Models for AI Agents
Best LLMs for AI Agents: Tool Use, Context, and Pricing
Building an AI agent? You need a model that supports tool use (function calling), has a large context window for maintaining conversation state, and won't drain your budget on long-running agentic loops. We compare every model that fits — from Claude to GPT to Gemini — ranked by capability and cost. Deploy your agent on OpenClaw for $33/mo flat.
Top Picks
Most Capable
GPT 5.4 Pro
OpenAI
$30.00/1M input
Largest Context
Grok 4.20 Beta
xAI
2Mcontext
Compare Models
Related Categories
Coding Models
Top models for code generation, debugging, and software engineering — ranked by LiveBench coding scores and API price.
Writing Models
Models with the highest language and writing scores for content creation, copywriting, marketing, and creative tasks.
Reasoning Models
Models with extended thinking for complex math, logic, and multi-step problem solving — ranked by benchmarks.
Budget Models
The most affordable LLMs under $1/1M input tokens for high-volume apps, prototyping, and cost-sensitive production.
Cost per 1M Tokens / Flagship Models
All Models for AI Agents
| Provider | Model | Input $/1M | Output $/1M | Context | Quality |
|---|---|---|---|---|---|
| Mistral | Mistral Nemo | $0.0200 | $0.0400 | 131.1K | N/A |
| OpenAI | GPT Oss 20b | $0.0300 | $0.1100 | 131.1K | 65.7Frontier |
| Qwen | Qwen Turbo | $0.0325 | $0.1300 | 131.1K | N/A |
| Amazon | Nova Micro V1 | $0.0350 | $0.1400 | 128K | N/A |
| OpenAI | GPT Oss 120b | $0.0390 | $0.1900 | 131.1K | 47.7Good |
| NVIDIA | Nemotron Nano 9b V2 | $0.0400 | $0.1600 | 131.1K | N/A |
| Arcee-ai | Trinity Mini | $0.0450 | $0.1500 | 131.1K | N/A |
| Qwen | Qwen3.5 9b | $0.0500 | $0.1500 | 256K | N/A |
| NVIDIA | Nemotron 3 Nano 30b A3b | $0.0500 | $0.2000 | 262.1K | 65.7Frontier |
| OpenAI | GPT 5 Nano | $0.0500 | $0.4000 | 400K | 49.9Good |
| xAI | Glm 4.7 Flash | $0.0600 | $0.4000 | 202.8K | 74.7Frontier |
| Amazon | Nova Lite V1 | $0.0600 | $0.2400 | 300K | N/A |
| Qwen | Qwen3.5 Flash 02 23 | $0.0650 | $0.2600 | 1M | 80.6Frontier |
| Baidu | Ernie 4.5 21b A3b | $0.0700 | $0.2800 | 120K | N/A |
| Qwen | Qwen3 Coder 30b A3b Instruct | $0.0700 | $0.2700 | 160K | N/A |
| Qwen | Qwen3 235b A22b 2507 | $0.0710 | $0.1000 | 262.1K | 52.2Strong |
| Bytedance-seed | Seed 1.6 Flash | $0.0750 | $0.3000 | 262.1K | N/A |
| OpenAI | GPT Oss Safeguard 20b | $0.0750 | $0.3000 | 131.1K | N/A |
| Mistral | Mistral Small 3.2 24b Instruct | $0.0750 | $0.2000 | 128K | N/A |
| Gemini 2.0 Flash Lite 001 | $0.0750 | $0.3000 | 1.0M | 72.0Frontier | |
| Qwen | Qwen3 Vl 8b Instruct | $0.0800 | $0.5000 | 131.1K | N/A |
| Qwen | Qwen3 30b A3b Thinking 2507 | $0.0800 | $0.4000 | 131.1K | 38.2Good |
| Meta | Llama 4 Scout | $0.0800 | $0.3000 | 327.7K | N/A |
| Xiaomi | Mimo V2 Flash | $0.0900 | $0.2900 | 262.1K | N/A |
| Alibaba | Tongyi Deepresearch 30b A3b | $0.0900 | $0.4500 | 131.1K | N/A |
| Qwen | Qwen3 Next 80b A3b Instruct | $0.0900 | $1.10 | 262.1K | 50.7Strong |
| Qwen | Qwen3 30b A3b Instruct 2507 | $0.0900 | $0.3000 | 262.1K | 38.2Good |
| Qwen | Qwen3 Next 80b A3b Thinking | $0.0975 | $0.7800 | 131.1K | 50.7Strong |
| NVIDIA | Nemotron 3 Super 120b A12b | $0.1000 | $0.5000 | 262.1K | 74.0Frontier |
| Bytedance-seed | Seed 2.0 Mini | $0.1000 | $0.4000 | 262.1K | N/A |
| Stepfun | Step 3.5 Flash | $0.1000 | $0.3000 | 256K | 78.3Frontier |
| Mistral | Ministral 3b 2512 | $0.1000 | $0.1000 | 131.1K | N/A |
| NVIDIA | Llama 3.3 Nemotron Super 49b V1.5 | $0.1000 | $0.4000 | 131.1K | 70.1Frontier |
| Gemini 2.5 Flash Lite Preview 09 2025 | $0.1000 | $0.4000 | 1.0M | 40.8Good | |
| xAI | Glm 4 32b | $0.1000 | $0.1000 | 128K | N/A |
| Gemini 2.5 Flash Lite | $0.1000 | $0.4000 | 1.0M | 40.9Good | |
| Mistral | Devstral Small | $0.1000 | $0.3000 | 131.1K | N/A |
| OpenAI | GPT 4.1 Nano | $0.1000 | $0.4000 | 1.0M | 66.3Frontier |
| Gemini 2.0 Flash 001 | $0.1000 | $0.4000 | 1.0M | 73.3Frontier | |
| Meta | Llama 3.3 70b Instruct | $0.1000 | $0.3200 | 131.1K | 65.8Frontier |
| Qwen | Qwen3 Vl 32b Instruct | $0.1040 | $0.4160 | 131.1K | N/A |
| Qwen | Qwen3 Vl 8b Thinking | $0.1170 | $1.36 | 131.1K | N/A |
| Qwen | Qwen3 Coder Next | $0.1200 | $0.7500 | 262.1K | N/A |
| Qwen | Qwen3 Vl 30b A3b Thinking | $0.1300 | $1.56 | 131.1K | N/A |
| Qwen | Qwen3 Vl 30b A3b Instruct | $0.1300 | $0.5200 | 131.1K | N/A |
| xAI | Glm 4.5 Air | $0.1300 | $0.8500 | 131.1K | 75.4Frontier |
| Qwen | Qwen3 235b A22b Thinking 2507 | $0.1495 | $1.50 | 131.1K | 52.2Strong |
| Mistral | Mistral Small 2603 | $0.1500 | $0.6000 | 262.1K | 72.7Frontier |
| Upstage | Solar Pro 3 | $0.1500 | $0.6000 | 128K | N/A |
| Mistral | Ministral 8b 2512 | $0.1500 | $0.1500 | 262.1K | 51.2Strong |
Page 1 of 5
Deploy your AI agent for $33/mo flat.
Managed Telegram bot hosting. We handle the infrastructure.
Any model. Any channel. Zero infrastructure.