All Models

OpenAI's next-generation flagship — significant capability jump over GPT-4.1 with 1M context

Affordable GPT-5 intelligence — brings GPT-5 capability to cost-sensitive workloads

Latest flagship with 1M context window and strong coding/instruction following

Affordable intelligence with 1M context — best cost/performance in the 4.1 family

Smallest and cheapest GPT-4.1 model — ideal for simple tasks needing 1M context

Fast, efficient reasoning model optimized for STEM and coding tasks

Advanced reasoning model at significantly reduced price (80% cut from launch)

OpenAI's original frontier reasoning model — deep thinking for the hardest problems

Multimodal model with strong vision, audio, and text capabilities

Ultra-affordable model for high-volume tasks with good quality

Previous generation GPT-4 Turbo — powerful but superseded by GPT-4o in cost-efficiency

Classic fast model — still cost-effective for simple chat tasks and legacy integrations

Most capable Claude model — step-change improvement in agentic coding

Optimal balance of intelligence, cost, and speed with 1M context

Previous flagship — strong reasoning and extended thinking support

Most capable Claude 4 model with extended thinking — top performance on complex reasoning and coding

Fastest and most cost-efficient Claude with near-frontier intelligence

Previous generation Sonnet — high intelligence at moderate cost, widely used in production

Previous generation fast model — great balance of speed and intelligence at low cost

Third-generation flagship — powerful reasoning, still used for demanding legacy workloads

Google's most powerful model — frontier reasoning, native multimodal, 2M context window

Gemini 3's balanced model — strong reasoning at a fraction of Ultra cost

Fast and capable Gemini 3 — ideal for real-time applications needing 1M context

Most affordable Gemini 3 model — high-volume tasks with 1M context at near-zero cost

Most capable Gemini model with deep reasoning and multimodal support

Best-in-class speed and efficiency for diverse tasks

Most cost-efficient Gemini model for high-volume, latency-sensitive workloads

Previous gen workhorse — fast multimodal model with excellent price-to-performance

Ultra-cheap previous gen model — suitable for high-volume simple generation tasks

First model with 2M token context window — great for massive document analysis

Mistral's reasoning model — strong for complex analytical and math tasks

Frontier-level MoE model (675B total / 41B active params) at competitive price

State-of-the-art performance at 8x lower cost than previous generation

Efficient small model for simple, high-volume tasks

Code-specialized model with 256k context — optimized for fill-in-the-middle

Compact multilingual model with 128k context — great budget option for EU-compliance workloads

DeepSeek's second-generation reasoning model — stronger than R1 across all benchmarks at similar cost

Open-source reasoning model matching o1-level performance at a fraction of the cost. Ideal for math, coding, logic.

Cost-efficient chat model with strong multilingual performance. Best price-to-quality for Asian languages.

Meta's powerful Llama 4 model balancing performance and cost with 1M context

Meta's latest efficient model with a massive 10M token context window at extremely low cost

Meta's largest open-source model — frontier-class intelligence available via third-party API providers

Meta's large open-source model with strong reasoning. Great value via providers like Together AI or Fireworks.

Meta's efficient open-source model. Cheapest option for high-volume tasks via third-party API providers.

xAI's flagship model with real-time web access and strong performance on coding and analysis.

xAI's high-throughput variant of Grok 3 — same intelligence as flagship with faster response times

xAI's efficient model optimized for fast responses and cost-sensitive workloads.

Alibaba's fastest model with 256k context window at near-zero cost. Best for ultra high-volume tasks.

Alibaba's large MoE model with exceptional price — $0.06/1M for both input and output tokens.

Alibaba's mid-size model — solid performance at near-zero cost for everyday tasks

Alibaba's small efficient model — one of the cheapest options for simple classification and generation