GPT-3.5-turbo-instruct
GPT-3.5-turbo-instruct is a text model from
OpenAI with a context window of 8K tokens and max output of 4K tokens. Pricing starts at 1.50 per million input tokens and 2.00 per million output tokens (cheapest at OpenAI).
Capabilities
✗ Vision✗ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Specifications
| Model Key | gpt-3.5-turbo-instruct |
| Provider | |
| Provider ID | text-completion-openai |
| Mode | Text |
| Canonical Name | gpt-3.5 |
| Context Window | 8K tokens |
| Max Output | 4K tokens |
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | 0.0015 | 1.50 |
| Output Tokens | 0.0020 | 2.00 |
Price Comparison by Provider
Compare prices for GPT-3.5-turbo-instruct across different providers. The same model may be available through multiple providers at different price points.
Provider | Model Key | Input Price, $ | Output Price, $ |
|---|---|---|---|
| vercel_ai_gateway/openai/gpt-3.5-turbo | 0.500 | 1.50 | |
| openrouter/openai/gpt-3.5-turbo | 1.50 | 2.00 | |
| gpt-3.5-turbo-instruct | 1.50 | 2.00 | |
| gpt-3.5-turbo | 0.500 | 1.50 | |
| github_copilot/gpt-3.5-turbo | N/A | N/A | |
| azure/gpt-35-turbo-instruct-0914 | 1.50 | 2.00 | |
| azure/gpt-3.5-turbo-0125 | 0.500 | 1.50 |
All Variants
All available versions, regions, and API endpoints for GPT-3.5-turbo-instruct.
Model Key | Provider | Mode | Input Price, $ | Output Price, $ | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| azure/gpt-3.5-turbo | Text | 0.500 | 1.50 | 4K | 4K | no | yes | |
| azure/gpt-3.5-turbo-0125 | Text | 0.500 | 1.50 | 16K | 4K | no | yes | |
| azure/gpt-35-turbo | Text | 0.500 | 1.50 | 4K | 4K | no | yes | |
| azure/gpt-35-turbo-0125 | Text | 0.500 | 1.50 | 16K | 4K | no | yes | |
| azure/gpt-35-turbo-0301 | Text | N/A | N/A | 4K | 4K | no | yes | |
| azure/gpt-35-turbo-0613 | Text | N/A | N/A | 4K | 4K | no | yes | |
| azure/gpt-35-turbo-1106 | Text | 1.00 | 2.00 | 16K | 4K | no | yes | |
| azure/gpt-35-turbo-16k | Text | 3.00 | 4.00 | 16K | 4K | no | no | |
| azure/gpt-35-turbo-16k-0613 | Text | 3.00 | 4.00 | 16K | 4K | no | yes | |
| github_copilot/gpt-3.5-turbo | Text | N/A | N/A | 16K | 4K | no | yes | |
| github_copilot/gpt-3.5-turbo-0613 | Text | N/A | N/A | 16K | 4K | no | yes | |
| azure/gpt-3.5-turbo-instruct-0914 | Text | 1.50 | 2.00 | 4K | N/A | no | no | |
| azure/gpt-35-turbo-instruct | Text | 1.50 | 2.00 | 4K | N/A | no | no | |
| azure/gpt-35-turbo-instruct-0914 | Text | 1.50 | 2.00 | 4K | N/A | no | no | |
| ft:gpt-3.5-turbo | Text | 3.00 | 6.00 | 16K | 4K | no | no | |
| ft:gpt-3.5-turbo-0125 | Text | 3.00 | 6.00 | 16K | 4K | no | no | |
| ft:gpt-3.5-turbo-0613 | Text | 3.00 | 6.00 | 4K | 4K | no | no | |
| ft:gpt-3.5-turbo-1106 | Text | 3.00 | 6.00 | 16K | 4K | no | no | |
| gpt-3.5-turbo | Text | 0.500 | 1.50 | 16K | 4K | no | yes | |
| gpt-3.5-turbo-0125 | Text | 0.500 | 1.50 | 16K | 4K | no | yes | |
| gpt-3.5-turbo-0301 | Text | N/A | N/A | 4K | 4K | no | no | |
| gpt-3.5-turbo-0613 | Text | N/A | N/A | 4K | 4K | no | yes | |
| gpt-3.5-turbo-1106 | Text | 1.00 | 2.00 | 16K | 4K | no | yes | |
| gpt-3.5-turbo-16k | Text | 3.00 | 4.00 | 16K | 4K | no | no | |
| gpt-3.5-turbo-16k-0613 | Text | N/A | N/A | 16K | 4K | no | no | |
| gpt-3.5-turbo-instruct | Text | 1.50 | 2.00 | 8K | 4K | no | no | |
| gpt-3.5-turbo-instruct-0914 | Text | 1.50 | 2.00 | 8K | 4K | no | no | |
| openrouter/openai/gpt-3.5-turbo | Text | 1.50 | 2.00 | 4K | N/A | no | no | |
| openrouter/openai/gpt-3.5-turbo-16k | Text | 3.00 | 4.00 | 16K | N/A | no | no | |
| vercel_ai_gateway/openai/gpt-3.5-turbo | Text | 0.500 | 1.50 | 16K | 4K | no | yes | |
| vercel_ai_gateway/openai/gpt-3.5-turbo-instruct | Text | 1.50 | 2.00 | 8K | 4K | no | no |