All Models

Browse 26 models across 8 providers.

O

OpenAI

6 models
OGPT-4.1

Latest flagship with 1M context window and strong coding/instruction following

$2 in$8 out1M
OGPT-4.1 Mini

Affordable intelligence with 1M context — best cost/performance in the 4.1 family

$0.4 in$1.6 out1M
OGPT-4o

Multimodal model with strong vision, audio, and text capabilities

$2.5 in$10 out128k
OGPT-4o Mini

Ultra-affordable model for high-volume tasks with good quality

$0.15 in$0.6 out128k
Oo3

Advanced reasoning model at significantly reduced price (80% cut from launch)

$0.4 in$1.6 out200k
Oo4-mini

Fast, efficient reasoning model optimized for STEM and coding tasks

$1.1 in$4.4 out200k
A

Anthropic

4 models
AClaude Opus 4.7

Most capable Claude model — step-change improvement in agentic coding

$5 in$25 out1M
AClaude Sonnet 4.6

Optimal balance of intelligence, cost, and speed with 1M context

$3 in$15 out1M
AClaude Haiku 4.5

Fastest and most cost-efficient Claude with near-frontier intelligence

$1 in$5 out200k
AClaude Opus 4.6

Previous flagship — strong reasoning and extended thinking support

$5 in$25 out1M
G

Google

3 models
GGemini 2.5 Pro

Most capable Gemini model with deep reasoning and multimodal support

$1.25 in$10 out1M
GGemini 2.5 Flash

Best-in-class speed and efficiency for diverse tasks

$0.3 in$2.5 out1M
GGemini 2.5 Flash-Lite

Most cost-efficient Gemini model for high-volume, latency-sensitive workloads

$0.1 in$0.4 out1M
M

Mistral

5 models
MMistral Large 3

Frontier-level MoE model (675B total / 41B active params) at competitive price

$0.5 in$1.5 out256k
MMagistral Medium

Mistral's reasoning model — strong for complex analytical and math tasks

$2 in$5 out128k
MMistral Medium 3

State-of-the-art performance at 8x lower cost than previous generation

$0.4 in$2 out128k
MMistral Small 3.1

Efficient small model for simple, high-volume tasks

$0.1 in$0.3 out128k
MCodestral

Code-specialized model with 256k context — optimized for fill-in-the-middle

$0.3 in$0.9 out256k
D

DeepSeek

2 models
DDeepSeek Chat

Cost-efficient chat model with strong multilingual performance. Best price-to-quality for Asian languages.

$0.27 in$1.1 out64k
DDeepSeek R1

Open-source reasoning model matching o1-level performance at a fraction of the cost. Ideal for math, coding, logic.

$0.55 in$2.19 out64k
L

Meta

2 models
LLlama 3.1 8B

Meta's efficient open-source model. Cheapest option for high-volume tasks via third-party API providers.

$0.02 in$0.05 out128k
LLlama 3.3 70B

Meta's large open-source model with strong reasoning. Great value via providers like Together AI or Fireworks.

$0.23 in$0.4 out128k
X

xAI

2 models
XGrok 3

xAI's flagship model with real-time web access and strong performance on coding and analysis.

$3 in$15 out128k
XGrok 3 Mini

xAI's efficient model optimized for fast responses and cost-sensitive workloads.

$0.3 in$0.5 out128k
Q

Qwen

2 models
QQwen3 235B

Alibaba's large MoE model with exceptional price — $0.06/1M for both input and output tokens.

$0.06 in$0.06 out32k
QQwen3.5 Flash

Alibaba's fastest model with 256k context window at near-zero cost. Best for ultra high-volume tasks.

$0.01 in$0.05 out256k