# DeepSeek V4 Flash vs MiniMax M3

As of October 21, 2026, DeepSeek V4 Flash and MiniMax M3 cost the same: $0.30 per 1M input tokens and $1.20 per 1M output tokens, and both have a 1M-token context window.

- Page: https://models.litellm.ai/compare/deepseek-v4-flash-vs-minimax-m3
- DeepSeek V4 Flash: https://models.litellm.ai/models/deepseek-v4-flash
- MiniMax M3: https://models.litellm.ai/models/minimax-m3

## Side by side

| | DeepSeek V4 Flash | MiniMax M3 |
|---|---|---|
| Input, per 1M tokens | $0.30 | $0.30 |
| Output, per 1M tokens | $1.20 | $1.20 |
| Cache read, per 1M tokens | $0.006 | $0.06 |
| Cache write, per 1M tokens | $0 | – |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 393,216 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 23 | 10 |
| Price shown is from | DeepSeek | MiniMax |
| Added to LiteLLM | June 2026 | June 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- DeepSeek V4 Flash: DeepInfra at $0.08 input per 1M tokens (`deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731`)
- MiniMax M3: Weights & Biases at $0.23 input per 1M tokens (`wandb/MiniMaxAI/MiniMax-M3`)

## Benchmark scores

| Benchmark | DeepSeek V4 Flash | MiniMax M3 |
|---|---|---|
| FrontierCode (Coding and agents) | 18.8% | 14.7% |
| GPQA Diamond (Reasoning and knowledge) | 91.0% (max) | 90.9% |
| OTIS Mock AIME 2024-2025 (Math) | 94.4% (max) | 71.1% |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of August 27, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- DeepSeek V4 Flash: Returns up to 393,216 tokens per response, vs 128,000.
- DeepSeek V4 Flash: Available from 23 providers through LiteLLM, vs 10.

## FAQ

### Which is cheaper, DeepSeek V4 Flash or MiniMax M3?

They cost the same: $0.30 per 1M input tokens and $1.20 per 1M output tokens, as of October 21, 2026.

### Which has the larger context window, DeepSeek V4 Flash or MiniMax M3?

Both have a 1,000,000-token context window.

### Can I switch from DeepSeek V4 Flash to MiniMax M3 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "deepseek-v4-flash" to "minimax/MiniMax-M3", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.