Hyperbolic

United States

Compare

Performance

Latency and throughput from recent gateway traffic, with leading models for each signal.

Models

Browse models available through Hyperbolic.

14 models

DeepSeek R1Not active

deepseek/deepseek-r1-fp8

$2 / 1M tokens

Input

Text

Output

Text

—

Flux 1 DevNot active

black-forest-labs/flux-1-dev

$0.01 / image

Input

Text

Output

Image

—

Qwen 2.5 Coder 32B InstructNot active

qwen/qwen2.5-coder-32b-fp8

$0.20 / 1M tokens

Input

Text

Output

Text

—

Qwen 2.5 VL 7B InstructNot active

qwen/qwen2.5-vl-7b-instruct-bf16

$0.20 / 1M tokens

Input

ImageText

Output

Text

—

Qwen 3 Coder 480B A35B InstructNot active

qwen/qwen3-coder-480b-a35b-fp8

$2 / 1M tokens

Input

Text

Output

Text

—

Qwen 3 Next 80B A3B InstructNot active

qwen/qwen3-next-80b-a3b-instruct

$0.30 / 1M tokens

Input

Text

Output

Text

—

Qwen 3 Next 80B A3B ThinkingNot active

qwen/qwen3-next-80b-a3b-thinking

$0.30 / 1M tokens

Input

Text

Output

Text

—

GPT OSS 120bNot active

openai/gpt-oss-120b-fp8

$0.30 / 1M tokens

Input

Text

Output

Text

5 Aug 2025

GPT OSS 20bNot active

openai/gpt-oss-20b-fp8

$0.10 / 1M tokens

Input

Text

Output

Text

5 Aug 2025

DeepSeek R1 (2025-05-28)Not active

deepseek/deepseek-r1-0528-fp8

$3 / 1M tokens

Input

Text

Output

Text

28 May 2025

DeepSeek V3 (2025-03-24)Not active

deepseek/deepseek-v3-0324-fp8

$1.25 / 1M tokens

Input

Text

Output

Text

24 Mar 2025

Qwen 2.5 VL 72B InstructNot active

qwen/qwen2.5-vl-72b-instruct-bf16

$0.60 / 1M tokens

Input

ImageText

Output

Text

26 Jan 2025

Llama 3.3 70B InstructNot active

meta/llama-3.3-70b-fp8

$0.40 / 1M tokens

Input

Text

Output

Text

6 Dec 2024

Llama 3.1 8B InstructNot active

meta/llama-3.1-8b-fp8

$0.10 / 1M tokens

Input

Text

Output

Text

23 Jul 2024

Help keep public data accurate

Help keep public data accurate

Hyperbolic

Performance

Models

Token usage