gemma-3-27b-it
Google · chat model
gemma-3-27b-it is listed here as a chat model from Google. 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
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 |
|---|
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-3-27b-it Google | In N/A Out N/A |
Output: unknown | VisionFunction callingTool choiceResponse schema | 8.2K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| gemini-2.0-flash-lite vercel_ai_gateway | In $0.0750 / 1M tokens Out $0.3000 / 1M tokens | audioimage
Output: text | VisionFunction callingTool choiceResponse schema | 8.2K | Partial I/O overlap Overall 40% |
| llama-4-scout-17b-16e-instruct Groq | In $0.1100 / 1M tokens Out $0.3400 / 1M tokens |
Output: unknown | VisionFunction callingTool choiceResponse schema | 8.2K | Partial I/O overlap Overall 40% |
| gemini-2.0-flash vercel_ai_gateway | In $0.1500 / 1M tokens Out $0.6000 / 1M tokens | audioimage
Output: audio, image, text | VisionFunction callingTool choiceResponse schema | 8.2K | Partial I/O overlap Overall 40% |
| llama-4-maverick-17b-128e-instruct Groq | In $0.2000 / 1M tokens Out $0.6000 / 1M tokens |
Output: unknown | VisionFunction callingTool choiceResponse schema | 8.2K | Partial I/O overlap Overall 40% |
| claude-3.5-haiku vercel_ai_gateway | In $0.8000 / 1M tokens Out $4.0000 / 1M tokens | fileimage
Output: text | VisionFunction callingTool choiceResponse schema | 8.2K | Partial I/O overlap Overall 40% |
| claude-3.5-sonnet vercel_ai_gateway | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | fileimage
Output: text | VisionFunction callingTool choiceResponse schema | 8.2K | Partial I/O overlap Overall 40% |
| gemini-exp-1114 Google | In N/A Out N/A |
Output: unknown | VisionFunction callingTool choiceResponse schema | 8.2K | Same provider Overall 35% |
| gemini-exp-1206 Google | In N/A Out N/A |
Output: unknown | VisionFunction callingTool choiceResponse schema | 8.2K | Same provider Overall 35% |
| learnlm-1.5-pro-experimental Google | In N/A Out N/A |
Output: unknown | VisionFunction callingTool choiceResponse schema | 8.2K | Same provider Overall 35% |
| gemini-gemma-2-27b-it Google | In $0.3500 / 1M tokens Out $1.0500 / 1M tokens |
Output: unknown | VisionFunction callingTool choice | 8.2K | Same provider Overall 34% |
| gemini-gemma-2-9b-it Google | In $0.3500 / 1M tokens Out $1.0500 / 1M tokens |
Output: unknown | VisionFunction callingTool choice | 8.2K | Same provider Overall 34% |
| anthropic.claude-3-5-sonnet-20240620-v1:0 Bedrock | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choiceResponse schema | 4.1K | Partial I/O overlap Overall 33% |
| anthropic.claude-3-opus-20240229-v1:0 Bedrock | In $15.0000 / 1M tokens Out $75.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choiceResponse schema | 4.1K | Partial I/O overlap Overall 33% |
| eu.anthropic.claude-3-opus-20240229-v1:0 Bedrock | In $15.0000 / 1M tokens Out $75.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choiceResponse schema | 4.1K | Partial I/O overlap Overall 33% |
| gemini-2.0-flash-001 Google | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | audioimage
Output: text | VisionFunction callingTool choiceResponse schema | 8.2K | Same provider Overall 29% |
| Mistral Large Mistral | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choiceResponse schema | 262.1K | Partial I/O overlap Overall 25% |
| Llama-3.2-3B-Instruct deepinfra | In $0.0200 / 1M tokens Out $0.0200 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Partial I/O overlap Overall 13% |
| llama3.2-11b-vision-instruct lambda_ai | In $0.0150 / 1M tokens Out $0.0250 / 1M tokens |
Output: unknown | VisionFunction callingTool choice | 131.1K | Partial I/O overlap Overall 13% |
| paddleocr-vl novita | In $0.0200 / 1M tokens Out $0.0200 / 1M tokens | imagetext
Output: text | Vision | 16.4K | Partial I/O overlap Overall 13% |
| llama3.2-3b-instruct lambda_ai | In $0.0150 / 1M tokens Out $0.0250 / 1M tokens |
Output: unknown | Function callingTool choice | 131.1K | Partial I/O overlap Overall 9% |
| 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.