Side-by-side comparison of AI models: pricing, context windows, tool calling, reasoning, vision, and structured output. Data from 95 providers, 4,587 models.
The top models from each major provider, compared across all key dimensions.
| Model | Provider | Input $/M | Output $/M | Context | Tool Call | Reasoning | Vision | Struct. Output |
|---|---|---|---|---|---|---|---|---|
| GPT-4.1 | OpenAI | $2.00 | $8.00 | 1,047K | ✅ | ❌ | ✅ | ✅ |
| o3 | OpenAI | $2.00 | $8.00 | 200K | ✅ | ✅ | ✅ | ✅ |
| o4-mini | OpenAI | $1.10 | $4.40 | 200K | ✅ | ✅ | ✅ | ✅ |
| Claude Opus 4 | Anthropic | $15.00 | $75.00 | 200K | ✅ | ✅ | ✅ | ✅ |
| Claude Sonnet 4 | Anthropic | $3.00 | $15.00 | 200K | ✅ | ✅ | ✅ | ✅ |
| Claude Haiku 3.5 | Anthropic | $0.80 | $4.00 | 200K | ✅ | ❌ | ✅ | ✅ |
| Gemini 2.5 Pro | $1.25 | $10.00 | 1,048K | ✅ | ✅ | ✅ | ✅ | |
| Gemini 2.5 Flash | Free | Free | 1,048K | ✅ | ✅ | ✅ | ✅ | |
| Grok 3 | xAI | $3.00 | $15.00 | 131K | ✅ | ❌ | ❌ | ❌ |
| Grok 3 Mini | xAI | $0.30 | $0.50 | 131K | ✅ | ✅ | ❌ | ❌ |
| DeepSeek R1 | DeepSeek | Free | Free | 164K | ✅ | ✅ | ❌ | ❌ |
| DeepSeek V3 | DeepSeek | $0.07 | $0.27 | 164K | ✅ | ❌ | ❌ | ❌ |
| Mistral Large | Mistral | $2.00 | $6.00 | 128K | ✅ | ❌ | ✅ | ✅ |
| Codestral | Mistral | $0.30 | $0.90 | 256K | ❌ | ❌ | ❌ | ❌ |
| Qwen3-235B | Alibaba | Free | Free | 128K | ✅ | ✅ | ✅ | ✅ |
| Command R+ | Cohere | $2.50 | $10.00 | 128K | ✅ | ❌ | ❌ | ✅ |
| Llama 4 Maverick | Meta | Free | Free | 1,048K | ✅ | ❌ | ✅ | ❌ |
| Nova Pro | Amazon | $0.80 | $3.20 | 300K | ✅ | ❌ | ✅ | ✅ |
Models that offer strong capabilities at budget-friendly prices.
| Model | Provider | Input $/M | Output $/M | Context | Tool Call | Reasoning | Vision |
|---|---|---|---|---|---|---|---|
| Gemini 2.5 Flash | Free | Free | 1,048K | ✅ | ✅ | ✅ | |
| DeepSeek R1 | DeepSeek | Free | Free | 164K | ✅ | ✅ | ❌ |
| Qwen3-235B | Alibaba | Free | Free | 128K | ✅ | ✅ | ✅ |
| DeepSeek V3 | DeepSeek | $0.07 | $0.27 | 164K | ✅ | ❌ | ❌ |
| Grok 3 Mini | xAI | $0.30 | $0.50 | 131K | ✅ | ✅ | ❌ |
| Codestral | Mistral | $0.30 | $0.90 | 256K | ❌ | ❌ | ❌ |
| Claude Haiku 3.5 | Anthropic | $0.80 | $4.00 | 200K | ✅ | ❌ | ✅ |
| Nova Pro | Amazon | $0.80 | $3.20 | 300K | ✅ | ❌ | ✅ |
Models with the largest context windows for processing long documents.
| Model | Provider | Context Window | Input $/M | Tool Call |
|---|---|---|---|---|
| Gemini 2.5 Pro | 1,048,576 | $1.25 | ✅ | |
| Gemini 2.5 Flash | 1,048,576 | Free | ✅ | |
| GPT-4.1 | OpenAI | 1,047,576 | $2.00 | ✅ |
| Llama 4 Maverick | Meta | 1,048,576 | Free | ✅ |
| Nova Pro | Amazon | 300,000 | $0.80 | ✅ |
| Claude Opus/Sonnet 4 | Anthropic | 200,000 | $3-15 | ✅ |
| o3 / o4-mini | OpenAI | 200,000 | $1.10-2 | ✅ |
| DeepSeek R1/V3 | DeepSeek | 163,840 | Free | ✅ |
How many models support each capability across our catalog.
| Capability | Models | Free Models | Cheapest Paid |
|---|---|---|---|
| Tool Calling | 2,350 | 54 | ling-2.6-flash ($0.01/$0.03) |
| Reasoning | 1,306 | 18 | qwen3.5-0.8b ($0.01/$0.05) |
| Vision | 1,487 | 35 | ling-2.6-flash ($0.01/$0.03) |
| Structured Output | 829 | 24 | ling-2.6-flash ($0.01/$0.03) |
| Open Weights | 527 | 81 | Free |
| Image Output | 28 | 5 | Various |
| Audio Input | 118 | 12 | Various |
| Audio Output | 34 | 8 | Various |
| Use Case | Best Model | Why | Cost |
|---|---|---|---|
| AI Agents | GPT-4.1 | #1 tool calling, parallel calls | $2/$8 |
| Coding | Claude Sonnet 4 | #1 SWE-bench, 64K output | $3/$15 |
| Reasoning | o3 | #1 MATH, GPQA | $2/$8 |
| Long Documents | Gemini 2.5 Pro | 1M context, best price | $1.25/$10 |
| Chat | GPT-4.1 | #1 Chatbot Arena | $2/$8 |
| Budget | Gemini 2.5 Flash | Free with 1M context | Free |
| Open Source | Qwen3-235B | Best open-weight model | Free |
| Vision | Gemini 2.5 Pro | Best MMMU, image+video | $1.25/$10 |