Pricingby GlyphMay 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.
Ways to buy 3
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
fp4 · cached $0.35 | $0.5 | $2.15 | $0.5 / $2.15Cheapest | $0.35 | Cheapest |
fp8 | $0.5 | $2.18 | $0.5 / $2.18+1% vs cheapest | n/a | +1% vs cheapest |
| StreamLake Default region | $0.571 | $2.29 | $0.571 / $2.29+10% vs cheapest | n/a | +10% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $93.00 direct.
Kong AI Gateway$93.00+0%
LiteLLM$93.00+0%
Eden AI$98.11+5.5%
OpenRouter$98.11+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
RequestyNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
Vercel AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. |
DeepSeek · 1M | $0.44 | $1.32 | $0.44 / $1.32 | $0.66 | 1M | on DeepInfra (fp8) | · | DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabi |
DeepSeek · 1M | $0.66 | $1.98 | $0.66 / $1.98 | $0.99 | 1M | Lab list price | · | DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. |
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. |
Google · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. |
Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · | Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. |
Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | · | Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. |
About R1 0528
Takes text in and returns text. First listed Sep 23, 2026. Up to 33K output tokens. Blended price $0.913 per 1M tokens at 3 input to 1 output. Model id deepseek-r1-0528.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does R1 0528 cost?
$0.5 per million input tokens and $2.15 per million output tokens, with cached input at $0.35.
What is the context window of R1 0528?
164K tokens, with up to 33K tokens of output.
Where is R1 0528 cheapest?
Of 3 routes tracked, DeepInfra is cheapest at $0.5 input and $2.15 output per million tokens.