Llama-4-Maverick-17B-128E-Instruct-FP8
azure_ai · chat model
Llama-4-Maverick-17B-128E-Instruct-FP8 is listed here as a chat model from azure_ai. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$1.4100 / 1M tokens
Output
$0.3500 / 1M tokens
Cached input
N/A
Context
16.4K
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 | $1.4100 / 1M tokens |
| Output | $0.3500 / 1M tokens |
| Embedding | $1.4100 / 1M tokens |
Token limits
Context window
16.4K
Max input tokens
1.0M
Max output tokens
16.4K
Max tokens
16.4K
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 |
|---|---|---|---|---|---|
| MMMU | 73.4 | accuracy | Base model: Llama 4 (Llama 4 Maverick) | 2026-05-31 | Link |
| ChartQA | 90.0 | relaxed_accuracy | Base model: Llama 4 (Llama 4 Maverick) | 2026-05-31 | Link |
| DocVQA | 94.4 | anls | Base model: Llama 4 (Llama 4 Maverick) | 2026-05-31 | Link |
| MMLU-Pro | 80.5 | macro_avg/acc | Base model: Llama 4 (Llama 4 Maverick) | 2026-05-31 | Link |
| GPQA Diamond | 69.8 | accuracy | Base model: Llama 4 (Llama 4 Maverick) | 2026-05-31 | Link |
| Artificial Analysis Intelligence Index | 18.4 | score | Base model: llama-4 (meta-llama/llama-4-maverick) | 2026-05-31 | Link |
| Artificial Analysis Coding Index | 15.6 | score | Base model: llama-4 (meta-llama/llama-4-maverick) | 2026-05-31 | Link |
| Artificial Analysis Agentic Index | 7.2 | score | Base model: llama-4 (meta-llama/llama-4-maverick) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
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 |
|---|---|---|---|---|---|
| Llama-4-Maverick-17B-128E-Instruct-FP8 azure_ai | In $1.4100 / 1M tokens Out $0.3500 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 16.4K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| Llama-4-Scout-17B-16E-Instruct azure_ai | In $0.2000 / 1M tokens Out $0.7800 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 16.4K | Same provider Overall 86% |
| llama-4-scout vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 8.2K | Text + image covered Overall 83% |
| llama-3.2-90b vercel_ai_gateway | In $0.7200 / 1M tokens Out $0.7200 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 8.2K | Text + image covered Overall 82% |
| gpt-4o-mini vercel_ai_gateway | In $0.1500 / 1M tokens Out $0.6000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 16.4K | Text + image covered Overall 81% |
| Llama-3.2-11B-Vision-Instruct azure_ai | In $0.3700 / 1M tokens Out $0.3700 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 2.0K | Same provider Overall 80% |
| grok-2-vision vercel_ai_gateway | In $2.0000 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 32.8K | Text + image covered Overall 79% |
| mistral-large-3 azure_ai | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 8.2K | Same provider Overall 78% |
| mistral-small-2503 azure_ai | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 128.0K | Same provider Overall 77% |
| Llama-3.2-90B-Vision-Instruct azure_ai | In $2.0400 / 1M tokens Out $2.0400 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 2.0K | Same provider Overall 75% |
| Qwen2.5-VL-32B-Instruct deepinfra | In $0.2000 / 1M tokens Out $0.6000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 128.0K | Text + image covered Overall 75% |
| Phi-3.5-vision-instruct azure_ai | In $0.1300 / 1M tokens Out $0.5200 / 1M tokens | imagetext
Output: text | VisionTool choice | 4.1K | Same provider Overall 69% |
| Meta-Llama-3-70B-Instruct azure_ai | In $1.1000 / 1M tokens Out $0.3700 / 1M tokens | imagetext
Output: text | Tool choice | 2.0K | Same provider Overall 56% Missing image |
| Llama-3.3-70B-Instruct-Turbo Together AI | In $0.8800 / 1M tokens Out $0.8800 / 1M tokens | imagetext
Output: text | Function callingTool choice | N/A | Partial I/O overlap Overall 48% Missing image |
| Meta-Llama-3.1-70B-Instruct-Turbo Together AI | In $0.8800 / 1M tokens Out $0.8800 / 1M tokens | imagetext
Output: text | Function callingTool choice | N/A | Partial I/O overlap Overall 48% Missing image |
| deepseek-v3 fireworks_ai | In $0.9000 / 1M tokens Out $0.9000 / 1M tokens | imagetext
Output: text | Low overlap | 8.2K | Partial I/O overlap Overall 46% Missing image |
| Mixtral-8x22B-Instruct-v0.1 anyscale | In $0.9000 / 1M tokens Out $0.9000 / 1M tokens | imagetext
Output: unknown | Function calling | 65.5K | Partial I/O overlap Overall 22% Missing text, image |
| Qwen2.5-Coder-32B-Instruct ovhcloud | In $0.8700 / 1M tokens Out $0.8700 / 1M tokens | imagetext
Output: unknown | Low overlap | 32.0K | Partial I/O overlap Overall 18% Missing text, image |
No models match this filter.