Phi-4-multimodal-instruct
GitHub ModelsOpen weights
Phi-4-multimodal-instruct by GitHub Models costs $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 128K-token context window.
Pricing
Input (per 1M tokens)
$0.00
Output (per 1M tokens)
$0.00
Cached input (per 1M)
—
Specifications
- Provider
- GitHub Models
- Context window
- 128K tokens
- Parameters
- —
- Released
- Dec 2024
- Open weights
- Yes
- Frontier model
- No
Compare Phi-4-multimodal-instruct with…
Phi-4-multimodal-instruct vs Grok Code Fast 1$0.00/1MPhi-4-multimodal-instruct vs Gemma 4 31B IT$0.00/1MPhi-4-multimodal-instruct vs DeepSeek R1 Distill Qwen 1.5B$0.00/1MPhi-4-multimodal-instruct vs Qwen3-Max-Preview$0.00/1MPhi-4-multimodal-instruct vs Codestral 25.01$0.00/1MPhi-4-multimodal-instruct vs Llama-4-Maverick-17B-128E-Instruct-FP8$0.00/1M
FAQ
How much does Phi-4-multimodal-instruct cost?
Phi-4-multimodal-instruct is priced at $0.00 per 1M input tokens and $0.00 per 1M output tokens. Output tokens cost more than input.
What is Phi-4-multimodal-instruct's context window?
Phi-4-multimodal-instruct supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.
Is Phi-4-multimodal-instruct open weight?
Yes — Phi-4-multimodal-instruct has openly available weights.
Data as of 2026-06-28. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.