# DeepSeek V4 Flash vs GPT OSS 120B

As of October 21, 2026, DeepSeek V4 Flash costs 900% more per input token than GPT OSS 120B ($0.30 vs $0.03 per 1M) and has a 1M-token context window versus 131K.

- Page: https://models.litellm.ai/compare/deepseek-v4-flash-vs-gpt-oss-120b
- DeepSeek V4 Flash: https://models.litellm.ai/models/deepseek-v4-flash
- GPT OSS 120B: https://models.litellm.ai/models/gpt-oss-120b

## Side by side

| | DeepSeek V4 Flash | GPT OSS 120B |
|---|---|---|
| Input, per 1M tokens | $0.30 | $0.03 |
| Output, per 1M tokens | $1.20 | $0.17 |
| Cache read, per 1M tokens | $0.006 | – |
| Cache write, per 1M tokens | $0 | – |
| Context window | 1,000,000 tokens | 131,000 tokens |
| Max output | 393,216 tokens | 131,072 tokens |
| Image input | Yes | – |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 23 | 24 |
| Price shown is from | DeepSeek | Weights & Biases |
| Added to LiteLLM | June 2026 | August 2025 |

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`)
- GPT OSS 120B: Weights & Biases at $0.03 input per 1M tokens (`wandb/openai/gpt-oss-120b`)

## When to pick which

- DeepSeek V4 Flash: Larger context window: 1,000,000 vs 131,000 tokens.
- DeepSeek V4 Flash: Returns up to 393,216 tokens per response, vs 131,072.
- GPT OSS 120B: Costs 90% less per input token: $0.03 vs $0.30 per 1M.

## FAQ

### Which is cheaper, DeepSeek V4 Flash or GPT OSS 120B?

GPT OSS 120B is cheaper at 3 input tokens per output token: $0.065 per 1M tokens blended ($0.03 input, $0.17 output), versus $0.525 ($0.30 and $1.20) for DeepSeek V4 Flash, as of October 21, 2026.

### Which has the larger context window, DeepSeek V4 Flash or GPT OSS 120B?

DeepSeek V4 Flash has the larger context window: 1,000,000 tokens, versus 131,000 for GPT OSS 120B.

### Can I switch from DeepSeek V4 Flash to GPT OSS 120B without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "deepseek-v4-flash" to "wandb/openai/gpt-oss-120b", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.