InternVL3 78B
InternVL3 78B is InternLM's language model with a 16K context window and up to 16K output tokens, starting at $0.9 / 1M input and $0.9 / 1M output. A 78B-parameter multimodal vision-language model combining superior visual perception and language generation in a ViT-MLP-LLM architecture.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.9 | $0.9 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host InternVL3 78B, ranked by cheapest on-demand price. The model needs about 187 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP40s |  Azure | 4× AMD Alveo U250 FPGA (64GB) | 256 GB | $6.60/hr | westus2 | |
| g2-standard-96 |  GCP | 8× nvidia-l4 | 192 GB | $7.98/hr | us-east4 | |
| g7e.12xlarge |  AWS | 2× RTX PRO Server 6000 | 192 GB | $8.29/hr | us-east-1 | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| InternVL3 78B | — | 16K | $0.900 | $0.900 | Current |
| InternVL3 38B | — | 16K | $0.900 | $0.900 | Available |
| InternVL3 8B | — | 16K | $0.200 | $0.200 | Available |
| InternLM 2.5 20B Chat | — | 33K | — | — | Available |