Best cost/speed trade-off
DeepInfra
deepinfra/fp4$1.05 / 1M tokens
25.78 s estimated response
DeepSeek: R1 0528 provider comparison
deepseek/deepseek-r1-0528
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
- Endpoints:
- 4
- Context:
- 163.8K
- Input:
- text
- Output:
- text
At a glance
Comparison winners
Based on 1,000 input and 500 output tokens using the latest published median speed data.
Cheapest
DeepInfra
deepinfra/fp4$1.05 / 1M tokens
$0.001575 for the sample request
Fastest
StreamLake
streamlake19.76 s estimated response
$1.1427 / 1M tokens
Visual comparison
Price and performance charts
Compare published endpoint pricing and estimated response time visually.
USD per 1 million tokens for input and output. Lower is better.
DeepInfra has the lowest estimated cost for 1,000 input and 500 output tokens at $0.001575.
Based on 1,000 input and 500 output tokens. Cost is shown in USD per 1 million tokens. Lower and further left is better; the single best cost/speed trade-off appears at full opacity.
3 providers have complete pricing and speed data. DeepInfra is closest to the ideal combination of lowest cost and fastest response.
Server-rendered comparison
Provider endpoints
Prompt and completion prices are effective USD per token as published by OpenRouter. Missing speed data never removes an endpoint.
Rank providers by
| Provider / route | Current pricing ↗ | Speed measurements | Endpoint details |
|---|---|---|---|
| Provider / route | Current pricing
| Speed measurements
| Endpoint details
15 parametersfrequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_p |
Provider / route SiliconFlow siliconflow/fp8 | Current pricing
| Speed measurements
| Endpoint details
11 parametersfrequency_penalty, include_reasoning, max_tokens, reasoning, response_format, structured_outputs, temperature, tool_choice, tools, top_k, top_p |
| Provider / route | Current pricing
| Speed measurements
| Endpoint details
12 parametersfrequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, stop, structured_outputs, temperature, top_logprobs, top_p |
| Provider / route NovitaAI novita/fp8 | Current pricing
| Speed measurements
| Endpoint details
15 parametersfrequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p |
Endpoint data fetched .
R1 0528 deployment guide
How to choose a R1 0528 inference provider
R1 0528 is indexed here as a text model by DeepSeek, with 4 provider endpoints from DeepInfra, SiliconFlow, StreamLake, NovitaAI. The comparison preserves each exact OpenRouter routing tag so pricing and performance observations can be connected to the route an application would actually request.
Match the endpoint to the workload
The model publishes a 163.8K-token context window. It accepts text input and returns text output. 19 distinct supported parameters appear across the listed routes. Confirm limits on the specific endpoint rather than assuming every host exposes the same configuration.
Compare the real request economics
DeepInfra currently has the lowest estimated cost for the standard 1,000-input/500-output-token sample at $0.001575. Input-heavy and output-heavy applications can produce a different result, so review both per-million-token prices in the endpoint table.
Balance response start and generation speed
StreamLake currently has the shortest estimated 500-token response at 19.76 seconds. DeepInfra is the single endpoint closest to the current ideal cost/speed combination. Recent observations can change, so validate finalists with your own prompts.