DeepSeek V4 Flash vs GPT OSS 120B
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Fireworks
3 providers:
DeepSeek $0.140/$0.280
Fireworks $0.140/$0.280
DeepInfra $0.090/$0.180
|
by Fireworks
|
|---|---|---|
| Overview | ||
| Status | Current budget | Current budget Open weights |
| Released | Apr 24, 2026 | Jan 1, 2026 |
| Pricing per million tokens | ||
| Input | $0.140/Mtok | $0.150/Mtok |
| Output | $0.280/Mtok | $0.600/Mtok |
| Blended avg | $0.175/Mtok | $0.262/Mtok |
| Cached input | $0.028/Mtok | $0.015/Mtok |
| Specifications | ||
| Context window | 1M tokens | 128K tokens |
| Parameters | Proprietary | 120B |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: DeepSeek model card / Vellum LLM Leaderboard | ||
| Avg benchmark score | 77.5 | 65.5 |
| Perf / dollar | 442.9 | 249.5 |
| GPQA Diamond | 88.1 | 80.1 |
| LiveCodeBench | 91.6 | 69 |
| Humanity's Last Exam | 51.6 | 14.9 |
| AIME 2025 | 58 vendor | 97.9 |
| SWE-Bench Verified | 79 vendor | — |
| MCP Atlas | 69 | — |
| BrowseComp | 85.9 | — |
| ARC-AGI 2 | 18 vendor | — |
| MMMLU | 75 vendor | — |
| BFCL | 62 vendor | — |
| HumanEval | 79 | — |
| MATH 500 | 68 vendor | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 51.8 | 24.1 |
| AA Agentic Index | 48.4 | 13.4 |
| AA-Omniscience Index (−100–100) | -14.3 | -49.2 |
| GDPval-AA v2 | 1558.4 ELO | — |
| LMSYS Chatbot Arena | — | 1352.5 ELO |
| Providers | ||
| Available from |
DeepSeek — $0.140/$0.280/Mtok
Fireworks — $0.140/$0.280/Mtok
DeepInfra — $0.090/$0.180/Mtok
|
Fireworks — $0.150/$0.600/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | DeepSeek V4 Flash | GPT OSS 120B | Savings |
|---|---|---|---|
| 1M tokens | $0.18 | $0.26 | $0.09 (34.3%) |
| 10M tokens | $1.75 | $2.62 | $0.87 (33.1%) |
| 100M tokens | $17.5 | $26.25 | $8.75 (33.3%) |
| 1000M tokens | $175 | $262.5 | $87.5 (33.3%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.175/Mtok blended vs $0.262 — 33.3% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 128K (7.8×)
- raw capability matters more than price: 77.5 vs 65.5 average benchmark score
- provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.015/Mtok — 90% off its list input price
- you want open weights — self-host it, fine-tune it, or exit the API entirely; DeepSeek V4 Flash is closed
The cheaper option here — DeepSeek V4 Flash costs $0.175/Mtok blended on Fireworks.
Summary
DeepSeek V4 Flash by Fireworks costs $0.140/Mtok input and $0.280/Mtok output, with a 1M-token context window. It supports text input and is available from 3 providers.
GPT OSS 120B by Fireworks costs $0.150/Mtok input and $0.600/Mtok output, with a 128K-token context window. It supports text input.
On a blended cost basis, DeepSeek V4 Flash is 33.3% cheaper than GPT OSS 120B.It also has a larger context window.
On benchmarks, DeepSeek V4 Flash scores higher (77.5 vs 65.5) on average. In terms of value, DeepSeek V4 Flash has better performance per dollar (442.9 vs 249.5).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.