API Marketplace

Compare LLM API providers by model, input/output token cost, and features.

Filters
✦ Free Tier Only: Pros & Cons
Pros: No credit card required on most plans · Great for prototyping and learning · Zero cost to get started.
Cons: Limited resources (CPU, RAM, bandwidth) · Often includes usage caps or sleep/spin-up delays · Not suitable for production traffic · May require upgrade without warning.
OpenAI logo
OpenAI ✓ Verified LLM API
OpenAI API · Text & multimodal models priced per token.

gpt-5.6-sol
In $4.00 Cached $0.400 Out $20.00
varies
per 1M tokens
gpt-5.6-terra
In $2.00 Cached $0.200 Out $12.00
varies
per 1M tokens
gpt-5.6-luna
In $0.20 Cached $0.020 Out $1.20
varies
per 1M tokens
gpt-5.5
Flagship model
In $5.00 Cached $0.500 Out $30.00
varies
per 1M tokens
gpt-5.5-pro
Highest-compute reasoning tier
In $30.00 Out $180.00
varies
per 1M tokens
gpt-5.4
Strong general model
In $2.50 Cached $0.250 Out $15.00
varies
per 1M tokens
gpt-5.4-mini
Cost-efficient workhorse
In $0.75 Cached $0.075 Out $4.50
varies
per 1M tokens
gpt-5.4-nano
Cheapest OpenAI model
In $0.20 Cached $0.020 Out $1.25
varies
per 1M tokens
gpt-5.6-cyber
In $12.50 Cached $1.250 Out $75.00
varies
per 1M tokens
gpt-5.3-codex
In $1.75 Cached $0.175 Out $14.00
varies
per 1M tokens
chat-latest
In $5.00 Cached $0.500 Out $30.00
varies
per 1M tokens
Anthropic logo
Anthropic ✓ Verified LLM API
Claude API · Claude models priced per token, plus caching options.

Fable 5
In $10.00 Cached $1.000 Out $50.00
varies
per 1M tokens
Opus 5
In $5.00 Cached $0.500 Out $25.00
varies
per 1M tokens
Sonnet 5
In $2.00 Cached $0.200 Out $10.00
varies
per 1M tokens
Haiku 4.5
In $1.00 Cached $0.100 Out $5.00
varies
per 1M tokens
Google logo
Google ✓ Verified LLM API
Gemini Developer API · Gemini models with free tier and paid per-token pricing.

Gemini 3.0 Flash
In $1.50 Cached $0.150 Out $7.50
varies
per 1M tokens
Gemini 3.0 Flash Lite
In $0.75 Cached $0.075 Out $3.75
varies
per 1M tokens
Gemini 3.0 Pro
In $2.00 Cached $0.270 Out $12.00
varies
per 1M tokens
Gemini 3.1 Flash
In $0.75 Cached $0.075 Out $3.75
varies
per 1M tokens
Gemini 3.1 Flash Lite
In $0.75 Cached $0.075 Out $4.50
varies
per 1M tokens
Gemini 3.1 Pro
In $1.35 Cached $0.135 Out $6.75
varies
per 1M tokens
Gemini 3.5 Flash
Latest fast frontier model
In $0.75 Cached $0.075 Out $3.75
varies
per 1M tokens
Gemini 3.5 Flash Lite
In $0.15 Cached $0.020 Out $1.25
varies
per 1M tokens
Gemini 2.5 Flash
In $0.25 Cached $0.025 Out $1.50
varies
per 1M tokens
Gemini 2.5 Flash-Lite
In $0.12 Cached $0.013 Out $0.75
varies
per 1M tokens
Gemini 3.0
In $2.00 Out $12.00
varies
per 1M tokens
Gemini 3.0 Ultra
In $3.60 Out $21.60
varies
per 1M tokens
Gemini 3.5 Pro
In $1.35 Cached $0.135 Out $6.75
varies
per 1M tokens
Gemini 2.0 Flash
In $0.30 Cached $0.030 Out $2.50
varies
per 1M tokens
Gemini 2.0 Flash Lite
In $0.30 Cached $0.030 Out $2.50
varies
per 1M tokens
Gemini 2.0 Pro Exp
In $2.70 Cached $0.270 Out $16.20
varies
per 1M tokens
Gemini 1.5 Flash
In $0.25 Cached $0.025 Out $1.50
varies
per 1M tokens
Gemini 1.5 Flash-8B
In $0.15 Cached $0.020 Out $1.25
varies
per 1M tokens
Gemini 3 Flash
In $0.38 Cached $0.037 Out $1.88
varies
per 1M tokens
Gemini 3 Pro
In $1.35 Cached $0.135 Out $6.75
varies
per 1M tokens
Gemini Exp 1114
In $2.00 Out $12.00
varies
per 1M tokens
Gemini 3 Flash-Lite
In $0.38 Cached $0.037 Out $1.88
varies
per 1M tokens
Gemini 2.5 Pro
In $2.00 Cached $0.200 Out $12.00
varies
per 1M tokens
Gemini 3.5 Flash (New)
In $1.50 Cached $0.150 Out $9.00
varies
per 1M tokens
xAI logo
xAI ✓ Verified LLM API
Grok API · Grok models with per-token pricing and cached input discounts.

grok-4.3
Flagship; 1M context, real-time X/web data
In $1.25 Out $2.50
varies
per 1M tokens
grok-4.20 (reasoning)
1M context reasoning model
In $1.25 Out $2.50
varies
per 1M tokens
grok-4.20 (non-reasoning)
1M context, low-latency
In $1.25 Out $2.50
varies
per 1M tokens
grok-build-0.1
Agentic coding; 256K context
In $1.00 Out $2.00
varies
per 1M tokens
DeepSeek logo
DeepSeek ✓ Verified LLM API
DeepSeek API · High-performance open-weight models with extremely low token pricing.

deepseek-v4-flash
Frontier-quality at commodity prices; replaces deepseek-chat
In $0.44 Cached $0.014 Out $1.32
varies
per 1M tokens
deepseek-v4-pro
Strongest DeepSeek model; replaces deepseek-reasoner
In $1.32 Cached $0.044 Out $3.96
varies
per 1M tokens
deepseek-v4-flash-vision-exp
In $0.44 Cached $0.014 Out $1.32
varies
per 1M tokens
Groq logo
Groq ✓ Verified LLM API
Groq API · Ultra-fast LLM inference on custom LPU hardware.

GPT OSS 120B
OpenAI open-weight 120B on LPU
In $0.15 Out $0.60
varies
per 1M tokens
GPT OSS 20B
OpenAI open-weight 20B on LPU
In $0.07 Out $0.30
varies
per 1M tokens
Llama 4 Scout
17Bx16E MoE, 128K context
In $0.11 Out $0.34
varies
per 1M tokens
Llama 3.3 70B Versatile
128K context
In $0.59 Out $0.79
varies
per 1M tokens
Llama 3.1 8B Instant
Fastest, cheapest tier
In $0.05 Out $0.08
varies
per 1M tokens
Qwen3 32B
131K context
In $0.29 Out $0.59
varies
per 1M tokens
Mistral AI logo
Mistral AI ✓ Verified LLM API
Mistral API · European AI with strong multilingual and coding models.

Mistral Large 3
Frontier open-weight flagship
In $0.50 Out $1.50
varies
per 1M tokens
Mistral Medium 3.5
Strongest proprietary tier
In $1.50 Out $7.50
varies
per 1M tokens
Mistral Small 4
Cost-efficient general model
In $0.15 Out $0.60
varies
per 1M tokens
GLM 5.2
In $1.40 Cached $0.140 Out $4.40
varies
per 1M tokens
Codestral
Purpose-built code model
In $0.30 Out $0.90
varies
per 1M tokens
Ministral 3 (3B)
In $0.10 Out $0.10
varies
per 1M tokens
Ministral 3 (8B)
In $0.15 Out $0.15
varies
per 1M tokens
Ministral 3 (14B)
In $0.20 Out $0.20
varies
per 1M tokens
Together AI logo
Together AI ✓ Verified LLM API
Together Inference API · Run popular open-source models at competitive prices.

Llama 3.3 70B
Open-source workhorse
In $1.04 Out $1.04
varies
per 1M tokens
Llama 3 8B Instruct Lite
Cheapest Llama tier
In $0.14 Out $0.14
varies
per 1M tokens
Qwen3.7-Max
Strongest hosted Qwen
In $1.25 Out $3.75
varies
per 1M tokens
DeepSeek V4 Pro
Hosted DeepSeek flagship
In $1.74 Cached $0.200 Out $3.48
varies
per 1M tokens
Kimi K2.7 Code
Agentic coding model
In $0.95 Out $4.00
varies
per 1M tokens
GLM-5.2
Frontier open-weight model
In $1.40 Cached $0.260 Out $4.40
varies
per 1M tokens
CloudMart AI API
Answers from live pricing data
🤖
Find the right LLM API.
Describe your use case and volume, or ask anything - "Grok vs GPT-5.5", "best model for coding" - answers come from live token pricing.
Enter to send · Shift+Enter for a new line
Compare:
Report a problem