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-4o
Flagship multimodal model
In $2.50 Cached $1.250 Out $10.00
varies
per 1M tokens
gpt-4o-mini
Fast and cheap for many workloads
In $0.15 Cached $0.075 Out $0.60
varies
per 1M tokens
gpt-4.1
Strong reasoning and coding
In $3.00 Cached $0.750 Out $12.00
varies
per 1M tokens
gpt-4.1-mini
Budget reasoning and coding
In $0.80 Cached $0.200 Out $3.20
varies
per 1M tokens
o1
Advanced reasoning with chain-of-thought
In $15.00 Cached $7.500 Out $60.00
varies
per 1M tokens
o3-mini
Cost-effective reasoning model
In $1.10 Cached $0.550 Out $4.40
varies
per 1M tokens
gpt-3.5-turbo
Budget workhorse for simple tasks
In $0.50 Out $1.50
varies
per 1M tokens
Anthropic logo
Anthropic ✓ Verified LLM API
Claude API · Claude models priced per token, plus caching options.

Claude Opus 4.6
Most capable Claude model; complex reasoning and long context
In $5.00 Cached $0.500 Out $25.00
varies
per 1M tokens
Claude Sonnet 4.6
Balanced performance and cost
In $3.00 Cached $0.300 Out $15.00
varies
per 1M tokens
Claude Haiku 4.5
Fastest and cheapest Claude model
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.

Free Tier
Free-of-charge usage with rate limits
Free tier is quota-limited; see official Gemini pricing page for current limits.
$0
tier
Gemini 2.5 Flash
Latest fast multimodal model — replaces 2.0 Flash
In $2.00 Cached $0.200 Out $12.00
varies
per 1M tokens
Gemini 2.5 Flash-Lite
Most cost-effective Gemini option
In $0.12 Cached $0.013 Out $0.75
varies
per 1M tokens
Gemini 2.0 Flash
Deprecating June 2026 — migrate to 2.5 Flash
In $0.12 Cached $0.013 Out $0.75
varies
per 1M tokens
xAI logo
xAI ✓ Verified LLM API
Grok API · Grok models with per-token pricing and cached input discounts.

grok-4
Frontier Grok model
In $2.00 Cached $0.750 Out $6.00
varies
per 1M tokens
grok-4.1-fast
Budget-tier fast model; 2M token context
In $0.20 Out $0.50
varies
per 1M tokens
grok-3
Strong reasoning and coding
In $3.00 Cached $0.750 Out $15.00
varies
per 1M tokens
grok-3-mini
Cost-effective reasoning model
In $0.30 Cached $0.075 Out $0.50
varies
per 1M tokens
DeepSeek logo
DeepSeek LLM API
DeepSeek API · High-performance open-weight models with extremely low token pricing.

deepseek-chat (V3)
General-purpose chat model
In $0.14 Cached $0.014 Out $0.28
Pay-as-you-go
per 1M tokens
deepseek-reasoner (R1)
Chain-of-thought reasoning model
In $0.55 Cached $0.140 Out $2.19
Pay-as-you-go
per 1M tokens
Groq logo
Groq LLM API
Groq API · Ultra-fast LLM inference on custom LPU hardware.

Free Tier
Rate-limited free access for testing and prototyping
Free tier has rate limits; see Groq console for current limits.
$0
tier
llama-3.3-70b
Llama 3.3 70B — fast inference, strong quality
In $0.59 Out $0.79
varies
per 1M tokens
llama-3.1-8b
Very cheap, fastest option for simple tasks
In $0.05 Out $0.08
varies
per 1M tokens
mixtral-8x7b
Mixtral MoE — balanced speed and quality
In $0.24 Out $0.24
varies
per 1M tokens
gemma2-9b
Google Gemma 2 9B on Groq LPU
In $0.20 Out $0.20
varies
per 1M tokens
Mistral AI logo
Mistral AI LLM API
Mistral API · European AI with strong multilingual and coding models.

mistral-small-3.1
Efficient general-purpose model
In $0.10 Out $0.30
varies
per 1M tokens
mistral-medium-3
Balanced performance and cost for demanding tasks
In $0.40 Out $1.20
varies
per 1M tokens
mistral-large-2
Top-tier Mistral model for complex tasks
In $2.00 Out $6.00
varies
per 1M tokens
codestral
Specialized for code generation and completion
In $0.10 Out $0.30
varies
per 1M tokens
Together AI logo
Together AI LLM API
Together Inference API · Run popular open-source models at competitive prices.

Llama 3.3 70B Turbo
Meta Llama 3.3 70B — fast turbo variant
In $0.88 Out $0.88
varies
per 1M tokens
Llama 3.1 8B Turbo
Cheap and fast for high-volume tasks
In $0.18 Out $0.18
varies
per 1M tokens
Llama 3.1 405B
Largest open-source Llama model
In $3.50 Out $3.50
varies
per 1M tokens
Qwen2.5 72B Instruct
Strong multilingual and coding model
In $1.20 Out $1.20
varies
per 1M tokens
DeepSeek-R1
Open-source reasoning model via Together
In $3.00 Out $7.00
varies
per 1M tokens
CloudMart AI
API
Find the right LLM API.
Describe your use case, token volume, and budget to get a recommendation. You can also ask general questions like "Grok vs GPT-4o" or "what model is best for coding."
Compare:
Report a problem