deepseek-v3.1-maas
vertex_ai-deepseek_models · chat model
deepseek-v3.1-maas is listed here as a chat model from vertex_ai-deepseek_models. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$1.3500 / 1M tokens
Output
$5.4000 / 1M tokens
Cached input
N/A
Context
32.8K
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 | $1.3500 / 1M tokens |
| Output | $5.4000 / 1M tokens |
| Embedding | $1.3500 / 1M tokens |
Token limits
Context window
32.8K
Max input tokens
163.8K
Max output tokens
32.8K
Max tokens
32.8K
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 | 88.5 | EM | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| GPQA Diamond | 59.1 | Pass@1 | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| LiveCodeBench | 37.6 | Pass@1 | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| AIME 2024 | 39.2 | Pass@1 | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| MATH-500 | 90.2 | EM | Base model: DeepSeek-V3 (DeepSeek-V3) | 2026-05-31 | Link |
| MMLU-Pro | 84.8 | EM | Base model: DeepSeek-V3.1 (DeepSeek-V3.1-Thinking) | 2026-05-31 | Link |
| GPQA Diamond | 80.1 | pass@1 | Base model: DeepSeek-V3.1 (DeepSeek-V3.1-Thinking) | 2026-05-31 | Link |
| Humanity's Last Exam | 15.9 | pass@1 | Base model: DeepSeek-V3.1 (DeepSeek-V3.1-Thinking) | 2026-05-31 | Link |
| LiveCodeBench | 74.8 | pass@1 | Base model: DeepSeek-V3.1 (DeepSeek-V3.1-Thinking) | 2026-05-31 | Link |
| Aider Polyglot | 76.3 | accuracy | Base model: DeepSeek-V3.1 (DeepSeek-V3.1-Thinking) | 2026-05-31 | Link |
| SWE-bench Verified (Agent mode) | 66.0 | resolved | Base model: DeepSeek-V3.1 (DeepSeek-V3.1-Thinking) | 2026-05-31 | Link |
| AIME 2025 | 88.4 | pass@1 | Base model: DeepSeek-V3.1 (DeepSeek-V3.1-Thinking) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
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 |
|---|---|---|---|---|---|
| deepseek-v3.1-maas vertex_ai-deepseek_models | In $1.3500 / 1M tokens Out $5.4000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 32.8K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| deepseek-r1-0528-maas vertex_ai-deepseek_models | In $1.3500 / 1M tokens Out $5.4000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 8.2K | Same provider Overall 49% |
| deepseek-v3.2-maas vertex_ai-deepseek_models | In $0.5600 / 1M tokens Out $1.6800 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 32.8K | Same provider Overall 47% |
| DeepSeek-V3-0324 sambanova | In $3.0000 / 1M tokens Out $4.5000 / 1M tokens |
Output: unknown | Function callingTool choiceReasoning | 32.8K | Partial I/O overlap Overall 47% |
| DeepSeek-V3.1 sambanova | In $3.0000 / 1M tokens Out $4.5000 / 1M tokens |
Output: unknown | Function callingTool choiceReasoning | 32.8K | Partial I/O overlap Overall 47% |
| magistral-medium-2506 Mistral | In $2.0000 / 1M tokens Out $5.0000 / 1M tokens | text
Output: text | Function callingTool choiceReasoning | 40.0K | Partial I/O overlap Overall 44% |
| magistral-medium-2509 Mistral | In $2.0000 / 1M tokens Out $5.0000 / 1M tokens | text
Output: text | Function callingTool choiceReasoning | 40.0K | Partial I/O overlap Overall 44% |
| glm-5-code zai | In $1.2000 / 1M tokens Out $5.0000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | N/A | Partial I/O overlap Overall 43% |
| glm-5-maas vertex_ai-zai_models | In $1.0000 / 1M tokens Out $3.2000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 128.0K | Partial I/O overlap Overall 42% |
| deepseek-v3-2-251201 volcengine | In N/A Out N/A |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 32.8K | Partial I/O overlap Overall 40% |
| apac.anthropic.claude-haiku-4-5-20251001-v1:0 bedrock_converse | In $1.1000 / 1M tokens Out $5.5000 / 1M tokens | pdf
Output: unknown | Function callingTool choicePrompt cachingReasoning | 64.0K | Partial I/O overlap Overall 38% |
| eu.anthropic.claude-haiku-4-5-20251001-v1:0 bedrock_converse | In $1.1000 / 1M tokens Out $5.5000 / 1M tokens | imagepdf
Output: text | Function callingTool choicePrompt cachingReasoning | 64.0K | Partial I/O overlap Overall 38% |
| glm-5 zai | In $1.0000 / 1M tokens Out $3.2000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | N/A | Partial I/O overlap Overall 38% |
| deepseek-r1 DeepSeek | In $0.5500 / 1M tokens Out $2.1900 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 8.2K | Partial I/O overlap Overall 37% |
| MAI-DS-R1 azure_ai | In $1.3500 / 1M tokens Out $5.4000 / 1M tokens | text
Output: text | Tool choiceReasoning | 8.2K | Partial I/O overlap Overall 36% |
| deepseek-r1 azure_ai | In $1.3500 / 1M tokens Out $5.4000 / 1M tokens | text
Output: text | Tool choiceReasoning | 8.2K | Partial I/O overlap Overall 36% |
| deepseek-v3.2 azure_ai | In $0.5800 / 1M tokens Out $1.6800 / 1M tokens | text
Output: text | Function callingTool choicePrompt cachingReasoning | 163.8K | Partial I/O overlap Overall 35% |
| deepseek-v3.2-speciale azure_ai | In $0.5800 / 1M tokens Out $1.6800 / 1M tokens | text
Output: text | Function callingTool choicePrompt cachingReasoning | 163.8K | Partial I/O overlap Overall 35% |
| glm-4.7 zai | In $0.6000 / 1M tokens Out $2.2000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | N/A | Partial I/O overlap Overall 33% |
| glm-4.6 zai | In $0.6000 / 1M tokens Out $2.2000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | N/A | Partial I/O overlap Overall 33% |
| deepseek-v3.2 DeepSeek | In $0.2800 / 1M tokens Out $0.4000 / 1M tokens |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 163.8K | Partial I/O overlap Overall 31% |
| glm-4-7-251222 volcengine | In N/A Out N/A |
Output: unknown | Function callingTool choicePrompt cachingReasoning | 131.1K | Partial I/O overlap Overall 29% |
| us.deepseek.r1-v1:0 bedrock_converse | In $1.3500 / 1M tokens Out $5.4000 / 1M tokens | text
Output: text | Reasoning | 4.1K | Partial I/O overlap Overall 28% |
No models match this filter.