GPT-4 Turbo, APIs getting cheaper and they are getting more capable
It's been 6 hours since the conference concluded and there's a lot of exciting news for us, developers!
Here're the highlights:
-
GPT-4 Turbo API
- Huge 128K context - the current GPT4 API has 8k and 32k flavours, the largest context available in commercial LLM so far is 100k in Anthropic's Claude 1/2
-
!!! 4 to 6 times cheaper than GPT-4 32K
- $0.01 per 1k input tokens vs $0.06 in GPT-4 32K
- $0.03 vs $0.12 for 1k output tokens
- Knowledge cut-off is now April 2023
-
GPT-4 Turbo with vision can now accept images along the text
- Available via
gpt-4-vision-preview
- Available via
- Opening GPT-4 for fine-tuning
- GPT-3.5 Turbo also gets updates in new API versions
- New APIs versions (
gpt-3.5-turbo-1006andgpt-4-1106-preview)- Improved instruction following
- 38% improvement on format following tasks such as generating JSON, XML and YAML for GPT-3.5 Turbo
- Function calling with improved accuracy and multiple functions called in one request
- JSON mode via
response_formatparam - Reproducible outputs via
seedparam -
logprobsparam in Completion API (log probabilities for the most likely output tokens)
- Improved instruction following
- Other services and features
- Assistants API - build and integrate AI agents in apps. One of the features is persistent and infinitely long threads (remember those context size limits and the necessity to send entire conversations via Chat APIs)
- Better quality Text-to-speech
-
dall-e-3image generator - Model customisations for enterprise customers
- Whisper v3 and Consistency Decoder
Prices are going down
| Older models | New models | |
|---|---|---|
| GPT-4 Turbo | GPT-4 8K Input: $0.03 Output: $0.06 GPT-4 32K Input: $0.06 Output: $0.12 |
GPT-4 Turbo 128K Input: $0.01 Output: $0.03 |
| GPT-3.5 Turbo | GPT-3.5 Turbo 4K Input: $0.0015 Output: $0.002 GPT-3.5 Turbo 16K Input: $0.003 Output: $0.004 |
GPT-3.5 Turbo 16K Input: $0.001 Output: $0.002 |
| GPT-3.5 Turbo fine-tuning | GPT-3.5 Turbo 4K fine-tuning Training: $0.008 Input: $0.012 Output: $0.016 |
GPT-3.5 Turbo 4K and 16K fine-tuning Training: $0.008 Input: $0.003 Output: $0.006 |
Coming soon
The new changes are expected to be rolled out in the coming weeks and become available to the paying customers. Also looking forward to the new features becoming available in Azure!
Top comments (0)