claude-opus-4-8Anthropic
- endpoints
- 10
- regions
- 8
- best tok/s
- 89
- api
- chat
- released
- May 2026
- eu routing
- available
capabilities 7/8
| # | flags | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 1 |  Anthropic PBC | Global | 1M | $5.00 | $25.00 | $0.50 | 1.32s | 47.0 | no-train | |
| 2 |  AWS Bedrock | Global | 1M | $5.00 | $25.00 | $0.50 | 1.93s | 89.0 | zdr | |
| 3 |  Google LLC (Vertex AI) | Global | 1M | $5.00 | $25.00 | $0.50 | 1.22s | 81.0 | - | zdr |
| 4 | AWS Bedrock | ap-northeast-1 | 1M | $5.50 | $27.50 | $0.55 | 1.93s | 89.0 | zdr | |
| 5 | AWS Bedrock | eu-central-1 | 1M | $5.50 | $27.50 | $0.55 | 1.93s | 89.0 | zdr | |
| 6 | AWS Bedrock | eu-north-1 | 1M | $5.50 | $27.50 | $0.55 | 1.93s | 89.0 | zdr | |
| 7 | AWS Bedrock | eu-west-1 | 1M | $5.50 | $27.50 | $0.55 | 1.93s | 89.0 | zdr | |
| 8 | AWS Bedrock | eu-west-3 | 1M | $5.50 | $27.50 | $0.55 | 1.93s | 89.0 | zdr | |
| 9 | Google LLC (Vertex AI) | eu | 1M | $5.50 | $27.50 | $0.55 | 1.22s | 81.0 | - | zdr |
| 10 | Google LLC (Vertex AI) | us | 1M | $5.50 | $27.50 | $0.55 | 1.22s | 81.0 | - | zdr |
| provider | now | low | high | change |
|---|---|---|---|---|
| Google LLC (Vertex AI) | 1.22s | 1.42s | 2.38s | +65% |
| Anthropic PBC | 1.32s | 1.54s | 1.91s | -15% |
| AWS Bedrock | 1.93s | 1.59s | 2.09s | -23% |
median wait before the first token lands. this is the number a user feels, and it moves with provider load through the day.
Lines are steps: each sample is one week of traffic held flat, not a slide from the week before. Click a name in the key to drop it from the plot. Measured through Sep 12.
| eval | Score as a share of 100 | /100 |
|---|---|---|
| τ²-Bench | 94.4 | |
| GPQA Diamond | 92.0 | |
| Coding Index | 74.3 | |
| Terminal-Bench Hard | 58.3 | |
| SciCode | 54.4 | |
| Humanity's Last Exam | 48.7 | |
| Intelligence Index | 42.0 | |
| 7 evals | mean | 66.3 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-05-28.
claude-opus-4-8requesty routes this id across every provider serving claude-opus-4-8, picking on price and health and failing over automatically. the id stays valid when a provider changes underneath it
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="claude-opus-4-8", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
Opus 4.8 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.7, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration. Beyond coding, Opus 4.8 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.
questions 7
Which providers serve claude-opus-4-8?
How much does claude-opus-4-8 cost?
Is claude-opus-4-8 open weights?
What is the context window of claude-opus-4-8?
Which provider is fastest for claude-opus-4-8?
How do I use claude-opus-4-8 with the OpenAI SDK?
Should I call claude-opus-4-8 by its managed id or a provider id?
more from anthropic 6
| model | context | from /M | providers |
|---|---|---|---|
| claude-fable-5.1 | 1M | $10.00 | 2 |
| claude-opus-5 | 1M | $5.00 | 3 |
| claude-sonnet-5 | 1M | $2.00 | 3 |
| claude-fable-5 | 1M | $10.00 | 3 |
| claude-opus-4-7 | 1M | $5.00 | 3 |
| claude-sonnet-4-6 | 1M | $3.00 | 3 |
route claude-opus-4-8 through one endpoint
One key for 3 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology