ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

GPT OSS 20B vs DeepSeek V4 Flash

Side-by-side comparison of API pricing, specs, benchmarks, and capabilities

GPT OSS 20B is 27.1% cheaper on blended cost ($0.128 vs $0.175/Mtok)
Specification
3 providers: DeepSeek $0.140/$0.280 Fireworks $0.140/$0.280 DeepInfra $0.090/$0.180
Overview
StatusCurrent budget Open weights Current budget
Released Jan 1, 2026 Apr 24, 2026
Pricing per million tokens
Input $0.070/Mtok $0.140/Mtok
Output $0.300/Mtok $0.280/Mtok
Blended avg $0.128/Mtok $0.175/Mtok
Cached input $0.035/Mtok $0.028/Mtok
Specifications
Context window 128K tokens 1M tokens
Parameters 20B Proprietary
Speed (TPS)
Modalities
Input
text
text
Benchmarks sources: Vellum LLM Leaderboard / DeepSeek model card
Avg benchmark score 62.5 82.2
Perf / dollar 490.2 469.7
GPQA Diamond 71.5 55 vendor
LiveCodeBench 69 91.6
Humanity's Last Exam 10.9 15 vendor
AIME 2025 98.7 58 vendor
SWE-Bench Verified 79 vendor
MCP Atlas 69
BrowseComp 85.9
ARC-AGI 2 18 vendor
MMMLU 75 vendor
BFCL 62 vendor
HumanEval 80 vendor
MATH 500 68 vendor
Independent composite scores each on its own scale — not part of the average above
AA Intelligence Index 15.2 40.3
AA Agentic Index 3.1 31.1
AA-Omniscience Index (−100–100) -63 -22.9
GDPval-AA v2 1188.8 ELO
Providers
Available from
Fireworks — $0.070/$0.300/Mtok
DeepSeek — $0.140/$0.280/Mtok
Fireworks — $0.140/$0.280/Mtok
DeepInfra — $0.090/$0.180/Mtok

Cost at scale

1M tokens · 50/50 input/output
Projected cost of GPT OSS 20B vs DeepSeek V4 Flash at increasing token volumes
VolumeGPT OSS 20BDeepSeek V4 FlashSavings
1M tokens $0.13 $0.18 $0.05 (28.6%)
10M tokens $1.27 $1.75 $0.48 (27.4%)
100M tokens $12.75 $17.5 $4.75 (27.1%)
1000M tokens $127.5 $175 $47.5 (27.1%)

When to pick which

distilled from the pricing and spec data above
Pick GPT OSS 20B if…
  • cost dominates: $0.128/Mtok blended vs $0.175 — 27.1% less on the same 50/50 token mix
  • you want open weights — self-host it, fine-tune it, or exit the API entirely; DeepSeek V4 Flash is closed
Pick DeepSeek V4 Flash if…
  • your workload re-reads context (agents, RAG, long chats): cached input costs $0.028/Mtok — 80% off its list input price
  • you need the longer context: 1M tokens vs 128K (7.8×)
  • raw capability matters more than price: 82.2 vs 62.5 average benchmark score
  • provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
Try GPT OSS 20B on Fireworks

The cheaper option here — GPT OSS 20B costs $0.128/Mtok blended on Fireworks.

Get API key →

Summary

GPT OSS 20B by Fireworks costs $0.070/Mtok input and $0.300/Mtok output, with a 128K-token context window. It supports text input.

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.

On a blended cost basis, GPT OSS 20B is 27.1% cheaper than DeepSeek V4 Flash.

On benchmarks, DeepSeek V4 Flash scores higher (82.2 vs 62.5) on average. In terms of value, GPT OSS 20B has better performance per dollar (490.2 vs 469.7).

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.

More comparisons

pairs sharing a model with this page