gemma-2-9b
vercel_ai_gateway · chat model
gemma-2-9b is listed here as a chat model from vercel_ai_gateway. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.2000 / 1M tokens
Output
$0.2000 / 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 | $0.2000 / 1M tokens |
| Output | $0.2000 / 1M tokens |
| Embedding | $0.2000 / 1M tokens |
Token limits
Context window
8.2K
Max input tokens
8.2K
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 | 75.2 | 5-shot, top-1 | Base model: Gemma 2 (Gemma 2 PT 27B) | 2026-05-31 | Link |
| HellaSwag | 86.4 | 10-shot | Base model: Gemma 2 (Gemma 2 PT 27B) | 2026-05-31 | Link |
| HumanEval | 51.8 | pass@1 | Base model: Gemma 2 (Gemma 2 PT 27B) | 2026-05-31 | Link |
| GSM8K | 74.0 | 5-shot, maj@1 | Base model: Gemma 2 (Gemma 2 PT 27B) | 2026-05-31 | Link |
| MTEB 56-task summary | 64.23 | Average | Base model: bge (BAAI/bge-large-en-v1.5) | 2026-05-31 | Link |
| MTEB 56-task summary | 63.55 | Average | Base model: bge (BAAI/bge-base-en-v1.5) | 2026-05-31 | Link |
| MTEB 56-task summary | 62.17 | Average | Base model: bge (BAAI/bge-small-en-v1.5) | 2026-05-31 | Link |
| MTEB 56-task summary | 63.98 | Average | Base model: bge (bge-large-en) | 2026-05-31 | Link |
| mGTE retrieval table | 64.3 | Avg | Base model: bge (BGE-M3 Dense) | 2026-05-31 | Link |
| mGTE retrieval table | 55.1 | Avg | Base model: bge (BGE-M3 Sparse) | 2026-05-31 | Link |
| mGTE retrieval table | 67.7 | Avg | Base model: bge (BGE-M3 Dense + Sparse) | 2026-05-31 | Link |
| MMLU | 75.2 | 5-shot, top-1 | Base model: Gemma 2 (Gemma PT 27B) | 2026-05-31 | Link |
| HellaSwag | 86.4 | 10-shot | Base model: Gemma 2 (Gemma PT 27B) | 2026-05-31 | Link |
| ARC-Challenge | 71.4 | 25-shot | Base model: Gemma 2 (Gemma PT 27B) | 2026-05-31 | Link |
| TriviaQA | 83.7 | 5-shot | Base model: Gemma 2 (Gemma PT 27B) | 2026-05-31 | Link |
| RealToxicity | 8.84 | average | Base model: Gemma 2 (Gemma 2 IT 27B) | 2026-05-31 | Link |
| TruthfulQA | 51.60 | score | Base model: Gemma 2 (Gemma 2 IT 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-2-9b vercel_ai_gateway | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text
Output: text | VisionFunction callingTool choice | 8.2K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| llama-3.2-11b vercel_ai_gateway | In $0.1600 / 1M tokens Out $0.1600 / 1M tokens | text image
Output: text | VisionFunction callingTool choice | 8.2K | Same provider Overall 84% |
| ministral-8b vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.1000 / 1M tokens | text
Output: text | VisionFunction callingTool choice | 4.0K | Same provider Overall 82% |
| mistral.mistral-7b-instruct-v0:2 Bedrock | In $0.1500 / 1M tokens Out $0.2000 / 1M tokens | text
Output: text | Tool choice | 8.2K | Text covered Overall 81% |
| mistral.mistral-7b-instruct-v0:2 Bedrock | In $0.1500 / 1M tokens Out $0.2000 / 1M tokens | text
Output: text | Tool choice | 8.2K | Text covered Overall 81% |
| mistral.mistral-7b-instruct-v0:2 Bedrock | In $0.1500 / 1M tokens Out $0.2000 / 1M tokens | text
Output: text | Tool choice | 8.2K | Text covered Overall 81% |
| mistral.mistral-7b-instruct-v0:2 Bedrock | In $0.2000 / 1M tokens Out $0.2600 / 1M tokens | text
Output: text | Tool choice | 8.2K | Text covered Overall 81% |
| llama-4-scout vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text image
Output: text | VisionFunction callingTool choice | 8.2K | Same provider Overall 80% |
| llama-3.3-70b vercel_ai_gateway | In $0.7200 / 1M tokens Out $0.7200 / 1M tokens | text
Output: text | Function callingTool choice | 8.2K | Same provider Overall 77% |
| llama-3.2-3b vercel_ai_gateway | In $0.1500 / 1M tokens Out $0.1500 / 1M tokens | text
Output: text | Function calling | 8.2K | Same provider Overall 76% |
| qwen-3-32b vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choice | 16.4K | Same provider Overall 76% |
| ministral-14b-2512 OpenRouter | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text image
Output: text | VisionFunction callingTool choice | 262.1K | Text covered Overall 73% |
| glm-4.7-flash OpenRouter | In $0.0700 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | VisionFunction callingTool choice | 32.0K | Text covered Overall 71% |
| gpt-3.5-turbo Azure | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Text covered Overall 69% |
| gpt-35-turbo Azure | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Text covered Overall 69% |
| minimax-m2.1 OpenRouter | In $0.2700 / 1M tokens Out $1.2000 / 1M tokens | text
Output: text | VisionFunction callingTool choice | 64.0K | Text covered Overall 69% |
| ministral-8b-2512 OpenRouter | In $0.1500 / 1M tokens Out $0.1500 / 1M tokens | text image
Output: text | VisionFunction callingTool choice | 262.1K | Text covered Overall 68% |
| glm-4.7 OpenRouter | In $0.4000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | VisionFunction callingTool choice | 64.0K | Text covered Overall 67% |
| Qwen2.5-VL-32B-Instruct deepinfra | In $0.2000 / 1M tokens Out $0.6000 / 1M tokens | text image
Output: text | VisionFunction callingTool choice | 128.0K | Text covered Overall 67% |
| mistral-small-2503 azure_ai | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text image
Output: text | VisionFunction callingTool choice | 128.0K | Text covered Overall 66% |
| llama-v3p2-11b-vision-instruct fireworks_ai | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text image
Output: text | Vision | 16.4K | Text covered Overall 62% |
| llama-guard-4-12b Groq | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text
Output: unknown | Low overlap | 8.2K | Partial I/O overlap Overall 35% Missing text |
| DeepSeek-V3 hyperbolic | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text
Output: unknown | Function callingTool choice | 32.8K | Partial I/O overlap Overall 34% Missing text |
| QwQ-32B hyperbolic | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text
Output: unknown | Function callingTool choice | 131.1K | Partial I/O overlap Overall 31% Missing text |
| Llama-3.3-70B-Instruct crusoe | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text
Output: unknown | Function callingTool choice | 131.1K | Partial I/O overlap Overall 31% Missing text |
| llama3-8b-instruct gradient_ai | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text
Output: unknown | Low overlap | 512 | Partial I/O overlap Overall 21% Missing text |
No models match this filter.