gemma-3-12b-it
novita · chat model
gemma-3-12b-it 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
$0.0500 / 1M tokens
Output
$0.1000 / 1M tokens
Cached input
N/A
Context
8.2K
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 | $0.0500 / 1M tokens |
| Output | $0.1000 / 1M tokens |
| Embedding | $0.0500 / 1M tokens |
Token limits
Context window
8.2K
Max input tokens
131.1K
Max output tokens
8.2K
Max tokens
8.2K
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 | 78.6 | 5-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| MMLU-Pro (CoT) | 52.2 | 5-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| GPQA | 24.3 | 5-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| HumanEval | 48.8 | 0-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| MATH | 50.0 | 4-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| MMLU | 78.6 | 5-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| GSM8K | 82.6 | 8-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| HumanEval | 48.8 | 0-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| MGSM | 74.3 | 0-shot | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| DocVQA | 85.6 | val | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| MMMU | 56.1 | pt | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| DocVQA | 85.6 | score | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| InfoVQA | 59.4 | score | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| MMMU | 56.1 | score | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| TextVQA | 68.6 | score | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| AI2D | 79.0 | score | Base model: Gemma 3 (Gemma 3 PT 27B) | 2026-05-31 | Link |
| ChartQA | 76.3 | score | Base model: Gemma 3 (Gemma 3 PT 27B) | 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 |
|---|---|---|---|---|---|
| gemma-3-12b-it novita | In $0.0500 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | 8.2K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| deepseek-ocr novita | In $0.0300 / 1M tokens Out $0.0300 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | 8.2K | Same provider Overall 89% |
| gpt-oss-20b novita | In $0.0400 / 1M tokens Out $0.1500 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | 32.8K | Same provider Overall 78% |
| l3-8b-lunaris novita | In $0.0500 / 1M tokens Out $0.0500 / 1M tokens | imagetext
Output: text | Tool choiceResponse schemaSystem messages | 8.2K | Same provider Overall 76% Missing image |
| google.gemma-3-4b-it bedrock_converse | In $0.0400 / 1M tokens Out $0.0800 / 1M tokens | imagetext
Output: image, text | VisionSystem messages | 8.2K | Text + image covered Overall 76% |
| mistral.ministral-3-3b-instruct bedrock_converse | In $0.1000 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: text | System messages | 8.2K | Text + image covered Overall 76% |
| llama-3.2-11b vercel_ai_gateway | In $0.1600 / 1M tokens Out $0.1600 / 1M tokens | imagetext
Output: text | VisionTool choice | 8.2K | Text + image covered Overall 75% |
| hermes-2-pro-llama-3-8b novita | In $0.1400 / 1M tokens Out $0.1400 / 1M tokens | imagetext
Output: text | Tool choiceResponse schemaSystem messages | 8.2K | Same provider Overall 73% Missing image |
| gpt-oss-120b novita | In $0.0500 / 1M tokens Out $0.2500 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | 32.8K | Same provider Overall 71% |
| ernie-4.5-vl-28b-a3b novita | In $0.1400 / 1M tokens Out $0.5600 / 1M tokens | imagetext
Output: text | VisionTool choiceSystem messages | 8.0K | Same provider Overall 71% |
| gemma-3-12b-it deepinfra | In $0.0500 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: text | Tool choice | 131.1K | Text + image covered Overall 66% |
| gemini-2.0-flash-001 OpenRouter | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | imagetext audiofile
Output: text | VisionTool choiceResponse schemaSystem messages | 8.2K | Text + image covered Overall 65% |
| gpt-4o-mini replicate | In $0.1500 / 1M tokens Out $0.6000 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | N/A | Text + image covered Overall 62% |
| qwen3-vl-8b-instruct novita | In $0.0800 / 1M tokens Out $0.5000 / 1M tokens | imagetext video
Output: text | VisionTool choiceResponse schemaSystem messages | 32.8K | Same provider Overall 60% |
| gpt-4.1-mini replicate | In $0.4000 / 1M tokens Out $1.6000 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | N/A | Text + image covered Overall 58% |
| gpt-5 replicate | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | N/A | Text + image covered Overall 57% |
| gpt-4.1 replicate | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext
Output: text | VisionTool choiceResponse schemaSystem messages | N/A | Text + image covered Overall 57% |
| qwen3-vl-30b-a3b-instruct novita | In $0.2000 / 1M tokens Out $0.7000 / 1M tokens | imagetext video
Output: text | VisionTool choiceResponse schemaSystem messages | 32.8K | Same provider Overall 56% |
| Qwen2.5-7B-Instruct deepinfra | In $0.0400 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: text | Low overlap | 32.8K | Partial I/O overlap Overall 50% Missing image |
| llama-4-maverick-17b-128e-instruct-fp8 lambda_ai | In $0.0500 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: unknown | Tool choiceSystem messages | 8.2K | Partial I/O overlap Overall 43% Missing text, image |
| llama-4-scout-17b-16e-instruct lambda_ai | In $0.0500 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: unknown | Tool choiceSystem messages | 8.2K | Partial I/O overlap Overall 43% Missing text, image |
| qwen25-coder-32b-instruct lambda_ai | In $0.0500 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: unknown | Tool choiceSystem messages | 131.1K | Partial I/O overlap Overall 29% Missing text, image |
| qwen3-32b-fp8 lambda_ai | In $0.0500 / 1M tokens Out $0.1000 / 1M tokens | imagetext
Output: unknown | Tool choiceSystem messages | 131.1K | Partial I/O overlap Overall 28% Missing text, image |
No models match this filter.