Model Pricing
This section provides the latest pricing information of models available on the Compass Platform.
Text Tokens
Prices per 1M tokens.
| Model Name | Model ID/Version | Input | Output |
| GPT-5 | gpt-5 | $1.25 | $10.00 |
| GPT-5 mini | gpt-5-mini | $0.25 | $2.00 |
| GPT-4.1 | GPT-4.1 | $2.00 | $8.00 |
| GPT-4o | gpt-4o-2024-08-06 | $2.50 | $10.00 |
| GPT-4o mini | gpt-4o-mini-2024-07-18 | $0.15 | $0.60 |
| GPT-4o Audio | gpt-4o-audio-preview-2024-12-17 | $2.50 | $10.00 |
| GPT-4o Transcribe | gpt-4o-transcribe | $2.50 | $10.00 |
| GPT-4o mini Transcribe | gpt-4o-mni-transcribe | $1.25 | $5.00 |
| GPT-4o mini TTS | GPT-4o-mini-tts | $0.60 | N/A |
| GPT-4o Realtime | gpt-4o-realtime-preview-2024-12-17 | $5.00 | $20.00 |
| gpt-4o-realtime-preview-2024-10-01 | $5.00 | $20.00 | |
| gpt-realtime | gpt-realtime | $4.00 | $16.00 |
| o1-preview | o1-preview-2024-09-12 | $15.00 | $60.00 |
| o1 | o1-2024-12-17 | $15.00 | $60.00 |
| o3 | o3-2025-04-16 | $10 | $40 |
| o3-mini | o3-mini-2025-01-31 | $1.10 | $4.40 |
| o4-mini | o4-mini | $1.1 | $4.4 |
| gpt-oss-120b | gpt-oss-120b-core42-amd | $0.3 | $0.75 |
| gpt-oss-120b-qualcomm | $0.15 | $0.37 | |
| gpt-oss-120b-cerbras | $0.25 | $0.69 | |
| gpt-oss-120b-core42 | $0.3 | $0.75 | |
| gpt-oss-120b-azure | $0.4 | $0.95 | |
| gpt-oss-20b | gpt-oss-20b-core42 | $0.2 | $0.6 |
| K2 Think | k2-think-core42 | $0.15 | $0.50 |
| k2-think-cerebras | $0.15 | $0.50 |
Audio Tokens
Price per 1M tokens
| Model | Model ID/Version | Input | Output |
| GPT-4o Audio | gpt-4o-audio-preview-2024-12-17 | $40.00 | $80.00 |
| GPT-4o Realtime | gpt-4o-realtime-preview-2024-12-17 | $40.00 | $80.00 |
| GPT-4o Realtime | gpt-4o-realtime-preview-2024-10-01 | $100.00 | $200.00 |
| gpt-realtime | gpt-realtime | $32.00 | $64.00 |
| GPT-4o Transcribe | gpt-4o-transcribe | $6.00 | N/A |
| GPT-4o mini Transcribe | gpt-4o-mini-transcribe | $3.00 | N/A |
| GPT-4o mini TTS | GPT-4o-mini-tts | N/A | $12.00 |
Image Tokens
Prices per 1M tokens.
| Model | Model ID/Version | Input | Output |
| GPT Image 1 | gpt-image-1 | $10.00 | $40.00 |
| gpt-realtime | gpt-realtime | $5.00 | N/A |
Image Generation
Price per 100 images.
| Model Name | Model ID/Version | Quality | 1024*1024 | 1024*1792 | 1792*1024 |
| Dall·E 3 | dall-e-3 | Standard | $4.00 | $8.00 | $8.00 |
| HD | $8.00 | $12.00 | $12.00 |
Transcription
| Model | Model ID/Version | Per Hour |
| Whisper | whisper-1 | $0.36 |
Embeddings
Price per 1M tokens.
| Model | Model ID/Version | Input Tokens per Million | Output Tokens per Million |
| Embeddings 3 Large | text-embedding-3-large | $0.13 | $0.13 |
Batch Processing
Batch is supported with GPT-4o and GPT-4o mini models.
| Tokens Consumption | |
| Batch | 50% discount on input and output tokens with the Batch |
Fine-Tuning
Price per 1M tokens.
| Model | Model ID/Version | Training |
| GPT-4.1 | gpt-4.1-2025-04-14 | $30.3 |
Response API Tools Calling
The supported models are:
- GPT-4.1
- GPT-4o
- GPT-4o mini
- o4-mini
- o3-mini
| Tool | Cost |
| File Search Storage | $0.11 GB of vector-storage per day (1 GB free) |
| File Search Tool Call | $2.50 /1000 calls |
Available Models [Free Until December 2025]
The following models are available at no cost until December 2025. Access and usage terms may be subject to change thereafter.
Text Generation
- Claude Sonnet 4
- Cohere Command A
- Command R
- Cohere Embed 4
- Jais 30B
- Llama 3 70B
- Llama 3.3 70B
- Mixtral 8x7B
- Mistral 7B
- DeepSeek R1 0528
- Qwen 3 14B
Image Generation
-
Stable Diffusion
Embeddings
-
Qwen 3 Embedding 8B
Reranker
-
Qwen 3 Reranker 8B
Web Search [Retired on Aug 29th, 2025]
Per 1000 transactions.
| Web Search API calls | $18.00 |