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.
| Attribute | Perceptron Mk1.5perceptron-mk1.5 | Transcribe 1 Protranscribe-1-pro | Gemma 4 31Bgemma-4-31b-it |
|---|---|---|---|
| Pricing | |||
| Input | $0.15 / 1M | — Not priced per input token | $0.14 / 1M |
| Output | $1.50 / 1M | — Not priced per output token | $0.40 / 1M |
| Cache Write (5m) | $0.15 / 1M | Not applicable | $0.14 / 1M |
| Cache Write (1h) | $0.15 / 1M | Not applicable | $0.14 / 1M |
| Cache Read | $0.15 / 1M | Not applicable | $0.14 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 36.9K | N/A | 262.1K |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | No | No | Yes |
| Function Calling | No | No | Yes |
| JSON Mode | No | No | Yes |
| Streaming | Yes | No | Yes |
| Catalogue | |||
| Provider | Perceptron | Fish Audio | |
| Category | chat | voice | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | 2026-09-25 | 2026-09-24 | — |
| Description | |||
| Summary | Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token. | Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio. | Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model, supporting text and image inputs with text outputs. It features a 256K token context window, configurable thinking/reasoning modes, native function calling, and broad multilingual support across 140+ languages. The model delivers strong performance in coding, reasoning, and document understanding, making it well suited for developer workflows, multilingual applications, and structured knowledge tasks. |