Share
Explore
LLM API Pricing
LLM API compare - ChatGPT Deep research
Provider & Model
Context Window
Input Pricing / 1M tokens
Output Pricing / 1M tokens
Quality & Performance
Function Calling
Streaming
Multimodal
Fine-tuning
Anthropic Claude 3.7
200k
$3.00
$15.00
State-of-the-art reasoning, “extended thinking” for hard tasks.
✅ Yes
✅ Yes
❌ No
❌ No
Claude 3.5 (Haiku)
200k
$0.40
$2.00
Fast, cost-effective for summaries and light analysis.
✅ Yes
✅ Yes
❌ No
❌ No
Claude 3 (Opus)
200k
$15.00
$75.00
High-end Claude for deep research, coding, analysis.
✅ Yes
✅ Yes
❌ No
❌ No
GPT-4.1
1M
$2.00
$8.00
OpenAI GPT-4.5 (Preview)
128k
$75.00
$150.00
Cutting-edge but expensive. Excellent reasoning and planning.
✅ Yes
✅ Yes
🔶 Text + Vision (limited)
❌ No
GPT-4o
128k
$2.50
$10.00
GPT-4-class quality at lower cost. Excellent for complex surveys.
✅ Yes
✅ Yes
❌ No
✅ Yes
GPT-4o Mini
128k
$0.15
$0.60
Light, affordable GPT model. Ideal for simple, scalable tasks.
✅ Yes
✅ Yes
❌ No
✅ Yes
GPT-4.1 mini
1M
$0.40
$1.60
OpenAI o3
1M
$10.00
$40.00
OpenAI o3-mini
200k
$1.10
$4.40
Cost-efficient reasoning model optimised for coding, math, and science tasks. Supports tools and structured outputs.
✅ Yes
✅ Yes
❌ No
❌ No
OpenAI o4-mini
1M
$1.10
$4.40
Our faster, cost-efficient reasoning model delivering strong performance on math, coding and vision
OpenAI o1
200k
$15.00
$60.00
Frontier reasoning model supporting tools, structured outputs, and vision capabilities. Designed for complex, multi-step problems.
✅ Yes
✅ Yes
✅ Text & Vision
❌ No
Gemini 2.5 Pro
1M (2M planned)
Free
Free
Top reasoning model; beats GPT-4 in some benchmarks; early access.
✅ Yes
✅ Yes
✅ Full (text, image, audio, video)
❌ No
Gemini 2.0 Flash
1M
$0.10
$0.40
Fast, versatile, excellent quality-to-price ratio.
✅ Yes
✅ Yes
✅ Full
❌ No
Gemini 2.0 Flash-Lite
1M
$0.08
$0.30
Cost-optimised with strong performance; best for high scale.
✅ Yes
✅ Yes
✅ Full
❌ No
xAI Grok 2
131k
$2.00
$10.00
“Raw” uncensored analysis. High context size and fast responses.
✅ Yes
✅ Yes
❌ No
❌ No
Grok 2 Vision
32k
$2.00
$10.00
Adds image/doc input. Great for mixed content analysis.
✅ Yes
✅ Yes
✅ Image + Text
❌ No
Grok 3 (Beta)
128k–1M (planned)
N/A
N/A
Expected to beat GPT-4 in reasoning. Not publicly available.
✅ Yes
✅ Yes
✅ Multimodal (video coming)
❌ No
DeepSeek V3 Chat
64k
$0.27
$1.10
MoE architecture; highly efficient for large scale.
✅ Yes
✅ Yes
❌ No
❌ No
DeepSeek R1 (Reasoner)
64k (+32k CoT)
$0.55
$2.19
Excellent at complex reasoning and CoT outputs; near-perfect coding.
✅ Yes
✅ Yes
❌ No
❌ No
There are no rows in this table
Want to print your doc?
This is not the way.
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.