llama-3.2-3b-instruct
novita · chat model
llama-3.2-3b-instruct is listed here as a chat model from novita. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.0300 / 1M tokens
Output
$0.0500 / 1M tokens
Cached input
N/A
Context
32.0K
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 | $0.0300 / 1M tokens |
| Output | $0.0500 / 1M tokens |
| Embedding | $0.0300 / 1M tokens |
Token limits
Context window
32.0K
Max input tokens
32.8K
Max output tokens
32.0K
Max tokens
32.0K
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 | 32.2 | macro_avg/acc_char | Base model: Llama 3.2 (Llama 3.2 1B) | 2026-05-31 | Link |
| ARC-Challenge | 32.8 | acc_char | Base model: Llama 3.2 (Llama 3.2 1B) | 2026-05-31 | Link |
| SQuAD | 49.2 | em | Base model: Llama 3.2 (Llama 3.2 1B) | 2026-05-31 | Link |
| MMLU | 58 | macro_avg/acc_char | Base model: Llama 3.2 (Llama 3.2 3B) | 2026-05-31 | Link |
| ARC-Challenge | 69.1 | acc_char | Base model: Llama 3.2 (Llama 3.2 3B) | 2026-05-31 | Link |
| SQuAD | 67.7 | em | Base model: Llama 3.2 (Llama 3.2 3B) | 2026-05-31 | Link |
| MMLU | 49.3 | macro_avg/acc | Base model: Llama 3.2 (Llama 3.2 1B bf16) | 2026-05-31 | Link |
| IFEval | 59.5 | Avg(Prompt/Instruction acc Loose/Strict) | Base model: Llama 3.2 (Llama 3.2 1B bf16) | 2026-05-31 | Link |
| MMLU | 63.4 | macro_avg/acc | Base model: Llama 3.2 (Llama 3.2 3B bf16) | 2026-05-31 | Link |
| IFEval | 77.4 | Avg(Prompt/Instruction acc Loose/Strict) | Base model: Llama 3.2 (Llama 3.2 3B bf16) | 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-3.2-3b-instruct novita | In $0.0300 / 1M tokens Out $0.0500 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 32.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| L3-8B-Stheno-v3.2 novita | In $0.0500 / 1M tokens Out $0.0500 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 32.0K | Same provider Overall 96% |
| qwen2.5-7b-instruct novita | In $0.0700 / 1M tokens Out $0.0700 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 32.0K | Same provider Overall 87% |
| qwen3-coder-30b-a3b-instruct novita | In $0.0700 / 1M tokens Out $0.2700 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 32.8K | Same provider Overall 81% |
| Mistral-Small-24B-Instruct-2501 deepinfra | In $0.0500 / 1M tokens Out $0.0800 / 1M tokens | text
Output: text | Function callingTool choice | 32.8K | Text covered Overall 79% |
| gpt-oss-20b OpenRouter | In $0.0200 / 1M tokens Out $0.1000 / 1M tokens | text
Output: text | Function callingParallel function callingTool choice | 32.8K | Text covered Overall 79% |
| qwen3-next-80b-a3b-instruct novita | In $0.1500 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 32.8K | Same provider Overall 77% |
| mimo-v2-flash novita | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 32.0K | Same provider Overall 76% |
| Meta-Llama-3.1-8B-Instruct deepinfra | In $0.0300 / 1M tokens Out $0.0500 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Text covered Overall 76% |
| qwen3-235b-a22b-thinking-2507 novita | In $0.3000 / 1M tokens Out $3.0000 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 32.8K | Same provider Overall 76% |
| ernie-4.5-21B-a3b novita | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 8.0K | Same provider Overall 75% |
| Meta-Llama-3-8B-Instruct deepinfra | In $0.0300 / 1M tokens Out $0.0600 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Text covered Overall 75% |
| deepseek-v3-turbo novita | In $0.4000 / 1M tokens Out $1.3000 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 16.0K | Same provider Overall 74% |
| llama-3.3-70b-instruct novita | In $0.1350 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 120.0K | Same provider Overall 72% |
| llama-3.1-8b-instruct novita | In $0.0200 / 1M tokens Out $0.0500 / 1M tokens | text
Output: text | System messages | 16.4K | Same provider Overall 71% |
| l3-70b-euryale-v2.1 novita | In $1.4800 / 1M tokens Out $1.4800 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 8.2K | Same provider Overall 69% |
| l31-70b-euryale-v2.2 novita | In $1.4800 / 1M tokens Out $1.4800 / 1M tokens | text
Output: text | Function callingParallel function callingTool choiceSystem messages | 8.2K | Same provider Overall 69% |
| L3-8B-Lunaris-v1-Turbo deepinfra | In $0.0400 / 1M tokens Out $0.0500 / 1M tokens | text
Output: text | Low overlap | 8.2K | Text covered Overall 62% |
| hermes3-8b lambda_ai | In $0.0250 / 1M tokens Out $0.0400 / 1M tokens | text
Output: unknown | Function callingParallel function callingTool choiceSystem messages | 131.1K | Partial I/O overlap Overall 45% Missing text |
| llama-3.1-8b llamagate | In $0.0300 / 1M tokens Out $0.0500 / 1M tokens | text
Output: unknown | Function calling | 8.2K | Partial I/O overlap Overall 29% Missing text |
No models match this filter.