--- title: "Claude Haiku 4: Fast Reasoning Model for Real-Time Applications" canonical: https://telnyx.com/llm-library/claude-haiku-4-5 --- # Claude Haiku 4: Fast Reasoning Model for Real-Time Applications [Start building](https://telnyx.com/sign-up) ### Ask AI * [![GPT](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/chatgpt_icon-ea55e09d.jpeg?width=92&format=webp)](https://chat.openai.com/?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Claude](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/claude_icon-c7c8eef3.webp?width=92&format=webp)](https://claude.ai/new?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Perplexity](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/perplexity_icon-cd5b74f1.webp?width=92&format=webp)](https://www.perplexity.ai/search?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Gemini](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/gemini_icon-4ff1cbf4.webp?width=92&format=webp)](https://www.google.com/search?udm=50&aep=11&q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Grok](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/grok_icon-e588e5bd.webp?width=92&format=webp)](https://x.com/i/grok?text=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) Claude Haiku 4: Fast Reasoning Model for Real-Time Applications # Claude-Haiku-4-5 Anthropic's fastest model with near-frontier performance, matching Sonnet 4 in coding at one-third the cost and more than double the speed. [Start building](https://telnyx.com/sign-up)[GET Available Models](https://developers.telnyx.com/docs/inference/models) ## about Running at 98.9 tokens per second with a 0.68-second time-to-first-token, [Haiku 4.5](https://www.anthropic.com/news/claude-haiku-4-5) scores 73.3% on SWE-bench Verified, within 5 points of the mid-tier Sonnet despite costing $1/$5 per million tokens. It was the first Haiku model to ship with extended thinking, computer use, and context awareness, closing the gap between Anthropic's speed tier and its reasoning tier. Licenseanthropic Context window(in thousands) ## Explore Our LLM Library Discover the power and diversity of large language models available with Telnyx. Explore the options below to find the perfect model for your project. ### DeepSeek-V4-Flash-0731 OrganizationTelnyx Model NameDeepSeek-V4-Flash-0731 Taskstext generation Languages SupportedEnglish Context Length1,048,576 Parameters284.0B Model Tierunlisted Licensemit ### DeepSeek-V4.1-Flash ### gemma-2b-it ### gemma-4-26B-A4B-it ### gemma-4-31B-it ### Llama-3.3-70B-Instruct ### Meta-Llama-3.1-70B-Instruct ### Meta-Llama-3.1-8B-Instruct ### MiniMax-M2.7 ### MiniMax-M3-MXFP8 ### Kimi-K2.5 ### Kimi-K2.6 ### Kimi-K3 ### personaplex-7b-v1 ### Laguna-S-2.1 ### Qwen3-235B-A22B ### Qwen3.8-27B ### GLM-5.1-FP8 ### GLM-5.2 ### GLM-5.3 ### GLM-5.3-Flash ### claude-haiku-4-5 ### gemini-2.5-flash ### gemini-3.7-flash ### gpt-oss-120b ### gpt-4.1 ### gpt-4o ### gpt-4o-mini ### gpt-5 ### gpt-5.1 ### gpt-5.2 ### gpt-5.4 ### gpt-5.4-mini ### gpt-5.6-luna ### gpt-5.6-sol ### gpt-live-1 HOW IT WORKS ## Selecting LLMs for Voice AI [GET Available Models](https://developers.telnyx.com/docs/inference/models) ### Create an account Sign-up to the Telnyx platform to get access to our suite of intuitive AI tools. ### Choose Claude-Haiku-4-5 In the [AI Playground](https://portal.telnyx.com/#/app/next/ai/ai-playground "Telnyx AI Playground") select Claude-Haiku-4-5 from the dropdown. ### Enter your API key If you’re using a proprietary model, you’ll need your API key before prompting the LLM. Our vast selection of OS models allow you to get started right away. ### Prompt the LLM Get responses from an LLM in minutes, and scale with our [OpenAI-compatible APIs](https://developers.telnyx.com/docs/inference/getting-started "Inference API Quickstart"). Step 1/4 **RESOURCES** ## Get started Check out our helpful tools to help get you started. * ### Test in the portal Easily browse and select your preferred model in the AI Playground. [Test today](https://portal.telnyx.com/#/ai/assistants) ## Sign up and start building [Sign up](https://telnyx.com/sign-up)[Contact sales](https://telnyx.com/contact-us) ## faqs ### What is Claude Haiku 4.5 good for? Claude Haiku 4.5 is optimized for high-speed, cost-efficient tasks where quick responses matter. It excels at classification, summarization, and conversational AI, delivering [coding performance similar to Claude Sonnet 4](https://telnyx.com/release-notes/claude-haiku-4-5-voice-ai-assistants) at one-third the cost and more than double the speed. ### Can I use Haiku 4.5 in Claude Code? Yes, Claude Haiku 4.5 is available as a model option in Claude Code, providing a fast and cost-effective choice for [coding assistance and development workflows](https://telnyx.com/llm-library/claude-sonnet-4-20250514). Its low latency makes it particularly useful for rapid iteration during development. ### Is Claude Haiku 4.5 free? Claude Haiku 4.5 is available for free with usage limits on claude.ai. Through the API, it is , making it Anthropic's most affordable model. 200000 ## Use cases for Claude-Haiku-4-5 1. **Real-time customer interaction triage:** At 98.9 tokens per second and 0.68s time-to-first-token, Haiku 4.5 classifies and routes incoming queries faster than users can notice latency. 2. **Automated code review at scale:** Scoring 73.3% on SWE-bench Verified, it catches bugs and suggests fixes in pull request pipelines where speed matters more than maximum depth. 3. **Edge-deployed content moderation:** Its small footprint and extended thinking capability make it suited for on-device safety filtering where round-trip API calls are too slow. ## Quality Arena EloN/A MMLUN/A MT BenchN/A Claude Haiku 4.5 scores 73.3% on SWE-bench Verified, within 5 points of Claude Sonnet 4 (72.7%) on the same benchmark despite costing one-third as much. On MMLU, the Claude 3 Haiku baseline scored 76.7% (0-shot CoT), and the 4.5 update maintains that range while adding extended thinking and tool use. At 98.9 tokens per second, it delivers near-Sonnet quality at Haiku speed. **Claude-Opus-4-6** 1501 **GLM-5** 1456 **gpt-5.1** 1455 **Kimi-K2.5** 1454 **gpt-5.2** 1440 ## pricing Running Claude Haiku 4.5 through Telnyx Inference costs $1.00 per million input tokens and $5.00 per million output tokens. Processing 1,000,000 customer support conversations at 1,000 tokens each would cost approximately $3,000, roughly one-third the cost of the same workload on Claude Sonnet 4 ($9,000). ## What's Twitter saying? * Developers praise **Claude Haiku 4.5** for its near-Sonnet 4.5 performance on coding benchmarks like 73% on SWE-Bench Verified, at a fraction of the cost and twice the speed, ideal for agentic apps and tool calling. * Users on Hacker News call it **brilliant for nuanced coding tasks** but note it's slow in some cases and requires strict rules to avoid deviation. * Early testers report **shocking speed** enabling full-stack apps in under a minute, though one YouTube review finds it disappointing compared to GPT-5 in non-coding areas. | Organization | Model Name | Tasks | Languages Supported | Context Length | Parameters | Model Tier | License | | ------------ | ----------------------------------------------------------------------- | ---------------- | ------------------- | -------------- | ---------- | ---------- | ------------------------- | | Telnyx | DeepSeek-V4-Flash-0731 | text generation | English | 1,048,576 | 284.0B | unlisted | mit | | Telnyx | DeepSeek-V4.1-Flash | text generation | English | 1,048,576 | 552.0B | small | mit | | google | [gemma-2b-it](https://telnyx.com/llm-library/gemma-2b-it) | text generation | English | 8,192 | 2.5B | small | gemma | | google | gemma-4-26B-A4B-it | text to-text | Multilingual | 262,144 | 25.8B | small | apache-2.0 | | google | gemma-4-31B-it | text generation | Multilingual | 131,072 | 30.7B | small | apache-2.0 | | meta-llama | [Llama-3.3-70B-Instruct](https://telnyx.com/llm-library/llama-3.3-70b-instruct) | text generation | Multilingual | 99,000 | 70.6B | large | llama3.3 | | meta-llama | [Meta-Llama-3.1-70B-Instruct](https://telnyx.com/llm-library/meta-llama-3-1-70b-instruct) | text generation | Multilingual | 99,000 | 70.6B | large | llama3.1 | | meta-llama | [Meta-Llama-3.1-8B-Instruct](https://telnyx.com/llm-library/meta-llama-3.1-8b-instruct) | text generation | Multilingual | 131,072 | 8.0B | small | llama3.1 | | minimaxai | MiniMax-M2.7 | text generation | Multilingual | 200,000 | 0 | large | minimaxai | | minimaxai | MiniMax-M3-MXFP8 | text generation | Multilingual | 1,000,000 | 428.0B | small | minimax-community | | moonshotai | [Kimi-K2.5](https://telnyx.com/llm-library/kimi-k2.5) | text generation | Multilingual | 256,000 | 1.0T | large | modified-mit | | moonshotai | Kimi-K2.6 | text generation | Multilingual | 262,144 | 1.0T | medium | modified-mit | | moonshotai | Kimi-K3 | text generation | English | 1,000,000 | 2.8M | large | MIT Modified | | nvidia | personaplex-7b-v1 | speech to-speech | English | 3,000 | 7.0B | small | nvidia-open-model-license | | poolside | Laguna-S-2.1 | text generation | English | 1,048,576 | 117.6B | unlisted | OpenMDW-1.1 | | Qwen | [Qwen3-235B-A22B](https://telnyx.com/llm-library/qwen3-235b-a22b) | text generation | English | 32,768 | 235.1B | large | apache-2.0 | | Telnyx | Qwen3.8-27B | text generation | English | 262,144 | 27.0B | small | Apache 2.0 | | zai-org | GLM-5.1-FP8 | text generation | Multilingual | 202,752 | 753.9B | large | mit | | zai-org | GLM-5.2 | text generation | English | 1,000,000 | 753.9B | medium | MIT | | Telnyx | GLM-5.3 | text generation | English | 1,048,576 | 753.0B | medium | glm-5.3 | | zai-org | GLM-5.3-Flash | text generation | English | 1,048,576 | 320.0B | small | mit | | anthropic | [claude-haiku-4-5](https://telnyx.com/llm-library/claude-haiku-4-5) | text generation | Multilingual | 400,000 | 0 | large | openai | | google | [gemini-2.5-flash](https://telnyx.com/llm-library/gemini-2.5-flash) | text generation | Multilingual | 400,000 | 0 | large | openai | | google | gemini-3.7-flash | text generation | Multilingual | 400,000 | 0 | large | openai | | groq | [gpt-oss-120b](https://telnyx.com/llm-library/gpt-oss-120b) | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-4.1 | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | [gpt-4o](https://telnyx.com/llm-library/gpt-4-omni) | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | [gpt-4o-mini](https://telnyx.com/llm-library/gpt-4o-mini) | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-5 | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-5.1 | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | [gpt-5.2](https://telnyx.com/llm-library/gpt-5.2) | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-5.4 | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-5.4-mini | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-5.6-luna | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-5.6-sol | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | gpt-live-1 | speech to-speech | Multilingual | 400,000 | 0 | large | openai | * ### Explore the docs Don’t wait to scale, start today with our public API endpoints. [Get started](https://developers.telnyx.com/api-reference/assistants/list-assistants) * ### Stay up to date Keep an eye on our AI changelog so you don't miss a beat. [See updates](https://telnyx.com/release-notes) priced at $1 per million input tokens and $5 per million output tokens ### What's the difference between Claude 4.5 Sonnet vs Haiku? Sonnet 4 is Anthropic's more capable model for complex reasoning and multi-step tasks, while Haiku 4.5 prioritizes speed and cost efficiency. Haiku 4.5 approaches Sonnet's coding performance while running [significantly faster](https://telnyx.com/release-notes/tag/voice-ai) at a lower price, making it better suited for high-volume or latency-sensitive applications. ### Is Claude Haiku cheap? Haiku 4.5 is Anthropic's lowest-cost model at $1 per million input tokens, roughly one-third the price of [Claude Sonnet 4](https://telnyx.com/llm-library/claude-sonnet-4-20250514). For voice AI and real-time applications that require sub-second responses, this cost structure makes Haiku a practical choice for production workloads. ### Is Claude Haiku 4.5 bad? Haiku 4.5 is not a weak model. It performs competitively on coding benchmarks and handles most everyday tasks well, according to [Anthropic's own benchmarks](https://www.anthropic.com/news/claude-haiku-4-5). Its limitations show on complex reasoning and multi-step analysis, where Sonnet or Opus models are better suited. ### How much does Haiku 4.5 cost? Haiku 4.5 is priced at $1 per million input tokens and $5 per million output tokens through the API. Telnyx offers access to Haiku 4.5 through its [inference infrastructure](https://telnyx.com/release-notes/claude-haiku-4-5-voice-ai-assistants), where co-located processing can reduce overall pipeline latency.