Claude Haiku 4.5
anthropic/claude-haiku-4.5- Anthropic
- Family · Claude Haiku 4
- Text · Image · File → Text
- Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context195K
Max output64K
Input / 1M$1.00
Output / 1M$5.005× input
Usage
Tokens / day13.5B▼ 12% 7d
Usage rank#83
Requests / day2.1M
Tool calls / req0.12
Per request · 30 days
Avg input4.8K0.3× median
Avg output2150.3× median
Cache hit45%0.6× median
Reasoning share9.6%0.2× median
Tool-call failures1.7%about median
Consumption
Peak 51.5B 6 OctLow 8.8B 1 NovRank today #83
News & trends
6 mentions this weekthis model · videos, posts, articles · 30 days
Trending · 14 days
- AI vs AI ⚔️ Claude Fable 5.1 vs Claude Haiku 4.5 — LLM Battle #28 #Shorts217 views
- AI vs AI ⚔️ Claude Opus 5.5 vs Claude Haiku 4.5 — LLM Battle #27 #Shorts247 views
News · latest from Anthropic
- GPT-6.1 Terra vs. Claude Opus 5.5: Cheaper and faster in three tests at maxthenewstack.io · 2 Nov
- Claude Opus 5.5 and Claude Sonnet 5.5 are now available in Google AntigravityGoogle Cloud · 20 Oct
- GLM-5.3 vs. Claude Fable 5 on DeepSWE: Cost, Coding, and RoutingTogether AI · 21 Aug
- DeepSeek V4 Pro 0813 vs Claude Fable 5 on DeepSWE: Cost, Coding, and RoutingTogether AI · 17 Aug
Speed
Output speed#103/33489 tok/s1.3× faster than median
Fastest provider192 tok/sbest of 8 providers
First token#580.51 s2.0× quicker than median
Technical details
- Tokenizer
- Claude
- Moderation
- moderated
Request parameters 12
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
+2 more
- max_completion_tokens
- stop
When to use
Best for
- Low-latency chat and support bots
- Cost-sensitive document and image analysis
- Lightweight reasoning and design feedback
- Sub-agent steps in larger systems
Think twice for
- Long autonomous agent runs (weakest suite)
- Hardest coding tasks
- Self-hosting (closed weights)
Research papers
- RoleFUZZER: User-Behaviour Fuzzing for Role-Specification Adherence in Large Language Models28 Oct
- SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy26 Oct
- FlashScript: Compiling Recurring Agent Workflows into Reusable Neuro-Symbolic Programs24 Oct
- EGI-BENCH: An Enterprise General Intelligence Benchmark Suite19 Oct
- Vibenix: Agentic Software Packaging and Maintenance with Nix17 Oct
- HEPTABench: A framework for portable and controlled agentic evaluations in high energy physics13 Oct
- LLM Evolutionary Search Strategies Should be Compared by Tokens13 Oct
- Artifact Distillation: Training-Free Transfer from Frontier to Small Language Models12 Oct
Social
Most watched and discussed · 90 days
- AI vs AI ⚔️ Claude Opus 5.5 vs Claude Haiku 4.5 — LLM Battle #27 #ShortsLLMBattles · 247 views · 30 Oct
- AI vs AI ⚔️ Claude Fable 5.1 vs Claude Haiku 4.5 — LLM Battle #28 #ShortsLLMBattles · 217 views · 31 Oct
- AI vs AI ⚔️ Claude Haiku 4.5 vs Claude Fable 5.1 — LLM Battle #22 #ShortsLLMBattles · 214 views · 21 Oct
- AI vs AI ⚔️ Claude Sonnet 5 vs Claude Haiku 4.5 — LLM Battle #25 #ShortsLLMBattles · 188 views · 24 Oct
- Claude Haiku 4.5 vs 3.5: Why It Goes Off TrackRichard Seidl - Software-Testing · 50 views · 27 Oct
- Claude Haiku 4.5 vs GPT-5.6 Luna: 8-Soul Hit | Eigendark Model Arena 068Eigendark · 37 views · 20 Oct
- Claude Haiku 4.5 Leaves Free Claude Wednesday (Oct 29) — What Happens to Your ChatsAI Shortcut Lab · 15 views · 26 Oct
- Claude Haiku 4.5｜十月二十九退出選單AI in One · 13 views · 25 Oct
Same family
Claude Haiku 4Want Claude Haiku 4.5 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.