Anthropic: Claude Haiku 5.5
Fast Claude model for responsive assistance, classification, and lightweight agents
List input
$0.1
$/MTok · Anthropic
List output
$0.5
$/MTok
Context
1M
tokens
Sources
4
59 listings
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $0.5 → $0.25
- ↓ lowerInput $0.1 → $0.05
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| tokenstatanthropic/claude-haiku-5-5 | Anthropic | $0.1 | $0.5 | $0.01 | 1M |
| OpenRoutercheapestanthropic/claude-haiku-5.5:batch | OpenRouter | $0.05 | $0.25 | $0.005 | 1M |
| models.devanthropic/claude-haiku-5.5 | AI/ML API | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5-5 | Aixy | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | Anthropic | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5.5 | Cloudflare | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5-5 | CrossModel | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5-5 | Eden AI | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5.5 | Kilo Gateway | $0.1 | $0.5 | $0.01 | 1M |
| models.devaws-bedrock/claude-haiku-5-5 | LLM Gateway | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5-5 | Merge Gateway | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5.5 | NanoGPT | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5-5 | NEAR AI Cloud | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5.5 | Ofox | $0.1 | $0.5 | $0.01 | 1M |
| OpenRouteranthropic/claude-haiku-5.5 | OpenRouter | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5-5 | Perplexity | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5.5 | Standard Compute | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic/claude-haiku-5.5 | Vercel AI Gateway | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | 302.AI | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | AIHubMix | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | Azure | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | Azure | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | CommandCode | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5.5 | GitHub Copilot | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | DevPass (LLM Gateway) | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | Neon | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | OpenCode Go | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | OpenCode | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | Requesty | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | Venice AI | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5 | Vivgrid | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic.claude-haiku-5-5 | Amazon Bedrock | $0.1 | $0.5 | $0.01 | 1M |
| models.devglobal.anthropic.claude-haiku-5-5 | Amazon Bedrock | $0.1 | $0.5 | $0.01 | 1M |
| models.devanthropic-claude-5.5-haiku | DigitalOcean | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5@default | Vertex (Anthropic) | $0.1 | $0.5 | $0.01 | 1M |
| models.devclaude-haiku-5-5@default | Google Vertex AI | $0.1 | $0.5 | $0.01 | 1M |
| LiteLLMclaude-haiku-5-5 | N/A | $0.1 | $0.5 | $0.01 | N/A |
| LiteLLManthropic.claude-haiku-5-5 | N/A | $0.1 | $0.5 | $0.01 | N/A |
| LiteLLMglobal.anthropic.claude-haiku-5-5 | N/A | $0.1 | $0.5 | $0.01 | N/A |
| LiteLLMclaude-haiku-5-5@default | N/A | $0.1 | $0.5 | $0.01 | N/A |
| LiteLLMazure_ai/claude-haiku-5-5 | N/A | $0.1 | $0.5 | $0.01 | N/A |
| LiteLLMperplexity/anthropic/claude-haiku-5-5 | N/A | $0.1 | $0.5 | $0.01 | N/A |
| LiteLLMvertex_ai/claude-haiku-5-5 | N/A | $0.1 | $0.5 | $0.01 | N/A |
| LiteLLMvertex_ai/claude-haiku-5-5@default | N/A | $0.1 | $0.5 | $0.01 | N/A |
| models.devau.anthropic.claude-haiku-5-5 | Amazon Bedrock | $0.11 | $0.55 | $0.011 | 1M |
| models.deveu.anthropic.claude-haiku-5-5 | Amazon Bedrock | $0.11 | $0.55 | $0.011 | 1M |
| models.devjp.anthropic.claude-haiku-5-5 | Amazon Bedrock | $0.11 | $0.55 | $0.011 | 1M |
| models.devus.anthropic.claude-haiku-5-5 | Amazon Bedrock | $0.11 | $0.55 | $0.011 | 1M |
| LiteLLMau.anthropic.claude-haiku-5-5 | N/A | $0.11 | $0.55 | $0.011 | N/A |
| LiteLLMeu.anthropic.claude-haiku-5-5 | N/A | $0.11 | $0.55 | $0.011 | N/A |
| LiteLLMjp.anthropic.claude-haiku-5-5 | N/A | $0.11 | $0.55 | $0.011 | N/A |
| LiteLLMus.anthropic.claude-haiku-5-5 | N/A | $0.11 | $0.55 | $0.011 | N/A |
| LiteLLMapac.anthropic.claude-haiku-5-5 | N/A | $0.11 | $0.55 | $0.011 | N/A |
| LiteLLMbedrock_mantle/anthropic.claude-haiku-5-5 | N/A | $0.11 | $0.55 | $0.011 | N/A |
| models.devclaude-haiku-5.5 | Cortecs | $0.113 | $0.563 | $0.011 | 1M |
| LiteLLMbedrock/us-gov-east-1/anthropic.claude-haiku-5-5 | N/A | $0.12 | $0.6 | $0.012 | N/A |
| LiteLLMbedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5 | N/A | $0.12 | $0.6 | $0.012 | N/A |
| LiteLLMus-gov-east-1/anthropic.claude-haiku-5-5 | N/A | $0.12 | $0.6 | $0.012 | N/A |
| LiteLLMus-gov-west-1/anthropic.claude-haiku-5-5 | N/A | $0.12 | $0.6 | $0.012 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- In: file
- Out: text
Knowledge cutoff: 2026-06Released: 2026-10-07Output limit: 128K tokensFamily: claude-haiku
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence43.4i
- AA coding0i
- AA agentic0i
- FrontierCode v1.1 (Extended)58.4i
- AA-Briefcase1578i
- HLE (without tools)45.9i
- HLE (with tools)57.4i
- Terminal-Bench 4.039.2i
- FrontierCode v1.1 (Main)46.4i
- GDPVal-AA v2.11620i
- HealthBench Professional (length-adjusted)64.8i
- PhysicianBench43i
- SWE-Bench Pro64.8i
- SWE-bench Multilingual83.7i
- SWE-bench Multimodal30.7i
- OSWorld 2.1 (offline, partial)72.4i
- OSWorld 2.1 (offline, strict pass)37.1i
- Chartography (no tools)46.4i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.