Back
DeepSeek: R1 (free)
DeepSeek
Input: text
Output: text
Released: Jan 20, 2025•Updated: May 28, 2025
DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.
Fully open-source model & technical report.
MIT licensed: Distill & commercialize freely!
163,840 Token Context
Process and analyze large documents and conversations.
Hybrid Reasoning
Choose between rapid responses and extended, step-by-step processing for complex tasks.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| InferenceNet | inferenceNet | 128K | 33K | $0.45/M | $2.15/M | 48.0 t/s | 1178 ms |
| DeepInfra | deepInfra | 164K | 164K | $0.45/M | $2.15/M | 120.7 t/s | 503 ms |
| Lambda | lambda | 164K | 164K | $0.54/M | $2.18/M | 36.6 t/s | 589 ms |
| Novita | novitaAi | 64K | 16K | $0.70/M | $2.50/M | 27.8 t/s | 1211 ms |
| Nebius | nebiusAiStudio | 164K | - | $0.80/M | $2.40/M | 27.0 t/s | 740 ms |
| DeepInfra | deepInfraTurbo | 33K | - | $1.00/M | $3.00/M | 134.7 t/s | 582 ms |
| Kluster | klusterAi | 164K | 164K | $1.75/M | $5.00/M | 38.6 t/s | 1184 ms |
| Cent-ML | centMl | 131K | 131K | $1.99/M | $2.99/M | 70.9 t/s | 888 ms |
| Nebius | nebiusFast | 164K | - | $2.00/M | $6.00/M | 64.4 t/s | 665 ms |
| Friendli | friendli | 164K | 164K | $3.00/M | $7.00/M | 65.7 t/s | 851 ms |
| Fireworks | fireworks | 164K | - | $3.00/M | $8.00/M | 72.3 t/s | 638 ms |
| Minimax | minimax | 64K | 64K | $0.55/M | $2.19/M | 20.8 t/s | 2547 ms |
| Azure | azure | 164K | 4K | $1.48/M | $5.94/M | 75.0 t/s | 1810 ms |
Standard Pricing