Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
- Perceptron Mk1.5PerceptronRemove
- Nova-3DeepgramRemove
- Transcribe 1 ProFish AudioRemove
- S2.1 ProFish AudioRemove
4 is the maximum. Remove one to add another.
| Attribute | Perceptron Mk1.5perceptron-mk1.5 | Nova-3nova-3 | Transcribe 1 Protranscribe-1-pro | S2.1 Pros2.1-pro |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0.15 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Output | $1.50 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Cache Write (5m) | $0.15 / 1M | Not applicable | Not applicable | Not applicable |
| Cache Write (1h) | $0.15 / 1M | Not applicable | Not applicable | Not applicable |
| Cache Read | $0.15 / 1M | Not applicable | Not applicable | Not applicable |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 36.9K | N/A | N/A | N/A |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | No | No | No | No |
| Function Calling | No | No | No | No |
| JSON Mode | No | No | No | No |
| Streaming | Yes | No | No | No |
| Catalogue | ||||
| Provider | Perceptron | Deepgram | Fish Audio | Fish Audio |
| Category | chat | voice | voice | voice |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | 2026-09-25 | 2026-07-15 | 2026-09-24 | 2026-07-29 |
| Description | ||||
| Summary | Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token. | Deepgram Nova-3 speech-to-text. Billed per second of audio. | Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio. | Fish Audio S2.1 Pro text-to-speech. Billed per UTF-8 byte of input text. |