Compare AI Models,
Pricing & Performance
Explore the best AI models for coding, writing, image generation, video, reasoning, and APIs.
API Pricing Table
Per 1M tokens — USD. Click any model for full details.
| Model | Provider | Category | Input /1M | Output /1M | Context | API | Details |
|---|---|---|---|---|---|---|---|
| Chat Models | $0.10 | $0.40 | 1.0M | View → | |||
| DeepSeek | Coding Models | $0.27 | $1.10 | 128K | View → | ||
| Alibaba | Coding Models | $0.40 | $1.20 | 128K | View → | ||
| Moonshot | Reasoning Models | $0.50 | $2.00 | 128K | View → | ||
| DeepSeek | Reasoning Models | $0.55 | $2.19 | 128K | View → | ||
| Anthropic | Chat Models | $0.80 | $4.00 | 200K | View → | ||
| Reasoning Models | $1.25 | $10.00 | 1.0M | View → | |||
GPT-4.1NEW | OpenAI | Chat Models | $2.00 | $8.00 | 1.0M | View → | |
| OpenAI | Chat Models | $2.50 | $10.00 | 128K | View → | ||
| Anthropic | Chat Models | $3.00 | $15.00 | 200K | View → | ||
| OpenAI | Reasoning Models | $15.00 | $60.00 | 1.0M | View → | ||
| Anthropic | Reasoning Models | $15.00 | $75.00 | 200K | View → |
Chat Models
Ideal for customer service, daily conversation, office assistance, and content creation — the most versatile AI capability.
| Model | Provider | Input /1M | Output /1M | Context | API | Details |
|---|---|---|---|---|---|---|
GPT-4oHot GPT-4o is a fast multimodal model optimized for chat, coding, and vision tasks. | OpenAI | $2.50 | $10.00 | 128K | View → | |
Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:... | Openrouter | Not token-based | — | 128K | View → | |
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long... | Ibm-granite | $0.017 | $0.11 | 131K | View → | |
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to... | Meta | $0.02 | $0.05 | 16K | View → | |
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,... | Mistral AI | $0.02 | $0.03 | 131K | View → | |
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate... | Meta | $0.027 | $0.20 | 60K | View → | |
LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per... | Liquid AI | $0.03 | $0.12 | 33K | View → | |
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for... | OpenAI | $0.03 | $0.14 | 131K | View → | |
Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks. | Alibaba | $0.0325 | $0.13 | 131K | View → | |
Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length... | Amazon | $0.035 | $0.14 | 128K | View → | |
Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning... | Cohere | $0.0375 | $0.15 | 128K | View → | |
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized... | OpenAI | $0.039 | $0.18 | 131K | View → |
Coding Models
Optimized for software development: code generation, debugging, code review, and technical documentation.
| Model | Provider | Input /1M | Output /1M | Context | API | Details |
|---|---|---|---|---|---|---|
DeepSeek V3Hot DeepSeek V3 is a highly competitive MoE model for coding and general reasoning at low cost. | DeepSeek | $0.27 | $1.10 | 128K | View → | |
The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how... | Openrouter | Not token-based | — | 2.0M | View → | |
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the... | Alibaba | $0.07 | $0.27 | 160K | View → | |
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per... | Alibaba | $0.11 | $0.80 | 262K | View → | |
Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling... | Alibaba | $0.195 | $0.975 | 1.0M | View → | |
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... | xAI | $0.20 | $1.50 | 256K | View → | |
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over... | Alibaba | $0.22 | $1.80 | 262K | View → | |
KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,... | Kwaipilot | $0.30 | $1.20 | 256K | View → | |
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08) | Mistral AI | $0.30 | $0.90 | 256K | View → | |
Qwen 2.5 72B is Alibaba's open-source flagship with strong multilingual and coding capabilities. | Alibaba | $0.40 | $1.20 | 128K | View → | |
Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file... | Arcee-ai | $0.50 | $0.80 | 33K | View → | |
Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and... | Alibaba | $0.65 | $3.25 | 1.0M | View → |
Reasoning Models
Enhanced logical reasoning for math, science, complex analysis, and strategic planning.
| Model | Provider | Input /1M | Output /1M | Context | API | Details |
|---|---|---|---|---|---|---|
DeepSeek R1Hot DeepSeek R1 is a chain-of-thought reasoning model rivaling o1 at a fraction of the cost. | DeepSeek | $0.55 | $2.19 | 128K | View → | |
Gemini 2.5 Pro is Google's most capable model with native 1M token context and state-of-the-art reasoning. | $1.25 | $10.00 | 1.0M | View → | ||
GPT-5 is OpenAI's most capable model, integrating advanced reasoning and multimodal understanding. | OpenAI | $15.00 | $60.00 | 1.0M | View → | |
Claude Opus is Anthropic's most intelligent model for complex reasoning and agentic tasks. | Anthropic | $15.00 | $75.00 | 200K | View → | |
ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level academic benchmarks. | Baidu | $0.07 | $0.28 | 131K | View → | |
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated... | Alibaba | $0.08 | $0.40 | 131K | View → | |
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic... | Alibaba | $0.0975 | $0.78 | 131K | View → | |
Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and... | Alibaba | $0.117 | $1.365 | 131K | View → | |
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels... | Alibaba | $0.13 | $1.56 | 131K | View → | |
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144... | Alibaba | $0.1495 | $1.495 | 131K | View → | |
Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7... | Arcee-ai | $0.22 | $0.85 | 262K | View → | |
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination. | Alibaba | $0.26 | $0.78 | 1.0M | View → |
Image Generation
Generate high-quality images from text descriptions — ideal for design, advertising, illustration, and art.
| Model | Provider | Input /1M | Output /1M | Context | API | Details |
|---|---|---|---|---|---|---|
FLUX.1Hot FLUX.1 is a state-of-the-art image generation model known for photorealism and prompt accuracy. | Black Forest Labs | Not token-based | — | — | View → | |
Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,... | Openrouter | Not token-based | — | 2.0M | View → | |
Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,... | $0.30 | $2.50 | 33K | View → | ||
Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines... | $0.50 | $3.00 | 66K | View → | ||
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and... | $2.00 | $12.00 | 66K | View → | ||
GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text... | OpenAI | $2.50 | $2.00 | 400K | View → | |
[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and... | OpenAI | $8.00 | $15.00 | 272K | View → | |
[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,... | OpenAI | $10.00 | $10.00 | 400K | View → | |
Midjourney v6 produces stunning artistic images with exceptional aesthetic quality. | Midjourney | Not token-based | — | — | — | View → |
Stable Diffusion XL is the leading open-source image generation model for local deployment. | Stability AI | Not token-based | — | — | View → |
Video Generation
Generate videos from text or images — great for ads, short-form content, and film production assistance.
| Model | Provider | Input /1M | Output /1M | Context | API | Details |
|---|---|---|---|---|---|---|
SoraHot Sora generates realistic and imaginative videos from text prompts up to 60 seconds. | OpenAI | Not token-based | — | — | — | View → |
Kling AIHot Kling AI generates high-quality videos with realistic motion and fluid transitions. | Kling AI | Not token-based | — | — | View → | |
Veo 2 is Google's advanced video generation model with cinematic quality and physics understanding. | Not token-based | — | — | — | View → | |
Runway Gen-3 Alpha is a powerful video generation model with API access for developers. | Runway | Not token-based | — | — | View → |