Phi-4-mini-instruct
wandb · chat model
Phi-4-mini-instruct is listed here as a chat model from wandb. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$8000.0000 / 1M tokens
Output
$35000.0000 / 1M tokens
Cached input
N/A
Context
128.0K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $8000.0000 / 1M tokens |
| Output | $35000.0000 / 1M tokens |
| Embedding | $8000.0000 / 1M tokens |
Token limits
Context window
128.0K
Max input tokens
128.0K
Max output tokens
128.0K
Max tokens
128.0K
Capabilities
| Capability | Supported |
|---|---|
| Vision | — |
| Function calling | — |
| Parallel function calling | — |
| Tool choice | — |
| Prompt caching | — |
| Reasoning | — |
| Response schema | — |
| System messages | — |
| Audio input | — |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| MMLU | 84.8 | Popular Aggregated Benchmark | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| GPQA | 56.1 | Science | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| HumanEval | 82.6 | Code Generation | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| DROP | 75.5 | Reasoning | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| MMLU | 84.8 | Popular Aggregated Benchmark | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| GPQA | 56.1 | Science | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| HumanEval | 82.6 | Code Generation | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| SimpleQA | 3.0 | Factual Knowledge | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| DROP | 75.5 | Reasoning | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| Phi-4-mini-instruct wandb | In $8000.0000 / 1M tokens Out $35000.0000 / 1M tokens |
Output: unknown | No public capabilities | 128.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gpt-oss-20b wandb | In $5000.0000 / 1M tokens Out $20000.0000 / 1M tokens |
Output: unknown | Low overlap | 131.1K | Same provider Overall 27% |
| gpt-oss-120b wandb | In $15000.0000 / 1M tokens Out $60000.0000 / 1M tokens |
Output: unknown | Low overlap | 131.1K | Same provider Overall 26% |
| Llama-3.1-8B-Instruct wandb | In $22000.0000 / 1M tokens Out $22000.0000 / 1M tokens |
Output: unknown | Low overlap | 128.0K | Same provider Overall 25% |
| Llama-3.3-70B-Instruct wandb | In $71000.0000 / 1M tokens Out $71000.0000 / 1M tokens |
Output: unknown | Low overlap | 128.0K | Same provider Overall 21% |
| DeepSeek-V3.1 wandb | In $55000.0000 / 1M tokens Out $165000.0000 / 1M tokens |
Output: unknown | Low overlap | 128.0K | Same provider Overall 19% |
| GLM-4.5 wandb | In $55000.0000 / 1M tokens Out $200000.0000 / 1M tokens |
Output: unknown | Low overlap | 131.1K | Same provider Overall 18% |
| Qwen3-235B-A22B-Instruct-2507 wandb | In $10000.0000 / 1M tokens Out $10000.0000 / 1M tokens |
Output: unknown | Low overlap | 262.1K | Same provider Overall 18% |
| Qwen3-235B-A22B-Thinking-2507 wandb | In $10000.0000 / 1M tokens Out $10000.0000 / 1M tokens |
Output: unknown | Low overlap | 262.1K | Same provider Overall 18% |
| Llama-4-Scout-17B-16E-Instruct wandb | In $17000.0000 / 1M tokens Out $66000.0000 / 1M tokens |
Output: unknown | Low overlap | 64.0K | Same provider Overall 18% |
| jais-30b-chat azure_ai | In $3200.0000 / 1M tokens Out $9710.0000 / 1M tokens | text
Output: text | Low overlap | 8.2K | Partial I/O overlap Overall 8% |
| ai21.jamba-1-5-large-v1:0 Bedrock | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | text
Output: text | Low overlap | 256.0K | Partial I/O overlap Overall 8% |
| ai21.jamba-1-5-mini-v1:0 Bedrock | In $0.2000 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | Low overlap | 256.0K | Partial I/O overlap Overall 8% |
| ai21.j2-ultra-v1 Bedrock | In $18.8000 / 1M tokens Out $18.8000 / 1M tokens | text
Output: text | Low overlap | 8.2K | Partial I/O overlap Overall 1% |
| ai21.j2-mid-v1 Bedrock | In $12.5000 / 1M tokens Out $12.5000 / 1M tokens | text
Output: text | Low overlap | 8.2K | Partial I/O overlap Overall 1% |
| us.writer.palmyra-x4-v1:0 bedrock_converse | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | pdftext
Output: text | Low overlap | 8.2K | Partial I/O overlap Overall 1% |
| ai21.jamba-instruct-v1:0 Bedrock | In $0.5000 / 1M tokens Out $0.7000 / 1M tokens | text
Output: text | Low overlap | 4.1K | Partial I/O overlap Overall 0% |
No models match this filter.