llama-3.1-70b-instruct-maas
vertex_ai-llama_models · chat model
llama-3.1-70b-instruct-maas is listed here as a chat model from vertex_ai-llama_models. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
N/A
Output
N/A
Cached input
N/A
Context
2.0K
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 |
|---|
Token limits
Context window
2.0K
Max input tokens
128.0K
Max output tokens
2.0K
Max tokens
2.0K
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 (CoT) | 88.6 | macro_avg/acc | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| MMLU-Pro (CoT) | 73.3 | macro_avg/acc | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| GPQA Diamond | 49.0 | acc | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| HumanEval | 89.0 | pass@1 | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| MATH (CoT) | 73.8 | sympy_intersection_score | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| MMLU | 85.2 | macro_avg/acc_char | Base model: Llama 3.1 (Llama 3.1 405B) | 2026-05-31 | Link |
| MMLU-Pro (CoT) | 61.6 | macro_avg/acc_char | Base model: Llama 3.1 (Llama 3.1 405B) | 2026-05-31 | Link |
| AGIEval English | 71.6 | average/acc_char | Base model: Llama 3.1 (Llama 3.1 405B) | 2026-05-31 | Link |
| MMLU | 87.3 | macro_avg/acc | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| MMLU (CoT) | 88.6 | macro_avg/acc | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| MMLU-Pro (CoT) | 73.3 | micro_avg/acc_char | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| IFEval | 88.6 | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link | |
| ARC-Challenge | 96.9 | acc | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| GPQA | 50.7 | em | Base model: Llama 3.1 (Llama 3.1 405B Instruct) | 2026-05-31 | Link |
| MMLU | 69.4% | macro_avg/acc | Base model: Llama 3.1 (Llama-3.1-8B-Instruct) | 2026-05-31 | Link |
| MMLU | 83.6% | macro_avg/acc | Base model: Llama 3.1 (Llama-3.1-70B-Instruct) | 2026-05-31 | Link |
| HumanEval | 72.6% | pass@1 | Base model: Llama 3.1 (Llama-3.1-8B-Instruct) | 2026-05-31 | Link |
| HumanEval | 80.5% | pass@1 | Base model: Llama 3.1 (Llama-3.1-70B-Instruct) | 2026-05-31 | Link |
| GSM8K (CoT) | 84.5% | em_maj1@1 | Base model: Llama 3.1 (Llama-3.1-8B-Instruct) | 2026-05-31 | Link |
| GSM8K (CoT) | 95.1% | em_maj1@1 | Base model: Llama 3.1 (Llama-3.1-70B-Instruct) | 2026-05-31 | Link |
| BFCL | 76.1% | acc | Base model: Llama 3.1 (Llama-3.1-8B-Instruct) | 2026-05-31 | Link |
| BFCL | 84.8% | acc | Base model: Llama 3.1 (Llama-3.1-70B-Instruct) | 2026-05-31 | Link |
| Artificial Analysis Intelligence Index | 12.2 | score | Base model: llama-3.1 (meta-llama/llama-3.1-70b-instruct) | 2026-05-31 | Link |
| Artificial Analysis Coding Index | 10.9 | score | Base model: llama-3.1 (meta-llama/llama-3.1-70b-instruct) | 2026-05-31 | Link |
| Artificial Analysis Agentic Index | 5.1 | score | Base model: llama-3.1 (meta-llama/llama-3.1-70b-instruct) | 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-3.1-70b-instruct-maas vertex_ai-llama_models | In N/A Out N/A |
Output: unknown | VisionTool choiceSystem messages | 2.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| llama-3.1-8b-instruct-maas vertex_ai-llama_models | In N/A Out N/A |
Output: unknown | VisionTool choiceSystem messages | 2.0K | Same provider Overall 40% |
| llama-3.2-90b-vision-instruct-maas vertex_ai-llama_models | In N/A Out N/A |
Output: unknown | VisionTool choiceSystem messages | 2.0K | Same provider Overall 40% |
| llama-3.1-405b-instruct-maas vertex_ai-llama_models | In $5.0000 / 1M tokens Out $16.0000 / 1M tokens |
Output: unknown | VisionTool choiceSystem messages | 2.0K | Same provider Overall 40% |
| qwen-vl-plus OpenRouter | In $0.2100 / 1M tokens Out $0.6300 / 1M tokens |
Output: unknown | VisionTool choice | 2.0K | Partial I/O overlap Overall 32% |
| Llama-3.2-11B-Vision-Instruct azure_ai | In $0.3700 / 1M tokens Out $0.3700 / 1M tokens | imagetext
Output: text | VisionTool choice | 2.0K | Partial I/O overlap Overall 28% |
| Llama-3.2-90B-Vision-Instruct azure_ai | In $2.0400 / 1M tokens Out $2.0400 / 1M tokens | imagetext
Output: text | VisionTool choice | 2.0K | Partial I/O overlap Overall 28% |
| moonshotai.kimi-k2.5 Bedrock | In $0.7200 / 1M tokens Out $3.6000 / 1M tokens | imagetext
Output: text | VisionTool choiceSystem messages | 262.1K | Partial I/O overlap Overall 19% |
| moonshotai.kimi-k2.5 Bedrock | In $0.7200 / 1M tokens Out $3.6000 / 1M tokens | imagetext
Output: text | VisionTool choiceSystem messages | 262.1K | Partial I/O overlap Overall 19% |
| moonshotai.kimi-k2.5 Bedrock | In $0.7200 / 1M tokens Out $3.6000 / 1M tokens | imagetext
Output: text | VisionTool choiceSystem messages | 262.1K | Partial I/O overlap Overall 19% |
| paddleocr-vl novita | In $0.0200 / 1M tokens Out $0.0200 / 1M tokens | imagetext
Output: text | VisionSystem messages | 16.4K | Partial I/O overlap Overall 19% |
| llama3.2-11b-vision-instruct lambda_ai | In $0.0150 / 1M tokens Out $0.0250 / 1M tokens |
Output: unknown | VisionTool choiceSystem messages | 131.1K | Partial I/O overlap Overall 15% |
| llama3.2-3b-instruct lambda_ai | In $0.0150 / 1M tokens Out $0.0250 / 1M tokens |
Output: unknown | Tool choiceSystem messages | 131.1K | Partial I/O overlap Overall 10% |
| llama3-405b-instruct-maas vertex_ai-llama_models | In N/A Out N/A |
Output: unknown | Tool choice | 32.0K | Same provider Overall 9% |
| llama3-70b-instruct-maas vertex_ai-llama_models | In N/A Out N/A |
Output: unknown | Tool choice | 32.0K | Same provider Overall 9% |
| llama3-8b-instruct-maas vertex_ai-llama_models | In N/A Out N/A |
Output: unknown | Tool choice | 32.0K | Same provider Overall 9% |
| Llama-3.2-3B-Instruct deepinfra | In $0.0200 / 1M tokens Out $0.0200 / 1M tokens | text
Output: text | Tool choice | 131.1K | Partial I/O overlap Overall 6% |
| titan-embed-text-v2 vercel_ai_gateway | In $0.0200 / 1M tokens Out N/A | text
Output: embedding | Low overlap | 0 | Partial I/O overlap Overall 0% |
| Qwen2.5-Coder-3B-Instruct nscale | In $0.0100 / 1M tokens Out $0.0300 / 1M tokens |
Output: unknown | Low overlap | N/A | Partial I/O overlap Overall 0% |
No models match this filter.