Anthropic: Claude Opus 4.8
anthropic/claude-opus-4-8Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.
Modalities
In / out per 1M$5.00 / $25
Context1M
ReleasedMay 27, 2026
Providers
11 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Claude Platform on AWS | $5.00 | $25 | $0.50 | 1.29s | 60 tps | 100% |
 Amazon Bedrock | $5.00 | $25 | $0.50 | 1.57s | 80 tps | 100% |
 Google Vertexglobal | $5.00 | $25 | $0.50 | 1.22s | 72 tps | 100% |
| Amazon Bedrockus-east-1 | $5.50 | $28 | $0.55 | 1.23s | 80 tps | 100% |
| Amazon Bedrockeu-west-1 | $5.50 | $28 | $0.55 | 0.92s | 81 tps | 100% |
| Google Vertexeu | $5.50 | $28 | $0.55 | 0.79s | 97 tps | 100% |
| Anthropic | $10 | $50 | $1.00 | 0.83s | 161 tps | 100% |
| Anthropic | $5.00 | $25 | $0.50 | 1.54s | 55 tps | 99.91% |
 Azureglobal | $5.00 | $25 | $0.50 | 5.02s | 65 tps | — |
| Azureeastus2 | $5.50 | $28 | $0.55 | 3.80s | 47 tps | — |
| Google Vertexus | $5.50 | $28 | $0.55 | 1.40s | 53 tps | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Claude Opus 4.8 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Claude Opus 4.8 costs pay-as-you-go elsewhere, not what you pay here.
Input
$5.00
per 1M tokens
Output
$25
per 1M tokens
Cache read
$0.50
per 1M cached tokens
Included in every pass
Claude Opus 4.8 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s5.0s10.0s15.0s20.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Claude Platform on AWS Google Vertex (global) Anthropic Anthropic Amazon Bedrock Azure (global) Amazon Bedrock (eu-west-1) Google Vertex (eu) Amazon Bedrock (us-east-1)
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Claude Platform on AWS Google Vertex (global) Anthropic Amazon Bedrock Anthropic Azure (global) Amazon Bedrock (eu-west-1) Google Vertex (eu) Amazon Bedrock (us-east-1)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.98%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.97%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Claude Opus 4.8, by tokens this week.
Activity
1248.0B tokens processed market-wide in the last month.
050.0B100.0B150.0B200.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Claude Opus 4.8?
anthropic/claude-opus-4.8. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Claude Opus 4.8 hold?
1,000,000 tokens per request, of which up to 128,000 can be the response.
What can it accept and return?
Input: text, image, file. Output: text.
What does Claude Opus 4.8 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $5.00 per 1M input tokens and $25 per 1M output tokens.
Who built Claude Opus 4.8?
Anthropic, in the Claude family.
Explore
Other models your pass can call.
