Today's price · per 1M tokens
Input
$1.74
per 1M tokens
Output
$3.48
per 1M tokens
Blended
$2.17
blended $/1M — 3:1 weighted input:output
Cached input
$0.145
8% of input — prompt caching
Source: official Fireworks pricing · read Jun 25, 2026
MODELPRICEWATCH.COM · 2026-08-09
DeepSeek V4 Pro is available on 3 hosts.
See the full cheapest-first comparison on the consolidated DeepSeek V4 Pro page →
Overview
DeepSeek V4 Pro on Fireworks. $1.74/$3.48 per 1M; cached $0.145.
Capabilities
struck through = not supportedInput 1/5
Text ✓
Image
Audio
Video
PDF
Output 1/5
Text ✓
Image
Audio
Video
Embedding
Features 3/9
Prompt caching ✓
Reasoning ✓
Coding
Fast inference
Long context ✓
Open weights
Multimodal
Web search
Realtime
Benchmark performance
accuracy % · higher is betterAvg benchmark score70.7%
Perf per $/Mtok32.5
GPQA Diamond
72%
SWE-Bench Verified vendor
80.6%
LiveCodeBench
93.5%
MCP Atlas
73.6%
BrowseComp
83.4%
Humanity's Last Exam
28%
ARC-AGI 2
30%
AIME 2025
75%
MMMLU
82%
BFCL
72%
HumanEval
88%
MATH 500
80%
Independent composite scores
- AA Intelligence Index: 44.3 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 36.4 (Tool use, planning, autonomy)
- AA-Omniscience Index: -10 (−100–100)
- GDPval-AA v2: 1305.5 ELO (Real-world work tasks, human baseline = 1000)
How it stacks up
- Ranks #31 of 67 benchmarked models by average score
- Ranks #45 of 150 comparably-measured models by percentile score, across 15 independent measurements
- Ranks #91 of 150 comparably-tested models by normalized performance per dollar
- Strongest at LiveCodeBench — 93.5%, #2 of 23
80 tokens/sec output
Source: DeepSeek model card, Artificial Analysis · updated Jun 29, 2026 · See full rankings →
Specifications
- Provider
- Fireworks
- Context window
- 1M tokens
- Modality
- text
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Apr 24, 2026
- Status
- Current
- Last updated
- Jun 25, 2026
- Tags
Availability verified: Aug 3, 2026 — listed on Fireworks's own page