Low-Latency on Best of AI

Amazon Nova Lite

Thu, 16 Jul 2026 00:00:00 +0000

Amazon Nova Lite is a multimodal model in Amazon’s Nova family, announced in December 2024 at AWS re:Invent and available through Amazon Bedrock. It accepts text, image, and video input and returns text output, with a 300,000-token context window, and is priced at $0.06 per million input tokens and $0.24 per million output tokens. Amazon built it as the mid-tier option between the text-only Nova Micro and the more capable Nova Pro, aimed at applications that need to handle images or video but still want fast response times and low cost.

Claude 3 Haiku

Thu, 16 Jul 2026 00:00:00 +0000

Claude 3 Haiku is the smallest and fastest model in Anthropic’s original Claude 3 family, launched in March 2024 alongside Sonnet and Opus. It was built for high-volume, latency-sensitive work such as customer support chat, content moderation, and data extraction, where a slower flagship model would be overkill. At $0.25 per million input tokens and $1.25 per million output tokens, it undercut most competing models on price while still reading images alongside text and handling a 200,000 token context window. Anthropic has since released faster, cheaper models in the Haiku line, so Claude 3 Haiku is now a legacy option kept available mainly for existing integrations built on it.

Claude 3.5 Haiku

Thu, 16 Jul 2026 00:00:00 +0000

Claude 3.5 Haiku is Anthropic’s fast, low-cost model in the Claude 3.5 family, released in October 2024 alongside an upgraded Claude 3.5 Sonnet. Anthropic built it to replace Claude 3 Haiku as the cheapest, quickest option in the lineup while closing much of the capability gap with larger models: on coding evaluations such as SWE-bench Verified, Claude 3.5 Haiku scored competitively with the original Claude 3.5 Sonnet and outperformed several larger models available at launch, and Anthropic reported an 88.1% score on HumanEval for code generation.

Claude Haiku 4.5

Thu, 16 Jul 2026 00:00:00 +0000

Claude Haiku 4.5 is Anthropic’s fastest and cheapest current-generation model, released on October 15, 2025. It is the first Haiku model to include extended thinking, computer use, and context awareness, features that had previously only shipped in Anthropic’s larger Sonnet and Opus models. On SWE-bench Verified it scores about 73.3 percent, which puts it within a few points of Claude Sonnet 4.5’s 77.2 percent despite costing a third as much: $1 per million input tokens and $5 per million output tokens versus Sonnet’s $3/$15. That makes it a practical choice for running many agents in parallel or handling high-volume tasks where Sonnet or Opus would be needlessly expensive. It reads both text and images and shares the 200,000 token context window used across the rest of the current Claude lineup.

Claude Instant

Thu, 16 Jul 2026 00:00:00 +0000

Claude Instant was Anthropic’s original budget model tier, introduced alongside Claude 1 in March 2023, well before the Claude 3 naming scheme existed. It traded some accuracy for speed and lower cost, and Anthropic pitched it for dialogue, text analysis, summarization, and document comprehension where a full-size Claude model wasn’t necessary. It supported a 100,000 token context window and text only, no image input. Anthropic notified developers in September 2024 that Claude Instant and the original Claude 1 models were being retired, and it has since been fully replaced by the Haiku line, making it a legacy model no longer recommended for new projects.

Command Light

Thu, 16 Jul 2026 00:00:00 +0000

Command Light is Cohere’s smallest and fastest model from the original Command family, released alongside Embed v3 in November 2023. It has around 6 billion parameters and a 4,096 token context window, and Cohere designed it for applications that need low latency and lower cost rather than top-tier reasoning. It was priced at $0.30 per million input tokens and $0.60 per million output tokens through the Cohere API. Cohere deprecated Command Light in September 2025 along with several other early Command models, and now points users toward Command R, Command R+, or Command A, calling Command A the strongest performer across the board. It remains documented here as a legacy option that some existing integrations may still reference.

Command R7B

Thu, 16 Jul 2026 00:00:00 +0000

Command R7B is the smallest model in Cohere’s R series, released in December 2024 as what the company called the final entry in that lineup. At 7 billion parameters it is built to run on cheap hardware, including CPUs and single GPUs, while still handling retrieval-augmented generation, tool use, and reasoning tasks that Cohere’s larger models were designed for. It topped the Hugging Face Open LLM Leaderboard among similarly sized open-weight models at launch, beating Gemma 2 9B, Ministral 8B, and Llama 3.1 8B on average across benchmarks including MMLU, IFEval, and GPQA. The model keeps the same 128,000-token context window as its bigger siblings and is priced far below them, making it a fit for high-volume, latency-sensitive applications rather than frontier-level tasks.

Gemini 2.0 Flash

Thu, 16 Jul 2026 00:00:00 +0000

Gemini 2.5 Flash

Thu, 16 Jul 2026 00:00:00 +0000

GPT-4o mini

Thu, 16 Jul 2026 00:00:00 +0000

Grok 4 Fast

Thu, 16 Jul 2026 00:00:00 +0000

Hunyuan Turbo

Thu, 16 Jul 2026 00:00:00 +0000

o3-mini

Thu, 16 Jul 2026 00:00:00 +0000

Sonic

Thu, 16 Jul 2026 00:00:00 +0000

text-embedding-3-small

Thu, 16 Jul 2026 00:00:00 +0000