Hyperbolic: Models Intelligence, Performance & Price
Analysis of Hyperbolic's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Hyperbolic for your use-case.
Most Intelligent
gpt-oss-120B (high)
DeepSeek R1 0528
Qwen3 Next 80B A3BQwen3 235B 2507Qwen3 Coder 480B (FP8)Intelligence index
Total 13 models
Fastest
gpt-oss-120B (high)gpt-oss-120B (low)Qwen3 Next 80B A3BQwen3 Next 80B A3Bgpt-oss-20B (high)Output speed
Total 13 models
Lowest Price
gpt-oss-20B (high)gpt-oss-20B (low)DeepSeek V3 (Dec) (FP8)gpt-oss-120B (high)Qwen3 Next 80B A3BBlended price (per 1M tokens)
Total 13 models
Hyperbolic offers 13 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Hyperbolic are gpt-oss-120B (high) (33), DeepSeek R1 0528 (27), Qwen3 Next 80B A3B (27).
- For output speed, the fastest models are gpt-oss-120B (high) (534 t/s), gpt-oss-120B (low) (489 t/s), Qwen3 Next 80B A3B (329 t/s). Speed varies significantly across models, with a 321% difference between the fastest and slowest.
- For latency, gpt-oss-120B (high) (0.63s), gpt-oss-120B (low) (0.65s), gpt-oss-20B (low) (0.78s) offer the lowest time to first token.
- For pricing, gpt-oss-20B (high) ($0.10), gpt-oss-20B (low) ($0.10), DeepSeek V3 (Dec) (FP8) ($0.25) offer the lowest blended prices per 1M tokens. Prices vary up to 3.0x across models.
- For context window size, Qwen3 Next 80B A3B (262k), Qwen3 235B 2507 (262k), Qwen3 Coder 480B (FP8) (262k) support the largest context windows on Hyperbolic.
- gpt-oss-120B (high) offers the best combination of intelligence and speed. For cost optimization, gpt-oss-20B (high) provides the most competitive pricing.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Intelligence vs. Price
Context Window
Context Window
JSON Mode & Function Calling
Function (Tool) Calling & JSON Mode
| Models | Function calling | JSON Mode |
|---|---|---|
| gpt-oss-120B (high), Hyperbolic | ||
| DeepSeek R1 0528, Hyperbolic | ||
| Qwen3 Next 80B A3B, Hyperbolic | ||
| Qwen3 235B 2507, Hyperbolic | ||
| Qwen3 Coder 480B (FP8), Hyperbolic | ||
| gpt-oss-20B (high), Hyperbolic | ||
| gpt-oss-120B (low), Hyperbolic | ||
| DeepSeek V3 0324, Hyperbolic | ||
| gpt-oss-20B (low), Hyperbolic | ||
| Qwen3 Next 80B A3B, Hyperbolic | ||
| DeepSeek R1 (Jan), Hyperbolic | ||
| DeepSeek V3 (Dec) (FP8), Hyperbolic |
Pricing
Intelligence vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Key definitions
Frequently Asked Questions
Common questions about Hyperbolic
Hyperbolic offers 13 models that we track: gpt-oss-120B (high), DeepSeek R1 0528, Qwen3 Next 80B A3B, Qwen3 235B 2507, Qwen3 Coder 480B, gpt-oss-20B (high), gpt-oss-120B (low), DeepSeek V3 0324, gpt-oss-20B (low), Qwen3 Next 80B A3B, DeepSeek R1 (Jan), DeepSeek V3 (Dec), and Llama 3.3 70B.
The most intelligent model available on Hyperbolic is gpt-oss-120B (high) with an Intelligence Index score of 33.
The fastest model on Hyperbolic by output speed is gpt-oss-120B (high) at 534.2 tokens per second.
The model with the lowest time to first token on Hyperbolic is gpt-oss-120B (high) at 0.63s. Lower latency means faster initial response time.
The most affordable model on Hyperbolic by blended price is gpt-oss-20B (high) at $0.10 per 1M tokens (3:1 input to output ratio).
Prices on Hyperbolic vary up to 30x across models, from $0.10 per 1M tokens for gpt-oss-20B (high) to $3.00 per 1M tokens for DeepSeek R1 0528.
Yes, Hyperbolic offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
8 of 13 models on Hyperbolic support JSON mode for structured output.
9 of 13 models on Hyperbolic support function calling (tool use).
Yes, Hyperbolic offers 7 reasoning models: gpt-oss-120B (high), DeepSeek R1 0528, Qwen3 Next 80B A3B, gpt-oss-20B (high), gpt-oss-120B (low), gpt-oss-20B (low), and DeepSeek R1 (Jan). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 13 models on Hyperbolic are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Hyperbolic, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.