GPT-4 Turbo

unknown

OpenAI · gpt family

Compact GPT model for low-latency assistance and high-volume workloads

Limits

Context128,000
InputUnknown
Output4,096

Modalities

Inputtext, image
Outputtext

Release info

Release2023-11-06
Last update2024-04-09
Knowledge cutoff2023-12

Provider offerings

Provider-specific prices and limits stay separate from canonical model facts.

ProviderProvider model IDInputOutputContextOutput limit
Azuregpt-4-turbo$10 / 1M$30 / 1M128,0004,096
Azure Cognitive Servicesgpt-4-turbo$10 / 1M$30 / 1M128,0004,096
OpenAIgpt-4-turbo$10 / 1M$30 / 1M128,0004,096
LLM Gatewaygpt-4-turbo$10 / 1M$30 / 1M128,0004,096
Cloudflare AI Gatewayopenai/gpt-4-turbo$10 / 1M$30 / 1M128,0004,096
Poeopenai/gpt-4-turbo$9 / 1M$27 / 1M128,0004,096
Vercel AI Gatewayopenai/gpt-4-turbo$10 / 1M$30 / 1M128,0004,096
Kilo Gatewayopenai/gpt-4-turbo$10 / 1M$30 / 1M128,0004,096
OrcaRouteropenai/gpt-4-turbo$10 / 1M$30 / 1M128,0004,096
NanoGPTopenai/gpt-4-turbo$10 / 1M$30 / 1M128,0004,096
OpenRouteropenai/gpt-4-turbo$10 / 1M$30 / 1M128,0004,096

Capabilities

Attachments

Yes

Reasoning

No

Tool calling

Yes

Structured output

No

Temperature

Yes