_query
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,498.74 rating

Confidence interval: 1,488.06 – 1,509.42

3286 votes

Category
math
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,489.31 rating

Confidence interval: 1,478.65 – 1,499.97

3386 votes

Category
math
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,505.26 rating

Confidence interval: 1,498.42 – 1,512.10

11414 votes

Category
multi_turn
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,503.98 rating

Confidence interval: 1,497.15 – 1,510.82

11699 votes

Category
multi_turn
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,480.33 rating

Confidence interval: 1,475.72 – 1,484.93

34931 votes

Category
non_english
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,474.36 rating

Confidence interval: 1,469.73 – 1,478.98

35630 votes

Category
non_english
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,489.72 rating

Confidence interval: 1,485.98 – 1,493.46

65110 votes

Category
overall
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,482.99 rating

Confidence interval: 1,479.24 – 1,486.74

66140 votes

Category
overall
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,489.95 rating

Confidence interval: 1,472.23 – 1,507.68

1124 votes

Category
polish
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference

1,479.05 rating

Confidence interval: 1,462.02 – 1,496.08

1194 votes

Category
polish
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,494.34 rating

Confidence interval: 1,486.35 – 1,502.33

6860 votes

Category
russian
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,484.43 rating

Confidence interval: 1,476.45 – 1,492.41

7017 votes

Category
russian
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Claude Opus 4.7

1,494.41 rating

Confidence interval: 1,480.12 – 1,508.71

2049 votes

Category
spanish
Evaluated configuration
Claude Opus 4.7 (High)
Evaluation type
human preference

1,473.12 rating

Confidence interval: 1,459.27 – 1,486.97

2090 votes

Category
spanish
Evaluated configuration
Claude Opus 4.7
Evaluation type
human preference

Run it locally

Inference · memory estimate

Claude Opus 4.7

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 4.7

Claude Opus 4.7 / Pricing tiers 4
Provider / scopeRateCurrencyAmount / unit
AWS BedrockClaude Opus 4.7Standard Global cross-region Cached inputUSD0.5 / 1M tokens
InputUSD5 / 1M tokens
OutputUSD25 / 1M tokens
Google Vertex AIClaude Opus 4.7Batch Token tier: 0 – 200,000 Cached inputUSD0.25 / 1M tokens
InputUSD2.5 / 1M tokens
OutputUSD12.5 / 1M tokens
Google Vertex AIClaude Opus 4.7Standard Token tier: 0 – 200,000 Cached inputUSD0.5 / 1M tokens
InputUSD5 / 1M tokens
OutputUSD25 / 1M tokens
Google Vertex AIClaude Opus 4.7Standard Token tier: 200,000 – No stated upper limit Cached inputUSD0.5 / 1M tokens
InputUSD5 / 1M tokens
OutputUSD25 / 1M tokens

Capabilities

Context window
1,000,000 tokens
Maximum input
1,000,000 tokens*
Maximum output
128,000 tokens
Reasoning
Yes
Tool calling
Yes
Structured output
Yes*
Open weights
No
Knowledge cutoff
2026-01-31
API mode
Chat*
Image input
Yes*
PDF input
Yes*
Prompt caching
Yes*
Tool choice
Yes*
Web search
Yes*
Model license
Proprietary

Input modalities

  • text
  • image
  • pdf

Output modalities

  • text

System configuration

Detailed specifications

Specifications · 68 fields
bedrock converse supports strict tools
No*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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.*
bedrock output config effort ceiling
xhigh*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
6.25e-6*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
6.25e-6*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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-4-7*
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
bedrock_converse*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
1,000,000*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
1,000,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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
128,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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
128,000*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
128,000*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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
128,000*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
2,048*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
2,048*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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.*
provider specific entry
us
1.1*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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 adaptive thinking
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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 adaptive thinking
Yes*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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 anthropic compaction
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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
No*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
No*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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 max reasoning effort
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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 max reasoning effort
Yes*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
No*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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 parallel tool use config
Yes*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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 sampling params
No*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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 sampling params
No*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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 speed
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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 search
Yes*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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-4-7*
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
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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 web search
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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 xhigh reasoning effort
Yes*
Scope and conditions
native_context
provider
anthropic*
mode
chat*
full_native_model_id
claude-opus-4-7*
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 xhigh reasoning effort
Yes*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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.*
token count model
model
anthropic.claude-opus-4-7*
litellm_provider
bedrock_mantle*
region
us-east-1*
Scope and conditions
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
anthropic.claude-opus-4-7*
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