Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window.

Reasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)

xAI: Grok 4.1 Fast

OpenRouter

Google

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.

The model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.

Google: Gemini 3 Flash Preview

MoonshotAI

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.

It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.

MoonshotAI: Kimi K2 Thinking

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It introduces notable enhancements in multimodal understanding, coding capabilities, complex instruction following, and function calling. These advancements come together to deliver more seamless and robust agentic experiences.

Google: Gemini 2.0 Flash

DeepSeek

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

DeepSeek: DeepSeek V3.2

Meta: Llama 4 Maverick

Anthropic

Claude 3 Haiku is Anthropic's fastest and most compact model for
near-instant responsiveness. Quick and accurate targeted performance.

See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)

#multimodal

Anthropic: Claude 3 Haiku

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well on a variety of tasks.

DeepSeek: DeepSeek V3 0324

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. 

Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).

Google: Gemini 2.5 Flash

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.

It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.

Anthropic: Claude Haiku 4.5

Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast).

Reasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)

xAI: Grok 4 Fast

Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality work flows.

xAI: Grok Code Fast 1

Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not exposed, reasoning cannot be disabled, and the reasoning effort cannot be specified. Pricing increases once the total tokens in a given request is greater than 128k tokens. See more details on the [xAI docs](https://docs.x.ai/docs/models/grok-4-0709)

xAI: Grok 4

A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.

xAI: Grok 3 Mini

Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.



xAI: Grok 3

Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand extensive domain knowledge, and shines in math-specific and quantitative use cases, such as solving challenging puzzles or math problems.

Transparent "thinking" traces accessible. Defaults to low reasoning, can boost with setting `reasoning: { effort: "high" }`

Note: That there are two xAI endpoints for this model. By default when using this model we will always route you to the base endpoint. If you want the fast endpoint you can add `provider: { sort: throughput}`, to sort by throughput instead. 


xAI: Grok 3 Mini Beta

Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science.

Excels in structured tasks and benchmarks like GPQA, LCB, and MMLU-Pro where it outperforms Grok 3 Mini even on high thinking. 

Note: That there are two xAI endpoints for this model. By default when using this model we will always route you to the base endpoint. If you want the fast endpoint you can add `provider: { sort: throughput}`, to sort by throughput instead. 


Model	Cost
Google: Gemini 2.0 Flash	-92%
DeepSeek: DeepSeek V3.2	-81%
Meta: Llama 4 Maverick	-79%
Anthropic: Claude 3 Haiku	-71%
DeepSeek: DeepSeek V3 0324	-70%

Model	Latency
Google: Gemini 2.0 Flash	-86%
Google: Gemini 2.5 Flash	-82%
Anthropic: Claude 3 Haiku	-78%
Google: Gemini 3 Flash Preview	-77%
Anthropic: Claude Haiku 4.5	-75%

Model	Score
Google: Gemini 3 Flash Preview	+11%
MoonshotAI: Kimi K2 Thinking	+2%

Model	Score	Latency	Cost/1M
xAI: Grok 4	82.5%	24.3s	$9.00
xAI: Grok 4 Fast	—	—	$0.35
xAI: Grok Code Fast 1	—	—	$0.85
xAI: Grok 3 Mini	—	—	$0.40
xAI: Grok 3	—	—	$9.00
xAI: Grok 3 Mini Beta	—	—	$0.40
xAI: Grok 3 Beta	—	—	$9.00

Benchmark	Score	Rank
Math Bench: Addition (1-10)	100.0%	20 / 35
Math Bench: Subtraction (1-10)	100.0%	22 / 35
Math Bench: Multiplication (1-10)	100.0%	22 / 35
Math Bench: Division (1-10)	100.0%	25 / 35
Math Bench: Arithmetic (1-100)	100.0%	23 / 35
Math Bench: Arithmetic (1-1000)	100.0%	12 / 35
Character Frequency Bench	90.9%	14 / 35
Spatial Reasoning: Germany	89.5%	24 / 35
Product Recommendations	82.5%	6 / 36
Karlsruhe Local Knowledge Benchmark	79.0%	13 / 35
Money Boy Cultural Literacy Test	30.0%	17 / 35
German Memelord Bench	17.6%	18 / 35
Karl Lorey knowlege	0.0%	29 / 36

xAI: Grok 4.1 Fast

Alternatives

Same Quality, Cheaper

Same Quality, Faster

Same Cost, Better

Other Models from xAI

Benchmark Performance

Price vs Performance

Score Over Time

Benchmark Activity

Quickstart