50 models7 providersprices scraped nightly — no estimates
deepseek · deepseek familyVerified May 18, 2026

DeepSeek R1

671B params · 131K context · mit · released 2025-01 · 4 providers

DeepSeek R1, released in January 2025 under the MIT license, was the first open-weights model to credibly match OpenAI's o1 series on reasoning benchmarks like AIME and MATH. It's a 671B-parameter MoE that uses extended chain-of-thought reasoning at inference time, which means it's more expensive per token than its non-reasoning siblings — typically $0.40–$0.55 per 1M input tokens and $2.00–$2.50 per 1M output tokens, since reasoning chains generate substantially more output tokens than a standard completion. Best for problems where verifiable correctness matters more than per-call cost: math, formal proofs, code synthesis with strict tests, and multi-step planning. For anything not requiring deep reasoning, V3.2 is a better cost choice.

Cheapest right now
DeepInfra$2.00/1M out
sticky while scrolling · verified May 18, 2026
Cheapest now
$2.00
DeepInfra · fp8 · $/1M out
90-day price Δ
cheapest-host trend
Fastest TTFT
550 ms
Fireworks AI · 90 tok/s
Providers
4
indexed providers
✓ verified May 18, 2026
#Provider$/1M in$/1M outTTFT p50tok/sQuant
1DeepInfraCHEAPEST$0.40$2.00600 ms75fp8go ↗
2OpenRouter$0.50$2.30unknowngo ↗
3Fireworks AIFASTEST$0.55$2.50550 ms90fp8go ↗
4Hyperbolic$2.00$2.00900 ms40fp8go ↗

Prices verified May 18, 2026 by scraping 4 providers. Methodology · Raw data