InternVL3 38B


InternVL3 38B is Opengvlab's language model with a 16K context window and up to 16K output tokens, starting at $0.900 / 1M input and $0.900 / 1M output. A 38B-parameter multimodal LLM combining a Vision Transformer with a language model for advanced vision-language understanding tasks.
Spec
Canonical IDopengvlab-internvl3-38b
TypeLanguage
StatusActive
CreatorOpengvlab
Providers
Context Window16K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Parameters38B

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

ProviderStandard
Input
$ / 1M
Output
$ / 1M
Fireworks AI logo
Fireworks AI
accounts/fireworks/models/internvl3-38b
$0.900$0.900

Cost Calculator

Preset:
Compares every provider & tier in USD

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
InternVL3 38B16KAvailable
InternVL3 78B16KAvailable
InternVL3 8B16KAvailable
InternVL3 38B16K$0.900$0.900Current
InternVL3 78B16K$0.900$0.900Available
InternVL3 8B16K$0.200$0.200Available

Model IDs