Models

Catalogue, pricing, usage, margin, cost advantage.

18 live models
Live models+2%
18
Revenue 30d+18.4%
$20.9K
Requests 30d+22.1%
19.9M
Tokens 30d+20.4%
53B
Avg margin+1.2%
46%
Open-source share
100%
  • Promote Qwen 2.5 72B vs Llama 3.1 70B for coding workloadsProduct · AI

    Higher margin (61% vs 48%) with comparable benchmarks. Add a 'recommended for coding' tag in the catalogue.

    Open
  • Re-price DeepSeek-R1 output to $1.80Pricing

    Demand sensitive at this tier; competing API at $2.19. Margin still holds above 50%.

  • Audit low-margin image models in EU — below 25% thresholdPricing · Legal

    Image generation models in EU show gross margin below the 25% floor. Review routing to higher-tier nodes or adjust regional pricing.

    Open

FAR AI vs centralized providers — $/1M tokens

~58% cheaper

Requests by modality

Catalogue
All FAR AI models with pricing, usage, margin, latency, error.
ModelTypeStatusSourceInput $/MOutput $/MRequests 30dTokensRevenue 30dMarginp95Err %
Llama 3.1 405B Instruct
Meta · llama-3.1-405b
textliveOpen$1.2$1.81.9M5.4B$7.2K40%2.1s2.3%
DeepSeek-R1
DeepSeek · deepseek-r1
reasoningliveOpen$0.55$2.191.2M3.4B$3.3K48%1.3s2.4%
Llama 3.1 70B Instruct
Meta · llama-3.1-70b
textliveOpen$0.35$0.552.9M6.6B$2.6K48%1.3s1.5%
Mistral Large 2
Mistral · mistral-large-2
textliveOpen$0.8$1.2795K2.1B$1.9K48%1.3s3.3%
Qwen 2 VL 72B
Alibaba · qwen-2-vl-72b
visionliveOpen$0.5$0.7960.7K2.2B$1.2K48%1.3s3.3%
DeepSeek-V3
DeepSeek · deepseek-v3
textliveOpen$0.14$0.281.9M5.1B$863.948%1.3s1.8%
DeepSeek Coder V2
DeepSeek · deepseek-coder-v2
codingliveOpen$0.14$0.281.4M4.7B$796.648%1.3s2.6%
Qwen 2.5 72B Instruct
Alibaba · qwen-2.5-72b
textliveOpen$0.3$0.5897K2.2B$786.648%1.3s2.9%
Mixtral 8x22B Instruct
Mistral · mixtral-8x22b
textliveOpen$0.45$0.75520.6K1.1B$587.148%1.3s3.4%
QwQ 32B Preview
Alibaba · qwq-32b
reasoningliveOpen$0.18$0.32659.5K1.7B$360.554%720ms3.1%
Llama 3.1 8B Instruct
Meta · llama-3.1-8b
textliveOpen$0.05$0.082.3M5.9B$335.254%720ms1.3%
Qwen 2.5 Coder 32B
Alibaba · qwen-2.5-coder-32b
codingliveOpen$0.12$0.2865.6K2.2B$305.654%720ms2.9%
LLaVA 1.6 34B
LLaVA · llava-1.6-34b
visionliveOpen$0.4$0.6205.2K674.3M$29748%1.3s3.4%
Whisper Large v3
OpenAI · whisper-large-v3
audioliveOpen$0.04$0551.9K1.8B$60.354%720ms3.4%
FLUX.1 [dev]
Black Forest · flux-1-dev
imageliveOpen$0.03$0.04742K2B$57.348%1.3s3.1%
FLUX.1 [schnell]
Black Forest · flux-1-schnell
imageliveOpen$0.01$0.021.2M3.2B$43.654%720ms2.9%
BGE Large EN v1.5
BAAI · bge-large-en
embeddingliveOpen$0.02$0609.5K1.8B$2654%720ms3.3%
Nomic Embed Text v1.5
Nomic · nomic-embed-text
embeddingliveOpen$0.02$0325.8K844.3M$12.954%720ms3.5%
Pixtral Large
Mistral · pixtral-large
visionbetaOpen$0.55$0.8500$00%1.3s0%
Stable Diffusion 3.5 Large
Stability AI · sd-3.5-large
imagebetaOpen$0.02$0.0300$00%1.3s0%
120 of 22