customers
All customer stories
Top Voice AI companies are building with Assembly.
resources
Latest Release
Universal 3.5 Pro
Our new flagship speech-to-text model handles real-world audio the way it actually happens. Available for real-time and pre-recorded audio.
resources
Compare capabilities, context, and pricing from leading providers so you can run any LLM-based task with the same API key as your Speech-to-Text.
Showing 31 of 31 models
| Model | Provider | Context tokens | Input per 1M tokens | Output per 1M tokens | Cached in per 1M tokens |
|---|---|---|---|---|---|
GPT-5 Nano gpt-5-nano | OpenAI | 400K | $0.05 | $0.40 | $0.005 |
GPT OSS 20B gpt-oss-20b | OpenAI | 131K | $0.07 | $0.30 | — |
Gemini 2.5 Flash Lite gemini-2.5-flash-lite | 1M | $0.10 | $0.40 | $0.01 | |
Qwen3.5 4B Fast qwen3.5-4b-32k-fast | Qwen | 33K | $0.10 | $0.50 | — |
gemma-4-31b gemma-4-31b | 256K | $0.14 | $0.40 | — | |
GPT OSS 120B gpt-oss-120b | OpenAI | 131K | $0.15 | $0.60 | — |
Qwen3 32B qwen3-32B | Qwen | 200K | $0.15 | $0.60 | — |
Qwen3 Next 80B A3B qwen3-next-80b-a3b | Qwen | 200K | $0.15 | $1.20 | — |
Gemini 3.1 Flash Lite gemini-3.1-flash-lite Retires 2027-05-07 | 1M | $0.25 | $1.50 | $0.03 | |
GPT-5 mini gpt-5-mini | OpenAI | 400K | $0.25 | $2.00 | $0.03 |
Gemini 2.5 Flash gemini-2.5-flash | 1M | $0.30 | $2.50 | $0.03 | |
Gemini 3.5 Flash Lite gemini-3.5-flash-lite | 1M | $0.30 | $2.50 | $0.03 | |
Gemini 3.7 Flash gemini-3.7-flash | 1M | $0.75 | $3.75 | $0.07 | |
GPT-5.6 Luna gpt-5.6-luna | OpenAI | 270K | $1.00 | $6.00 | $0.10 |
Haiku 4.5 claude-haiku-4-5-20251001 | Anthropic | 200K | $1.00 | $5.00 | $0.10 |
Gemini 2.5 Pro gemini-2.5-pro | 200K | $1.25 | $10.00 | $0.13 | |
Gemini 3.5 Flash gemini-3.5-flash | 1M | $1.25 | $9.00 | $0.13 | |
GPT-5 gpt-5 | OpenAI | 400K | $1.25 | $10.00 | $0.13 |
GPT-5.1 gpt-5.1 | OpenAI | 400K | $1.25 | $10.00 | $0.13 |
Gemini 3.6 Flash gemini-3.6-flash | 1M | $1.50 | $7.50 | $0.15 | |
GPT-5.2 gpt-5.2 | OpenAI | 400K | $1.75 | $14.00 | $0.17 |
GPT-4.1 gpt-4.1 | OpenAI | 1M | $2.00 | $8.00 | $0.50 |
GPT-5.6 Terra gpt-5.6-terra | OpenAI | 270K | $2.50 | $15.00 | $0.25 |
Sonnet 4.5 claude-sonnet-4-5-20250929 | Anthropic | 200K | $3.00 | $15.00 | $0.30 |
Sonnet 4.6 claude-sonnet-4-6 | Anthropic | 200K | $3.00 | $15.00 | $0.30 |
Sonnet 5 claude-sonnet-5 | Anthropic | 200K | $3.00 | $15.00 | $0.30 |
GPT-5.5 gpt-5.5 | OpenAI | 272K | $5.00 | $30.00 | $0.50 |
Opus 4.5 claude-opus-4-5-20251101 | Anthropic | 200K | $5.00 | $25.00 | $0.50 |
Opus 4.6 claude-opus-4-6 | Anthropic | 200K | $5.00 | $25.00 | $0.50 |
Opus 4.7 claude-opus-4-7 | Anthropic | 1M | $5.00 | $25.00 | $0.50 |
Opus 4.8 claude-opus-4-8 | Anthropic | 1M | $5.00 | $25.00 | $0.50 |
No models match these filters.
Try clearing the search or widening the filters on the left.
Rates are for global routing. In-region US and EU endpoints are 10% higher, passed through from provider pricing with no AssemblyAI upcharge. See pricing for the full rate card.
Cached input is the rate for tokens served from the prompt cache. An em dash means the model has no cache tier. See prompt caching.
This table is generated from the Gateway's own Models endpoint, so it always matches what the API accepts. The docs roster adds quality scores and measured latency.
