Skip to content
Rapid Router
593 models live now

Every AI model,
one API key.

Every model at its provider's list price, through one key.

593 models
Gemini 3.6 FlashVisionReasoningTools

Fast Gemini model balancing multimodal reasoning, tool use, and cost

₹73.69 in · ₹368 out /1M

google/gemini-3.6-flash, by Google3mo ago1.2s median1M context99.9% success
DeepSeek V4.1 FlashVisionReasoningTools

DeepSeek V4.1 Flash model for reasoning and agentic coding

₹19.65 in · ₹58.95 out /1M

deepinfra/deepseek-ai/deepseek-v4.1-flash, by DeepInfra1mo ago2.2s median1M context100% success
DeepSeek V4 Flash 0731ReasoningTools

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

₹5.89 in · ₹17.68 out /1M

deepseek/deepseek-v4-flash-0731, by DeepSeek2mo ago1.5s median1M context100% success
Claude Sonnet 5.5VisionReasoningTools

Fast Claude model for everyday coding, agents, and knowledge work

₹197 in · ₹983 out /1M

anthropic/claude-sonnet-5-5, by Anthropic24d ago1.9s median1M context100% success
DeepSeek V4 FlashVisionReasoningTools

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

₹8.84 in · ₹17.68 out /1M

deepseek/deepseek-v4-flash, by DeepSeek5d ago9.7s median1M context
Gemini 4 ArgonVisionReasoningTools

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

₹197 in · ₹983 out /1M

google/gemini-4-argon, by Google9d ago10.1s median1M context
Claude Haiku 5.5FastestVisionReasoningTools

Fast Claude model for responsive assistance, classification, and lightweight agents

₹9.83 in · ₹49.13 out /1M

anthropic/claude-haiku-5-5, by Anthropic15d ago930ms median1M context
GPT-6.1 SolVisionReasoningTools

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

₹197 in · ₹983 out /1M

openai/gpt-6.1-sol, by OpenAI23d ago2.3s median1.1M context
Claude Opus 5.5VisionReasoningTools

Claude model for long-running agentic coding and knowledge work

₹393 in · ₹1,965 out /1M

anthropic/claude-opus-5-5, by Anthropic1mo ago1.5s median1M context
GPT-6 LunaVisionReasoningTools

OpenAI's most efficient model for focused, high-volume tasks

₹9.83 in · ₹49.13 out /1M

openai/gpt-6-luna, by OpenAI1mo ago1.1M context
GPT-6 SolVisionReasoningTools

OpenAI model for complex coding and agentic workflows

₹197 in · ₹983 out /1M

openai/gpt-6-sol, by OpenAI1mo ago1.1M context
Grok 4.7VisionReasoningTools

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

₹197 in · ₹590 out /1M

x-ai/grok-4.7, by xAI1mo ago500K context
GLM-5.3-FlashXVisionReasoningTools

High-speed GLM-5.3-Flash serving option for coding and agent workflows

₹36.35 in · ₹123 out /1M

z-ai/glm-5.3-flashx, by Z.ai1mo ago1M context
GPT-6 AstraVisionReasoningTools

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

₹983 in · ₹4,913 out /1M

openai/gpt-6-astra, by OpenAI1mo ago1.1M context
Claude Fable 5.1VisionReasoningTools

Claude model for demanding reasoning and long-horizon agentic work

₹983 in · ₹4,913 out /1M

anthropic/claude-fable-5-1, by Anthropic1mo ago1M context
GLM-5.3-FlashVisionReasoningTools

Native multimodal GLM model for efficient coding and long-horizon agent tasks

₹14.74 in · ₹49.13 out /1M

z-ai/glm-5.3-flash, by Z.ai1mo ago1.5s median1M context
Qwen3.8 27BVisionReasoningTools

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

₹97.27 in · ₹146 out /1M

cerebras/qwen-3.8-27b, by Cerebras2mo ago262K context
Qwen3.8 27BVisionReasoningTools

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

₹19.65 in · ₹246 out /1M

qwen/qwen3.8-27b, by Qwen2mo ago386ms median262K context
GLM-5.3ReasoningTools

Flagship GLM model for long-horizon coding, agents, and complex project delivery

₹138 in · ₹432 out /1M

z-ai/glm-5.3, by Z.ai2mo ago2.1s median1M context
DeepSeek V4 ProReasoningTools

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

₹128 in · ₹255 out /1M

deepseek/deepseek-v4-pro, by DeepSeek2mo ago821ms median1M context
DeepSeek V4 Pro 0813ReasoningTools

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

₹128 in · ₹255 out /1M

deepseek/deepseek-v4-pro-0813, by DeepSeek2mo ago1.7s median1M context
Gemini 3.7 FlashVisionReasoningTools

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

₹73.69 in · ₹368 out /1M

google/gemini-3.7-flash, by Google2mo ago2.0s median1M context
Gemini Flash LatestVisionReasoningTools

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

₹73.69 in · ₹368 out /1M

google/gemini-flash-latest, by Google2mo ago2.1s median1M context
Qwen3.8 2.4T A95BVisionReasoningTools

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

₹88.42 in · ₹393 out /1M

qwen/qwen3.8-2.4t-a95b, by Qwen2mo ago411ms median1M context
Grok 4.6VisionReasoningTools

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

₹197 in · ₹590 out /1M

x-ai/grok-4.6, by xAI2mo ago18.4s median500K context
Muse Glimmer 30BVisionReasoningTools

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

₹29.47 in · ₹118 out /1M

meta/muse-glimmer-30b, by Meta2mo ago433ms median131K context
Inkling SmallVisionReasoningTools

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

₹44.21 in · ₹118 out /1M

thinkingmachines/inkling-small, by Thinking Machines2mo ago667ms median66K context
Claude Opus 5VisionReasoningTools

Strongest Claude Opus model for coding, agents, and professional work

₹491 in · ₹2,456 out /1M

anthropic/claude-opus-5, by Anthropic3mo ago1.0s median1M context
Ling 3.0 FlashReasoningTools

Efficient model for low-latency assistance, extraction, and routine automation

₹5.89 in · ₹17.68 out /1M

inclusionai/ling-3.0-flash, by inclusionAI3mo ago610ms median262K context
Gemini 3.5 Flash LiteFastestVisionReasoningTools

Fast Gemini model balancing multimodal reasoning, tool use, and cost

₹29.47 in · ₹246 out /1M

google/gemini-3.5-flash-lite, by Google3mo ago877ms median1M context
Gemini Flash-Lite LatestVisionReasoningTools

Fast Gemini model balancing multimodal reasoning, tool use, and cost

₹29.47 in · ₹246 out /1M

google/gemini-flash-lite-latest, by Google3mo ago1.1s median1M context
Kimi K3VisionReasoningTools

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

₹29.87 in · ₹1,173 out /1M

moonshotai/kimi-k3, by Moonshot3mo ago1.7s median1M context
Qwen3.7 FlashVisionReasoningTools

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

₹2.95 in · ₹12.77 out /1M

qwen/qwen3.7-flash, by Qwen3mo ago2.4s median1M context
Qwen3.7 FlashVisionReasoningTools

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

₹2.95 in · ₹12.77 out /1M

qwen/qwen3.7-flash-2026-07-15, by Qwen3mo ago394ms median1M context
InklingVisionReasoningTools

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

₹93.34 in · ₹398 out /1M

thinkingmachines/inkling, by Thinking Machines3mo ago542ms median66K context
GPT-5.6 LunaLongest contextVisionReasoningTools

Cost-efficient GPT-5.6 model for fast, high-volume workloads

₹19.65 in · ₹118 out /1M

openai/gpt-5.6-luna, by OpenAI3mo ago858ms median1.1M context
GPT-5.6 SolLongest contextVisionReasoningTools

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

₹393 in · ₹1,965 out /1M

openai/gpt-5.6-sol, by OpenAI3mo ago903ms median1.1M context
GPT-5.6 TerraVisionReasoningTools

Balanced GPT-5.6 model for capable, cost-efficient everyday work

₹197 in · ₹1,179 out /1M

openai/gpt-5.6-terra, by OpenAI3mo ago850ms median1.1M context
Grok 4.5VisionReasoningTools

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

₹197 in · ₹590 out /1M

x-ai/grok-4.5, by xAI3mo ago807ms median500K context
Hy3ReasoningTools

Tencent Hy reasoning model for coding, instruction following, and agent tasks

₹81.94 in · ₹246 out /1M

tencent/hy3, by Tencent3mo ago763ms median262K context
Claude Sonnet 5VisionReasoningTools

Everyday Claude agent model for coding, planning, browsing, and general work

₹197 in · ₹983 out /1M

anthropic/claude-sonnet-5, by Anthropic3mo ago13.5s median1M context
GLM-5.2ReasoningTools

Open flagship GLM for long-horizon coding agents and million-token context work

₹73.69 in · ₹236 out /1M

z-ai/glm-5.2, by Z.ai4mo ago1.8s median1M context
Kimi K2.7 CodeVisionReasoningTools

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

₹280 in · ₹1,400 out /1M

moonshotai/kimi-k2.7-code, by Moonshot4mo ago954ms median262K context
Kimi K2.7 Code HighSpeedVisionReasoningTools

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

₹187 in · ₹786 out /1M

moonshotai/kimi-k2.7-code-highspeed, by Moonshot4mo ago832ms median262K context
Claude Fable 5VisionReasoningTools

Claude model for creative writing, analysis, and controlled agent workflows

₹983 in · ₹4,913 out /1M

anthropic/claude-fable-5, by Anthropic4mo ago2.6s median1M context
Nemotron 3 Ultra 550B A55BReasoningTools

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

₹58.95 in · ₹354 out /1M

nvidia/nemotron-3-ultra-550b-a55b, by NVIDIA4mo ago585ms median203K context
Nemotron UltraReasoningTools

Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.

₹49.13 in · ₹216 out /1M

nvidia/nvidia-nemotron-3-ultra-550b-a55b, by NVIDIA4mo ago424ms median262K context
Nemotron 3 Ultra 550B A55BReasoningTools

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

₹49.13 in · ₹216 out /1M

nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16, by NVIDIA4mo ago427ms median1M context
Qwen3.7 PlusVisionReasoningTools

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

₹31.44 in · ₹126 out /1M

qwen/qwen3.7-plus, by Qwen4mo ago6.6s median1M context
Qwen3.7 PlusVisionReasoningTools

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

₹31.44 in · ₹126 out /1M

qwen/qwen3.7-plus-2026-05-26, by Qwen4mo ago1.2s median1M context
MiniMax-M3FastestVisionReasoningTools

MiniMax multimodal model for long-context coding, perception, and agent planning

₹27.51 in · ₹108 out /1M

minimax/minimax-m3, by MiniMax4mo ago595ms median1M context
Step 3.7 FlashVisionReasoningTools

Newer StepFun flash model for faster agents, coding, and multimodal prompts

₹13.76 in · ₹27.51 out /1M

stepfun/step-3.7-flash, by StepFun4mo ago1.2s median256K context
Claude Opus 4.8VisionReasoningTools

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

₹491 in · ₹2,456 out /1M

anthropic/claude-opus-4-8, by Anthropic4mo ago799ms median1M context
Nano Banana ProImageVisionReasoning

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

₹13.17 per image

google/gemini-3-pro-image, by Google4mo ago18.9s median66K context
Nano Banana ProImageVisionReasoning

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

₹13.17 per image

google/gemini-3-pro-image-preview, by Google4mo ago15.9s median66K context
Nano Banana 2ImageVisionReasoning

Image model for prompt-driven generation, editing, and visual design workflows

₹6.58 per image

google/gemini-3.1-flash-image, by Google4mo ago11.1s median131K context
Nano Banana 2ImageVisionReasoning

Image model for prompt-driven generation, editing, and visual design workflows

₹6.58 per image

google/gemini-3.1-flash-image-preview, by Google4mo ago9.8s median131K context
Qwen3.7 MaxReasoningTools

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

₹123 in · ₹368 out /1M

qwen/qwen3.7-max, by Qwen5mo ago3.5s median1M context
Qwen3.7 MaxReasoningTools

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

₹145 in · ₹435 out /1M

qwen/qwen3.7-max-2026-05-17, by Qwen5mo ago1M context
Qwen3.7 MaxReasoningTools

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

₹145 in · ₹435 out /1M

qwen/qwen3.7-max-2026-05-20, by Qwen5mo ago1.2s median1M context
Free

Free models. A model is free here when its provider charges us nothing for it, and then it is free to you too: tagged Free, $0 a request, no balance needed. Every other model is billed at the provider's price. Older ids ending in :free that are no longer free are not listed: they still answer if your code calls them, billed the same as the model without :free. Free requests have daily limits: how the free tier works.