Claude Opus 4.8: API Pricing, Context Window & Benchmarks
Claude Opus 4.8 is a language model from Anthropic, released in May 2026, with multimodal input, a 1M-token context window, and pricing from $5.00/M input, $0.500/M cached input, $25.00/M output.
Claude Opus 4.8 is Anthropic's upgrade to Opus 4.7 and its most capable general-access model at release, with improvements across software engineering, agentic tool use, reasoning, computer use, and knowledge-work benchmarks while shipping
Claude Opus 4.8 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Claude Opus 4.8 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Claude Opus 4.8 holds up as conversations get longer.
Quality Tracker
Claude Opus 4.8 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Aug 27 2026Claude Opus 4.8 pricing
Providers
Claude Opus 4.8 starts at $5.00 per million input tokens and $25.00 per million output tokens via Anthropic. Reused prompt prefixes cost $0.500 per million cached input tokens. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Anthropic | $5.00 | $0.500 | $25.00 | 1.0M/128.0K | 2.05 | 43 | / |
 Vertex AI | $5.00 | — | $25.00 | 1.0M/128.0K | 0.50 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Claude Opus 4.8 context window
Input and output token limits for Claude Opus 4.8, plus how it ranks on long-context understanding.
Claude Opus 4.8 API
Run a request to see the response
Use it in your code
Billed at $5.00 input / $0.50 cached input / $25.00 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="claude-opus-4-8",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
Claude Opus 4.8 latency
Claude Opus 4.8 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
Claude Opus 4.8 examples
Recent arena outputs from Claude Opus 4.8, picked from the highest-ranked matchups.
Claude Opus 4.8 license
Claude Opus 4.8 is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
Claude Opus 4.8 resources
Official sources for Claude Opus 4.8: api documentation, official playground, paper or system card, official launch post.
Claude Opus 4.8 vs other models
The most-compared alternatives to Claude Opus 4.8 are Claude Opus 4.6, Claude Mythos Preview, GPT-5.2 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Claude Opus 4.8
Models ranked just above and below Claude Opus 4.8 by LLM Stats score.
FAQ
Common questions about Claude Opus 4.8.