Model Benchmark
Every LLM,
compared.
317 models across 53 providers. Pricing, context windows, and capabilities, updated daily.
Last synced Mar 24, 2026, 08:59 PM
Compare Models
All Models
| Provider | Model | Input $/1M | Output $/1M | Context | Quality |
|---|---|---|---|---|---|
| Liquid | Lfm2 8b A1b | $0.0100 | $0.0200 | 32.8K | N/A |
| Liquid | Lfm 2.2 6b | $0.0100 | $0.0200 | 32.8K | N/A |
| Ibm-granite | Granite 4.0 H Micro | $0.0170 | $0.1100 | 131K | N/A |
| Gemma 3n E4b It | $0.0200 | $0.0400 | 32.8K | 65.8Frontier | |
| Meta | Llama Guard 3 8b | $0.0200 | $0.0600 | 131.1K | N/A |
| Meta | Llama 3.1 8b Instruct | $0.0200 | $0.0500 | 16.4K | 46.6Good |
| Mistral | Mistral Nemo | $0.0200 | $0.0400 | 131.1K | N/A |
| Meta | Llama 3.2 1b Instruct | $0.0270 | $0.2000 | 60K | 28.7Economy |
| Liquid | Lfm 2 24b A2b | $0.0300 | $0.1200 | 32.8K | N/A |
| OpenAI | GPT Oss 20b | $0.0300 | $0.1100 | 131.1K | 65.7Frontier |
| Qwen | Qwen2.5 Coder 7b Instruct | $0.0300 | $0.0900 | 32.8K | N/A |
| Mistral | Mistral Small 3.1 24b Instruct | $0.0300 | $0.1100 | 131.1K | 63.0Strong |
| Gemma 2 9b It | $0.0300 | $0.0900 | 8.2K | 58.8Strong | |
| Meta | Llama 3 8b Instruct | $0.0300 | $0.0400 | 8.2K | 48.7Good |
| Qwen | Qwen Turbo | $0.0325 | $0.1300 | 131.1K | N/A |
| Amazon | Nova Micro V1 | $0.0350 | $0.1400 | 128K | N/A |
| Cohere | Command R7b 12 2024 | $0.0375 | $0.1500 | 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 |
| Gemma 3 4b It | $0.0400 | $0.0800 | 131.1K | 63.0Strong | |
| Gemma 3 12b It | $0.0400 | $0.1300 | 131.1K | 69.9Frontier | |
| Qwen | Qwen 2.5 7b Instruct | $0.0400 | $0.1000 | 32.8K | N/A |
| Sao10k | L3 Lunaris 8b | $0.0400 | $0.0500 | 8.2K | N/A |
| Arcee-ai | Trinity Mini | $0.0450 | $0.1500 | 131.1K | N/A |
| Meta | Llama 3.2 11b Vision Instruct | $0.0490 | $0.0490 | 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 |
| Qwen | Qwen3 8b | $0.0500 | $0.4000 | 41.0K | N/A |
| Allenai | Olmo 2 0325 32b Instruct | $0.0500 | $0.2000 | 128K | 53.8Strong |
| Mistral | Mistral Small 24b Instruct 2501 | $0.0500 | $0.0800 | 32.8K | 57.8Strong |
| Meta | Llama 3.2 3b Instruct | $0.0510 | $0.3400 | 80K | 38.6Good |
| xAI | Glm 4.7 Flash | $0.0600 | $0.4000 | 202.8K | 74.7Frontier |
| Qwen | Qwen3 14b | $0.0600 | $0.2400 | 41.0K | N/A |
| Amazon | Nova Lite V1 | $0.0600 | $0.2400 | 300K | N/A |
| Gryphe | Mythomax L2 13b | $0.0600 | $0.0600 | 4.1K | N/A |
| Qwen | Qwen3.5 Flash 02 23 | $0.0650 | $0.2600 | 1M | 80.6Frontier |
| Microsoft | Phi 4 | $0.0650 | $0.1400 | 16.4K | 54.6Strong |
| Baidu | Ernie 4.5 21b A3b Thinking | $0.0700 | $0.2800 | 131.1K | N/A |
| 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 |
| Qwen | Qwen3 30b A3b | $0.0800 | $0.2800 | 41.0K | 38.2Good |
| Qwen | Qwen3 32b | $0.0800 | $0.2400 | 41.0K | 42.2Good |
Page 1 of 7
Cost per 1M Tokens / Flagship Models
Models by Use Case
218 models
Coding Models
Top models for code generation, debugging, and software engineering — ranked by LiveBench coding scores and API price.
174 models
Writing Models
Models with the highest language and writing scores for content creation, copywriting, marketing, and creative tasks.
4 models
Reasoning Models
Models with extended thinking for complex math, logic, and multi-step problem solving — ranked by benchmarks.
202 models
Models for AI Agents
Models built for autonomous AI agents — with function calling, large context windows, and competitive pricing for agentic workflows.
220 models
Budget Models
The most affordable LLMs under $1/1M input tokens for high-volume apps, prototyping, and cost-sensitive production.
119 models
Affordable Models
Mid-range models that balance quality and cost — under $5/1M input tokens with strong benchmark scores.
20 models
Premium Models
Top-tier frontier models from leading providers — maximum capability for demanding tasks.
153 models
Best Value Models
Models with the best quality-to-price ratio — high benchmark scores at affordable prices.
133 models
Vision Models
Models that process images alongside text for visual analysis, OCR, and multimodal tasks.
249 models
Long Context Models
Models with 100K+ token context windows for processing long documents, codebases, and conversations.
3 models
Models with Caching
Models that support prompt caching for reduced costs on repeated or similar requests.
133 models
Multimodal Models
Models that handle multiple input types including text, images, and audio.
Top Providers
60 models
OpenAI
Compare 60 OpenAI models by price, context window, and capabilities.
46 models
Qwen
Compare 46 Qwen models by price, context window, and capabilities.
25 models
Mistral
Compare 25 Mistral models by price, context window, and capabilities.
22 models
Compare 22 Google models by price, context window, and capabilities.
13 models
Anthropic
Compare 13 Anthropic models by price, context window, and capabilities.
12 models
Meta
Compare 12 Meta models by price, context window, and capabilities.
All Providers
DeepSeek
11 models
xAI
10 models
xAI
10 models
NVIDIA
7 models
Minimax
7 models
Amazon
5 models
Sao10k
5 models
Arcee-ai
5 models
Baidu
5 models
Nousresearch
5 models
Perplexity
5 models
Cohere
4 models
Allenai
4 models
Bytedance-seed
4 models
Thedrummer
4 models
Moonshot
4 models
Aion-labs
4 models
Liquid
3 models
Xiaomi
3 models
Inception
3 models
Microsoft
2 models
Morph
2 models
Relace
2 models
Inflection
2 models
Ibm-granite
1 models
Gryphe
1 models
Alibaba
1 models
Stepfun
1 models
Bytedance
1 models
Nex-agi
1 models
Tencent
1 models
Upstage
1 models
Essentialai
1 models
Prime-intellect
1 models
Meituan
1 models
Kwaipilot
1 models
Tngtech
1 models
Undi95
1 models
Writer
1 models
Mancer
1 models
Eleutherai
1 models
Alfredpros
1 models
Switchpoint
1 models
Deepcogito
1 models
AI21
1 models
Anthracite-org
1 models
Alpindale
1 models
Deploy your AI agent for $33/mo flat.
Managed Telegram bot hosting. We handle the infrastructure.
Any model. Any channel. Zero infrastructure.