Skip to content
ModelCap

Claude Opus 4.8

All-versions archive #13Arena #28API only

Anthropic·anthropic/claude-opus-4.8

Claude Opus 4.8 is a language model published by Anthropic. 8 OpenRouter endpoints are published in the latest snapshot. It accepts text, image, file input and returns text. The published context limit is 1M tokens. The catalogue declares support for reasoning, tool use, structured outputs.

ModelCap Index · All-versions archive
86.7#13
Measured · 90% support · score interval 86.7–92.3
Market Gravity
59.4
Secondary market signal

Superseded by Claude Opus 5. It no longer holds a current-board position; its all-versions archive rank is #13.

Input
$5.00
per 1M tokens
Output
$25.00
per 1M tokens
Context
1M
tokens
Providers
8
endpoints
Gateway spend
14.02%
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Amazon BedrockCheapest$5.00$25.001M—100.0%
Azureglobal$5.00$25.001M——
Googleglobal$5.00$25.001M—97.97%
Anthropic$5.00$25.001M—92.34%
Anthropic2$5.00$25.001M—99.33%
Googleeurope$5.50$27.501M——
Amazon Bedrockeu-west-1$5.50$27.501M——
Googleus$5.50$27.501M——

Reasoning efforts

Best supported result can inform ModelCap

Published Max, X-High, High and other configurations for this model. These are sourced scores, not head-to-head essays.

EffortAgent scoreSource rankSampleSource
Thinking
Claude Opus 4.8 (Thinking)
9.21%
CI 7.5–10.9%
#61.6M obs
35K sessions
LMArena Agent
Match 100%
Default
Claude Opus 4.8
3.09%
CI 1.0–5.2%
#191.4M obs
33K sessions
LMArena Agent
Match 100%

Related community configurations

Human preference rating
ConfigurationRatingSource rankVotesSource
Thinking
claude-opus-4-8-thinking
1483
CI 1478–1488
#1638KArena
Match 100%

Other versions (6)

ModelCap Index · All-versions archive

Methodology
86.7
Measured · 5 public benchmark observations across 5 boards
All-versions archive
#13
Public rank basis
Measured (measured)
Index support
89.9% · strong
Index interval
86.7–92.3
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · anthropic/anthropic/claude-opus-4.8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Direct benchmark observations
5
Breadth-adjusted BES point estimate
89.5
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
89.5
Evidence status
confirmed · 97% mass
General preference
89.6
Coding
94.5
Agents & tools
82.1
Reasoning
79.7
Evidence breadth
100%
Evidence coverage
90%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
45.0
Liquidity (providers × uptime)
93.6
Open reach (HF downloads)
—
Surface (context / tools / modalities)
100.0
Freshness
76.0
  • · OpenRouter popularity #23
  • · 4 live providers
  • · Catalogue: context 1000000, reasoning, tools, modalities Text/Image/File
  • · First seen 2026-05-27

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
53.6
partial · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
98.6
Evaluation provenance
89.6

Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
59.4
OpenRouter weekly popularity
#23 of 298
Vercel token share · 7d
6.53%
Venue data through
2026-08-07

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#28 of 385
Rating
1472.7
95% confidence interval
1468–1477
Votes
38K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
45.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
93.6

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
76.0

Time since first public availability, on a six-month half-life.

Specification

Context window
1M tokens
Max output
128K tokens
Inputs
Text, Image, File
Outputs
Text
Tokenizer
Claude
Cached input tokens
$0.50 / 1M
First seen on OpenRouter
27 May 2026

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Supported: Moderated