LLM Router
HomeRoutersModelsProvidersBenchmarksPricingCompareBlogAbout
HomeModelsBenchmarksPricingCompareBlog
LLM Router

Independent comparison platform for LLM routing infrastructure.

Platform

  • Home
  • Routers
  • Models
  • Pricing
  • Blog
  • About

Routers

  • Requesty
  • OpenRouter
  • Martian
  • Unify
  • LiteLLM

© 2026 LLM Router

Data from public sources. May not reflect real-time pricing.

MetaLlama 3.3Open SourceArena #154Dec 6, 2024

Meta: Llama 3.3 70B Instruct (free)

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. Model Card

Context Window
128K
tokens
Max Output
128K
tokens
Released
Dec 6, 2024
Arena Rank
#154
of 305 models
Output Speed
175
tokens/sec
Time to First Token
320ms
TTFT

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
⚡Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
Top K
Top-K sampling
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouterFreeFree—
Vercel AI$0.72$0.72—
Martian$0.10$0.32—

Benchmarks

Open LLM Leaderboard
AverageOpen LLM Leaderboard
44.85/100
IFEvalOpen LLM Leaderboard
89.98/100
BBHOpen LLM Leaderboard
56.56/100
MATH Lvl 5Open LLM Leaderboard
48.34/100
GPQAOpen LLM Leaderboard
10.51/100
MUSROpen LLM Leaderboard
15.57/100
MMLU-PROOpen LLM Leaderboard
48.13/100
Artificial Analysis
Intelligence IndexArtificial Analysis
48/100
Coding IndexArtificial Analysis
42/100
Math IndexArtificial Analysis
50/100
MMLU-PROArtificial Analysis
0.658/1
GPQA DiamondArtificial Analysis
0.448/1
MATH-500Artificial Analysis
0.712/1
AIME 2024Artificial Analysis
0.067/1
LiveCodeBenchArtificial Analysis
0.365/1
Aider Code Editing
Aider EditingAider Code Editing
42.1/100

Model IDs

OpenRoutermeta-llama/llama-3.3-70b-instruct:free
Hugging Facemeta-llama/Llama-3.3-70B-Instruct ↗

Tags

tool-calling
Compare with another model

Compare with…

Meta: Llama 4 ScoutLlama 3.3 70B InstructLlama 3.3 70B Instruct Turbo

Similar Models

Ranked by provider, pricing, capabilities, and arena performance

Meta#149
57% match

Meta: Llama 4 Scout

328K ctx$0.08/1M in

Same provider · Similar ranking

Meta
55% match

Llama 3.3 70B Instruct

128K ctx$0.13/1M in

Same family · Both support tools

Meta
55% match

Llama 3.3 70B Instruct Turbo

131K ctx$0.88/1M in

Same family · Both support tools

Meta#142
53% match

Meta: Llama 4 Maverick

1.0M ctx$0.15/1M in

Same provider · Both support tools

Meta
51% match

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

131K ctx$0.10/1M in

Same family · Both support tools

Meta#178
49% match

NVIDIA: Llama 3.1 Nemotron 70B Instruct

131K ctx$1.20/1M in

Same provider · Both support tools

← Back to all models