Pricing and availability as of
Claude Haiku 5.5 is Anthropic's fastest model for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks, with adaptive thinking and vision capabilities.
claude-haiku-5-5Compare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.
3 providers · select a column to sort
| Provider | Actions | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| 1M | 128k | $0.10 | $0.50 | $0.01 | |||||
3 regions | 1M | 128k | $0.10 | $0.50 | $0.01 | ||||
| 1M | 128k | $0.10 | $0.50 | $0.01 |
Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.
Claude Haiku 5.5 API pricing starts at $0.10 per 1M input tokens and $0.50 per 1M output tokens through LLM Gateway, on Vertex AI (Anthropic). Cached input starts at $0.01 per 1M tokens. Some providers charge more above a prompt-size threshold; prices here are base-tier rates, and the Providers tab shows the tiers.
| Provider | Input / 1M tokens | Output / 1M tokens | Cached input / 1M tokens | Context window |
|---|---|---|---|---|
| Vertex AI (Anthropic) | $0.10 | $0.50 | $0.01 | 1,000,000 tokens |
| AWS Bedrock (global) | $0.10 | $0.50 | $0.01 | 1,000,000 tokens |
| AWS Bedrock | $0.10 | $0.50 | $0.01 | 1,000,000 tokens |
| Anthropic | $0.10 | $0.50 | $0.01 | 1,000,000 tokens |
| AWS Bedrock (eu) | $0.11 | $0.55 | $0.011 | 1,000,000 tokens |
| AWS Bedrock (us) | $0.11 | $0.55 | $0.011 | 1,000,000 tokens |
| Monthly usage | Cost on Vertex AI (Anthropic) |
|---|---|
| 1M input + 250K output tokens | $0.225 |
| 10M input + 2.5M output tokens | $2.25 |
| 100M input + 25M output tokens | $22.50 |
The estimate uses base-tier prices. Prompts above a provider's size threshold cost more.
Claude Haiku 5.5 is Anthropic's fastest model for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks, with adaptive thinking and vision capabilities. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Claude Haiku 5.5 on LLM Gateway starts at $0.10 per million input tokens and $0.50 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Claude Haiku 5.5 supports a context window of up to 1,000,000 tokens on its largest provider deployment.
Claude Haiku 5.5 is served by Vertex AI (Anthropic), AWS Bedrock, Anthropic through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. Claude Haiku 5.5 supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.
Claude Haiku 5.5 was released on October 7, 2026.