Anthropic: Claude Haiku 5.5
anthropic/claude-haiku-5-5Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Modalities
In / out per 1M$0.10 / $0.50
Context1M
ReleasedOct 7, 2026
Providers
10 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Google Vertexglobal | $0.10 | $0.50 | $0.01 | 1.85s | 156 tps | 100% |
 Azureglobal | $0.10 | $0.50 | $0.01 | 1.39s | 136 tps | 100% |
 Anthropic | $0.10 | $0.50 | $0.01 | 0.88s | 147 tps | 100% |
| Google Vertexeu | $0.11 | $0.55 | $0.01 | 0.50s | 133 tps | 100% |
| Google Vertexus | $0.11 | $0.55 | $0.01 | 0.53s | 159 tps | 100% |
| Azureeastus2 | $0.11 | $0.55 | $0.01 | 0.66s | 145 tps | 100% |
 Amazon Bedrockus-east-1 | $0.11 | $0.55 | $0.01 | 1.32s | 190 tps | 100% |
| Amazon Bedrockeu-west-1 | $0.11 | $0.55 | $0.01 | 2.23s | 131 tps | 100% |
| Amazon Bedrock | $0.10 | $0.50 | $0.01 | 2.63s | 117 tps | 99.92% |
| Claude Platform on AWS | $0.10 | $0.50 | $0.01 | 1.30s | 163 tps | 99.9% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Claude Haiku 5.5 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Claude Haiku 5.5 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.10
per 1M tokens
Output
$0.50
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
Claude Haiku 5.5 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.
0.0s10.0s20.0s30.0s40.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Amazon Bedrock Google Vertex (global) Anthropic Claude Platform on AWS Google Vertex (us) Amazon Bedrock (eu-west-1) Google Vertex (eu) Azure (global) Amazon Bedrock (us-east-1) Azure (eastus2)
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Amazon Bedrock Google Vertex (global) Anthropic Claude Platform on AWS Google Vertex (us) Amazon Bedrock (eu-west-1) Google Vertex (eu) Azure (global) Amazon Bedrock (us-east-1) Azure (eastus2)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.96%
Oct 29, 5:00 PMNow
Availability over the last 24 hoursAvailability 99.95%
100% 98% 97% 95%
Oct 31, 5:20 PMNow
Apps
Tools that most often run Claude Haiku 5.5, by tokens this week.
Activity
8524.7B tokens processed market-wide in the last month.
0200.0B400.0B600.0B800.0B
Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens
FAQ
Which model id do I use for Claude Haiku 5.5?
anthropic/claude-haiku-5.5. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Claude Haiku 5.5 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 Haiku 5.5 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.10 per 1M input tokens and $0.50 per 1M output tokens.
Who built Claude Haiku 5.5?
Anthropic, in the Claude family.
Explore
Other models your pass can call.
