Model Benchmark

Every LLM,
compared.

309 models across 50 providers. Pricing, context windows, and capabilities, updated daily.

Last synced Jun 24, 2026, 08:16 PM

All Models

309 models
ProviderModelInput $/1MOutput $/1MContextQuality
InclusionaiLing 2.6 Flash$0.0100$0.0300262.1KN/A
Ibm-graniteGranite 4.0 H Micro$0.0170$0.1120131K
36.3Good
MetaLlama 3.1 8b Instruct$0.0200$0.0300131.1KN/A
MistralMistral Nemo$0.0200$0.0300131.1KN/A
MetaLlama 3.2 1b Instruct$0.0270$0.2010131.1KN/A
OpenAIGPT Oss 20b$0.0290$0.1400131.1KN/A
LiquidLfm 2 24b A2b$0.0300$0.1200128KN/A
AmazonNova Micro V1$0.0350$0.1400128KN/A
CohereCommand R7b 12 2024$0.0375$0.1500128KN/A
OpenAIGPT Oss 120b$0.0390$0.1800131.1K
47.7Good
QwenQwen 2.5 7b Instruct$0.0400$0.1000131.1KN/A
Sao10kL3 Lunaris 8b$0.0400$0.05008.2KN/A
Arcee-aiTrinity Mini$0.0450$0.1500131.1KN/A
QwenQwen3 30b A3b Instruct 2507$0.0482$0.1931131.1K
38.2Good
Ibm-graniteGranite 4.1 8b$0.0500$0.1000131.1KN/A
NVIDIANemotron 3 Nano 30b A3b$0.0500$0.2000262.1KN/A
OpenAIGPT 5 Nano$0.0500$0.4000400K
49.9Good
QwenQwen3 8b$0.0500$0.4000131.1KN/A
GoogleGemma 3 4b It$0.0500$0.1000131.1KN/A
GoogleGemma 3 12b It$0.0500$0.1500131.1KN/A
MistralMistral Small 24b Instruct 2501$0.0500$0.080032.8KN/A
MetaLlama 3.2 3b Instruct$0.0509$0.3350131.1KN/A
GoogleGemma 4 26b A4b It$0.0600$0.3300262.1KN/A
xAIGlm 4.7 Flash$0.0600$0.4000202.8KN/A
GoogleGemma 3n E4b It$0.0600$0.120032.8KN/A
AmazonNova Lite V1$0.0600$0.2400300KN/A
GrypheMythomax L2 13b$0.0600$0.06004.1KN/A
TencentHy3 Preview$0.0630$0.2100262.1KN/A
QwenQwen3.5 Flash 02 23$0.0650$0.26001MN/A
QwenQwen3 Coder 30b A3b Instruct$0.0700$0.2700160KN/A
MicrosoftPhi 4$0.0700$0.140016.4KN/A
InclusionaiRing 2.6 1t$0.0750$0.6250262.1KN/A
InclusionaiLing 2.6 1t$0.0750$0.6250262.1KN/A
Bytedance-seedSeed 1.6 Flash$0.0750$0.3000262.1KN/A
OpenAIGPT Oss Safeguard 20b$0.0750$0.3000131.1KN/A
MistralMistral Small 3.2 24b Instruct$0.0750$0.2000128KN/A
MicrosoftPhi 4 Mini Instruct$0.0800$0.3500131.1KN/A
QwenQwen3 Vl 8b Instruct$0.0800$0.5000256KN/A
QwenQwen3 30b A3b Thinking 2507$0.0800$0.4000131.1K
38.2Good
QwenQwen3 32b$0.0800$0.2800131.1K
42.2Good
GoogleGemma 3 27b It$0.0800$0.1600131.1KN/A
DeepSeekDeepseek V4 Flash$0.0900$0.18001.0M
68.9Frontier
NVIDIANemotron 3 Super 120b A12b$0.0900$0.45001MN/A
StepfunStep 3.5 Flash$0.0900$0.3000262.1KN/A
QwenQwen3 Next 80b A3b Instruct$0.0900$1.10262.1K
50.7Strong
QwenQwen3 235b A22b 2507$0.0900$0.1000262.1K
52.2Strong
QwenQwen3 Next 80b A3b Thinking$0.0975$0.7800262.1K
50.7Strong
PoolsideLaguna Xs.2$0.1000$0.2000262.1KN/A
RekaaiReka Edge$0.1000$0.100016.4KN/A
QwenQwen3.5 9b$0.1000$0.1500262.1KN/A

Page 1 of 7

Cost per 1M Tokens / Flagship Models

Input
Output

Models by Use Case

230 models

Coding Models

Top models for code generation, debugging, and software engineering — ranked by LiveBench coding scores and API price.

88 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.

227 models

Models for AI Agents

Models built for autonomous AI agents — with function calling, large context windows, and competitive pricing for agentic workflows.

204 models

Budget Models

The most affordable LLMs under $1/1M input tokens for high-volume apps, prototyping, and cost-sensitive production.

121 models

Affordable Models

Mid-range models that balance quality and cost — under $5/1M input tokens with strong benchmark scores.

30 models

Premium Models

Top-tier frontier models from leading providers — maximum capability for demanding tasks.

82 models

Best Value Models

Models with the best quality-to-price ratio — high benchmark scores at affordable prices.

158 models

Vision Models

Models that process images alongside text for visual analysis, OCR, and multimodal tasks.

272 models

Long Context Models

Models with 100K+ token context windows for processing long documents, codebases, and conversations.

6 models

Models with Caching

Models that support prompt caching for reduced costs on repeated or similar requests.

158 models

Multimodal Models

Models that handle multiple input types including text, images, and audio.

Top Providers

All Providers

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.