Model Library
Multiverse ComputingReleased May 26, 2026HyperNova 60B 2605
Multiverse Computing · Released May 26, 2026
Intelligence score
18
At a glance
- Intelligence
- 18
- Speed
- 352.9tokens/sec
- Latency
- 950mstime to first token
- Input price
- $0.04per 1M tokens
- Output price
- $0.14per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 58.7billions
Summary
Comparison summary
HyperNova 60B 2605 scores 18 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9). HyperNova 60B 2605 generates output at 352.9 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 88.2 t/s). HyperNova 60B 2605 costs $0.04 per 1M input tokens (very competitive, median: $0.40) and $0.14 per 1M output tokens (very competitive, median: $0.84), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | HyperNova 60B 2605 |
|---|---|
| Provider | Multiverse Computing |
| Release date | May 26, 2026 |
| Intelligence score | 18 |
| Speed | 352.9 tokens/sec |
| Latency (TTFT) | 0.95s |
| Input price | $0.04 / 1M tokens |
| Output price | $0.14 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 58.7B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: hypernova-60b |
Pricing
Token prices
Price per 1M tokens
HyperNova 60B 2605, as listed in the catalog record
- Input$0.04
- Output$0.14
| Token type | Price per 1M |
|---|---|
| Input | $0.04 |
| Output | $0.14 |
Model Intelligence legacy profile: hypernova-60b
FAQ · 21
Frequently asked questions
HyperNova 60B 2605 was released on May 26, 2026.
HyperNova 60B 2605 was created by Multiverse Computing.
HyperNova 60B 2605 scores 18 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
HyperNova 60B 2605 generates output at 352.9 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 88.2 t/s).
HyperNova 60B 2605 has a time to first token (TTFT) of 0.95s (based on the median across providers serving the model), which is very competitive compared to other open weight models of similar size (median: 1.52s).
HyperNova 60B 2605 costs $0.04 per 1M input tokens (very competitive, median: $0.40) and $0.14 per 1M output tokens (very competitive, median: $0.84), based on the median across providers serving the model.
HyperNova 60B 2605 costs $0.04 per 1M input tokens and $0.14 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.05 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, HyperNova 60B 2605 generated 130M output tokens, which is at the higher end compared to other open weight models of similar size (median: 59M).
Yes, HyperNova 60B 2605 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
HyperNova 60B 2605 supports text input.
HyperNova 60B 2605 supports text output.
No, HyperNova 60B 2605 does not support image input. It can only process text.
No, HyperNova 60B 2605 is not multimodal. It only supports text input.
HyperNova 60B 2605 has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, HyperNova 60B 2605 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
HyperNova 60B 2605 has 58.7 billion parameters (4.8 billion active).
HyperNova 60B 2605 is a Mixture of Experts (MoE) model with 58.7 billion total parameters, but only 4.8 billion active parameters are used during inference.
HyperNova 60B 2605 is released under the Apache 2.0 license. This license allows commercial use.
HyperNova 60B 2605 achieves a score of 18 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, HyperNova 60B 2605 is available via API through 1 provider.
HyperNova 60B 2605 is available through 1 API provider.