Audio LLM API pricing
All 82 models that accept or produce audio, for speech input, transcription or spoken output without a separate speech model, cheapest input from $0.04 per 1M tokens. Sort by price, context window or benchmark, filter by maker, and copy the exact model ID for any serving provider. Listed prices from LiteLLM, OpenRouter and Vercel.
Models
82
with audio
Cheapest input
$0.04
per 1M tokens
Cheapest output
$0.04
per 1M tokens
Max context
1M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Maker
| Gemini 2.5 Flash |  Google | Released Jun 17, 2025 | 1M | from $0.15 via OCI | from $0.60 via OCI | 9.8 | n/a | 68% | 8 providers |
| Gemini 3.7 Flash | Google | Released Aug 14, 2026 | 1M | from $0.75 via Google | from $3.75 via Google | 39.1 | 86% | 95% | 7 providers |
| Gemini 2.5 Pro | Google | Released Jun 17, 2025 | 1M | from $1.25 via Databricks | from $10.00 via Databricks | 16.1 | 28% | 84% | 7 providers |
| Gemini 3.5 Flash | Google | Released May 22, 2026 | 1M | from $1.50 via Google | from $9.00 via Google | 32.6 | 79% | 92% | 7 providers |
| Gemini 3.1 Flash Lite | Google | Released Mar 3, 2026 | 1M | from $0.25 via Google | from $1.50 via Google | n/a | n/a | n/a | 6 providers |
| Gemini 3.5 Flash Lite | Google | Released Jul 9, 2026 | 1M | from $0.30 via Google | from $2.50 via Aihubmix | 22.2 | 54% | 84% | 6 providers |
| Gemini 3 Flash Preview | Google | Released Dec 17, 2025 | 1M | from $0.50 via Google | from $3.00 via Google | n/a | n/a | n/a | 6 providers |
| Gemini 3.6 Flash | Google | Released Jul 9, 2026 | 1M | from $0.75 via Google | from $3.75 via Google | 34.0 | 78% | 93% | 6 providers |
| Gemini 3.1 Pro Preview | Google | Released Feb 19, 2026 | 1M | from $2.00 via Google | from $12.00 via Google | 29.7 | 74% | 94% | 6 providers |
| GPT-4o |  OpenAI | Released May 13, 2024 | 131K | from $2.50 via OpenAI | from $10.00 via OpenAI | 8.4 | n/a | 54% | 6 providers |
| Gemini 2.5 Flash Lite | Google | Released Jun 17, 2025 | 1M | from $0.075 via OCI | from $0.30 via OCI | 6.7 | n/a | 47% | 5 providers |
| Gemini 3.8 Flash | Google | Released Sep 2, 2026 | 1M | from $0.75 via Google | from $3.75 via Google | 40.9 | 88% | 95% | 5 providers |
| Gemini 3 Pro Preview | Google | Released Nov 18, 2025 | 1M | from $2.00 via Google | from $12.00 via Google | n/a | n/a | n/a | 5 providers |
| Gemini 3.1 Pro Preview Custom Tools | Google | First listed Feb 2026 | 1M | from $2.00 via Google | from $12.00 via Google | n/a | n/a | n/a | 5 providers |
| Gemini 4 Argon | Google | Released Oct 13, 2026 | 1M | from $2.00 via Google | from $10.00 via Google | 52.6 | n/a | n/a | 5 providers |
| Gemini 2.0 Flash Lite | Google | First listed Mar 2025 | 1M | from $0.075 via Google | from $0.30 via Google | n/a | n/a | n/a | 4 providers |
| Gemini 2.0 Flash | Google | First listed Feb 2025 | 1M | from $0.10 via Google | from $0.40 via Google | 8.9 | n/a | 62% | 4 providers |
| Gemini 2.0 Flash 001 | Google | First listed Feb 2025 | 1M | from $0.10 via Google | from $0.40 via Google | n/a | n/a | n/a | 4 providers |
| Qwen3.8 Omni Flash |  Alibaba | Released Sep 17, 2026 | 992K | from $0.15 via Dashscope | from $0.47 via Dashscope | n/a | n/a | n/a | 4 providers |
| Voxtral Small 24B 2507 |  Mistral | Released Jul 1, 2025 | 33K | from $0.10 via Amazon Bedrock | from $0.30 via Amazon Bedrock | n/a | n/a | n/a | 3 providers |
| MiMo-V2.6-Flash |  Xiaomi | Released Sep 22, 2026 | 1M | from $0.14 via Xiaomi Mimo | from $0.28 via Xiaomi Mimo | 37.9 | n/a | n/a | 3 providers |
| Gemini 3.1 Flash Lite Preview | Google | First listed Mar 2026 | 1M | from $0.25 via Google | from $1.50 via Google | 15.6 | 31% | 82% | 3 providers |
| MiMo-V2.6-Pro | Xiaomi | Released Sep 22, 2026 | 1M | from $0.435 via Xiaomi Mimo | from $0.87 via Xiaomi Mimo | 46.3 | n/a | n/a | 3 providers |
| GPT Audio Mini | OpenAI | First listed Jan 2026 | 128K | from $0.60 via OpenAI | from $2.40 via OpenAI | n/a | n/a | n/a | 3 providers |
| Gemini Robotics Er 2 Preview | Google | First listed Aug 2026 | 131K | from $1.00 via Google | from $5.00 via Google | n/a | n/a | n/a | 3 providers |
| Gemini Omni Flash Preview | Google | Released Jun 30, 2026 | 1M | from $1.50 via Google | from $9.00 via Google | n/a | n/a | n/a | 3 providers |
| GPT Audio | OpenAI | First listed Jan 2026 | 128K | from $2.50 via OpenAI | from $10.00 via OpenAI | n/a | n/a | n/a | 3 providers |
| Gemini 2.0 Flash Lite 001 | Google | First listed Apr 2025 | 1M | from $0.075 via Google | from $0.30 via Google | 7.4 | n/a | 54% | 2 providers |
| GPT 4o Mini Audio Preview (2024-12-17) | OpenAI | First listed Dec 2024 | 128K | from $0.15 via OpenAI | from $0.60 via OpenAI | n/a | n/a | n/a | 2 providers |
| Gemini 3 Flash | Google | Released Dec 17, 2025 | 1M | from $0.50 Routed quote | from $3.00 Routed quote | 17.9 | n/a | 81% | 2 providers |
| GPT 4o Mini Realtime Preview (2024-12-17) | OpenAI | First listed Dec 2024 | 128K | from $0.60 via OpenAI | from $2.40 via OpenAI | n/a | n/a | n/a | 2 providers |
| GPT Audio Mini (2025-10-06) | OpenAI | First listed Nov 2025 | 128K | from $0.60 via OpenAI | from $2.40 via OpenAI | n/a | n/a | n/a | 2 providers |
| GPT Realtime Mini (2025-10-06) | OpenAI | First listed Nov 2025 | 128K | from $0.60 via OpenAI | from $2.40 via OpenAI | n/a | n/a | n/a | 2 providers |
| Gemini Flash LatestPointer | Google | Released May 19, 2026 | 1M | from $0.75 via Google | from $3.75 via Google | n/a | n/a | n/a | 2 providers |
| Gemini 3.8 Flash Cyber | Google | First listed Sep 2026 | 1M | from $1.50 via Vertex AI | from $7.50 via Vertex AI | n/a | n/a | n/a | 2 providers |
| Gemini Omni 1.1 Flash | Google | First listed Aug 2026 | 1M | from $1.50 via Google | from $9.00 via Google | n/a | n/a | n/a | 2 providers |
| Gemini 3.1 Pro | Google | Released Feb 19, 2026 | 1M | from $2.00 via DeepInfra | from $12.00 via DeepInfra | n/a | n/a | n/a | 2 providers |
| Gemini 3 Pro | Google | Released Nov 18, 2025 | 1M | from $2.00 via Replicate | from $12.00 via Replicate | 28.0 | n/a | 91% | 2 providers |
| Gemini Pro LatestPointer | Google | Released Feb 27, 2026 | 1M | from $2.00 via Google | from $12.00 via Google | n/a | n/a | n/a | 2 providers |
| GPT 4o Audio Preview (2024-12-17) | OpenAI | First listed Dec 2024 | 128K | from $2.50 via OpenAI | from $10.00 via OpenAI | n/a | n/a | n/a | 2 providers |
| GPT Audio 1.5 | OpenAI | First listed Feb 2026 | 128K | from $2.50 via OpenAI | from $10.00 via OpenAI | n/a | n/a | n/a | 2 providers |
| GPT Audio (2025-08-28) | OpenAI | First listed Nov 2025 | 128K | from $2.50 via OpenAI | from $10.00 via OpenAI | n/a | n/a | n/a | 2 providers |
| GPT Realtime (2025-08-28) | OpenAI | First listed Aug 2025 | 32K | from $4.00 via OpenAI | from $16.00 via OpenAI | n/a | n/a | n/a | 2 providers |
| MiMo-V2.6-Pro-UltraSpeed | Xiaomi | Released Sep 21, 2026 | 1M | from $4.35 Routed quote | from $8.70 Routed quote | n/a | n/a | n/a | 2 providers |
| GPT 4o Realtime Preview (2024-12-17) | OpenAI | First listed Dec 2024 | 128K | from $5.00 via OpenAI | from $20.00 via OpenAI | n/a | n/a | n/a | 2 providers |
| Lyria 3 Clip Preview | Google | Released Mar 25, 2026 | 131K | Free tier onlyNo paid API price listed | n/a | n/a | n/a | 2 providers | |
| Lyria 3 Pro Preview | Google | Released Mar 25, 2026 | 131K | Free tier onlyNo paid API price listed | n/a | n/a | n/a | 2 providers | |
| Voxtral Mini 3B 2507 | Mistral | First listed Dec 2025 | 33K | $0.04 via Amazon Bedrock | $0.04 via Amazon Bedrock | n/a | n/a | n/a | Amazon Bedrock cheapest mistral.voxtral-mini-3b-2507 |
| Phi 4 Multimodal Instruct |  Microsoft | Released Jul 26, 2025 | 131K | $0.08 via Azure | $0.32 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-4-multimodal-instruct |
| Voxtral Small 2507 | Mistral | Released Feb 2, 2026 | 33K | $0.10 via Mistral | $0.40 via Mistral | n/a | n/a | n/a | Mistral cheapest mistral/voxtral-small-2507 |
Reasoning modelInput $/1M
from$0.15
via OCIOutput $/1M
from$0.60
via OCIIntelligence9.88 providers
Reasoning modelInput $/1M
from$0.75
via GoogleOutput $/1M
from$3.75
via GoogleIntelligence39.17 providers
Reasoning modelInput $/1M
from$1.25
via DatabricksOutput $/1M
from$10.00
via DatabricksIntelligence16.17 providers
Reasoning modelInput $/1M
from$1.50
via GoogleOutput $/1M
from$9.00
via GoogleIntelligence32.67 providers
Reasoning modelInput $/1M
from$0.25
via GoogleOutput $/1M
from$1.50
via GoogleIntelligencen/a6 providers
Reasoning modelInput $/1M
from$0.30
via GoogleOutput $/1M
from$2.50
via AihubmixIntelligence22.26 providers
Reasoning modelInput $/1M
from$0.50
via GoogleOutput $/1M
from$3.00
via GoogleIntelligencen/a6 providers
Reasoning modelInput $/1M
from$0.75
via GoogleOutput $/1M
from$3.75
via GoogleIntelligence34.06 providers
Reasoning modelInput $/1M
from$2.00
via GoogleOutput $/1M
from$12.00
via GoogleIntelligence29.76 providers
Input $/1M
from$2.50
via OpenAIOutput $/1M
from$10.00
via OpenAIIntelligence8.46 providers
Reasoning modelInput $/1M
from$0.075
via OCIOutput $/1M
from$0.30
via OCIIntelligence6.75 providers
Reasoning modelInput $/1M
from$0.75
via GoogleOutput $/1M
from$3.75
via GoogleIntelligence40.95 providers
Reasoning modelInput $/1M
from$2.00
via GoogleOutput $/1M
from$12.00
via GoogleIntelligencen/a5 providers
Reasoning modelInput $/1M
from$2.00
via GoogleOutput $/1M
from$12.00
via GoogleIntelligencen/a5 providers
Reasoning modelInput $/1M
from$2.00
via GoogleOutput $/1M
from$10.00
via GoogleIntelligence52.65 providers
Input $/1M
from$0.075
via GoogleOutput $/1M
from$0.30
via GoogleIntelligencen/a4 providers
Input $/1M
from$0.10
via GoogleOutput $/1M
from$0.40
via GoogleIntelligence8.94 providers
Input $/1M
from$0.10
via GoogleOutput $/1M
from$0.40
via GoogleIntelligencen/a4 providers
Reasoning modelInput $/1M
from$0.15
via DashscopeOutput $/1M
from$0.47
via DashscopeIntelligencen/a4 providers
Input $/1M
from$0.10
via Amazon BedrockOutput $/1M
from$0.30
via Amazon BedrockIntelligencen/a3 providers
Reasoning modelInput $/1M
from$0.14
via Xiaomi MimoOutput $/1M
from$0.28
via Xiaomi MimoIntelligence37.93 providers
Reasoning modelInput $/1M
from$0.25
via GoogleOutput $/1M
from$1.50
via GoogleIntelligence15.63 providers
Reasoning modelInput $/1M
from$0.435
via Xiaomi MimoOutput $/1M
from$0.87
via Xiaomi MimoIntelligence46.33 providers
Input $/1M
from$0.60
via OpenAIOutput $/1M
from$2.40
via OpenAIIntelligencen/a3 providers
Reasoning modelInput $/1M
from$1.00
via GoogleOutput $/1M
from$5.00
via GoogleIntelligencen/a3 providers
Reasoning modelInput $/1M
from$1.50
via GoogleOutput $/1M
from$9.00
via GoogleIntelligencen/a3 providers
Input $/1M
from$2.50
via OpenAIOutput $/1M
from$10.00
via OpenAIIntelligencen/a3 providers
Input $/1M
from$0.075
via GoogleOutput $/1M
from$0.30
via GoogleIntelligence7.42 providers
Input $/1M
from$0.15
via OpenAIOutput $/1M
from$0.60
via OpenAIIntelligencen/a2 providers
Input $/1M
from$0.50
Routed quoteOutput $/1M
from$3.00
Routed quoteIntelligence17.92 providers
Input $/1M
from$0.60
via OpenAIOutput $/1M
from$2.40
via OpenAIIntelligencen/a2 providers
Input $/1M
from$0.60
via OpenAIOutput $/1M
from$2.40
via OpenAIIntelligencen/a2 providers
Input $/1M
from$0.60
via OpenAIOutput $/1M
from$2.40
via OpenAIIntelligencen/a2 providers
Reasoning modelInput $/1M
from$0.75
via GoogleOutput $/1M
from$3.75
via GoogleIntelligencen/a2 providers
Reasoning modelInput $/1M
from$1.50
via Vertex AIOutput $/1M
from$7.50
via Vertex AIIntelligencen/a2 providers
Reasoning modelInput $/1M
from$1.50
via GoogleOutput $/1M
from$9.00
via GoogleIntelligencen/a2 providers
Reasoning modelInput $/1M
from$2.00
via DeepInfraOutput $/1M
from$12.00
via DeepInfraIntelligencen/a2 providers
Input $/1M
from$2.00
via ReplicateOutput $/1M
from$12.00
via ReplicateIntelligence28.02 providers
Reasoning modelInput $/1M
from$2.00
via GoogleOutput $/1M
from$12.00
via GoogleIntelligencen/a2 providers
Input $/1M
from$2.50
via OpenAIOutput $/1M
from$10.00
via OpenAIIntelligencen/a2 providers
Input $/1M
from$2.50
via OpenAIOutput $/1M
from$10.00
via OpenAIIntelligencen/a2 providers
Input $/1M
from$2.50
via OpenAIOutput $/1M
from$10.00
via OpenAIIntelligencen/a2 providers
Input $/1M
from$4.00
via OpenAIOutput $/1M
from$16.00
via OpenAIIntelligencen/a2 providers
Reasoning modelInput $/1M
from$4.35
Routed quoteOutput $/1M
from$8.70
Routed quoteIntelligencen/a2 providers
Input $/1M
from$5.00
via OpenAIOutput $/1M
from$20.00
via OpenAIIntelligencen/a2 providers
Free tier onlyNo paid API price listed. Expand to see who serves it.
Intelligencen/a2 providers
Free tier onlyNo paid API price listed. Expand to see who serves it.
Intelligencen/a2 providers
Input $/1M
$0.04
via Amazon BedrockOutput $/1M
$0.04
via Amazon BedrockIntelligencen/aAmazon Bedrock
Input $/1M
$0.08
via AzureOutput $/1M
$0.32
via AzureIntelligencen/aAzure
Input $/1M
$0.10
via MistralOutput $/1M
$0.40
via MistralIntelligencen/aMistral
1–50 of 89 models
Page 1 of 2
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 61 prices older, back to Jul 18, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI