deepseek-r1
replicate · chat model
deepseek-r1 is listed here as a chat model from replicate. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$3.7500 / 1M tokens
Output
$10.0000 / 1M tokens
Cached input
N/A
Context
8.2K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $3.7500 / 1M tokens |
| Output | $10.0000 / 1M tokens |
| Reasoning output | $10.0000 / 1M tokens |
| Embedding | $3.7500 / 1M tokens |
Token limits
Context window
8.2K
Max input tokens
65.5K
Max output tokens
8.2K
Max tokens
8.2K
Capabilities
| Capability | Supported |
|---|---|
| Vision | — |
| Function calling | — |
| Parallel function calling | — |
| Tool choice | — |
| Prompt caching | — |
| Reasoning | ✅ |
| Response schema | — |
| System messages | ✅ |
| Audio input | — |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| GPQA Diamond | 71.5 | Pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| LiveCodeBench | 65.9 | Pass@1-COT | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| AIME 2024 | 79.8 | Pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| MATH-500 | 97.3 | Pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| Aider Polyglot | 71.4% | percent correct | Base model: DeepSeek R1 (deepseek/deepseek-reasoner) | 2026-05-31 | Link |
| Artificial Analysis Intelligence Index | 18.8 | index score | Base model: DeepSeek R1 (deepseek/deepseek-r1) | 2026-05-31 | Link |
| Artificial Analysis Coding Index | 15.9 | index score | Base model: DeepSeek R1 (deepseek/deepseek-r1) | 2026-05-31 | Link |
| Artificial Analysis Agentic Index | 3.8 | index score | Base model: DeepSeek R1 (deepseek/deepseek-r1) | 2026-05-31 | Link |
| MMLU | 90.8 | pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| GPQA Diamond | 71.5 | pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| LiveCodeBench | 65.9 | pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| Codeforces | 2029 | rating | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| SWE-bench Verified | 49.2 | resolved | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| Aider Polyglot | 53.3 | accuracy | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| AIME 2024 | 79.8 | pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| MATH-500 | 97.3 | pass@1 | Base model: DeepSeek-R1 (DeepSeek-R1) | 2026-05-31 | Link |
| Artificial Analysis Intelligence Index | 18.8 | score | Base model: deepseek-r1 (deepseek/deepseek-r1) | 2026-05-31 | Link |
| Artificial Analysis Coding Index | 15.9 | score | Base model: deepseek-r1 (deepseek/deepseek-r1) | 2026-05-31 | Link |
| Artificial Analysis Agentic Index | 3.8 | score | Base model: deepseek-r1 (deepseek/deepseek-r1) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| deepseek-r1 replicate | In $3.7500 / 1M tokens Out $10.0000 / 1M tokens | text
Output: text | ReasoningSystem messages | 8.2K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| moonshot.kimi-k2-thinking bedrock_converse | In $0.6000 / 1M tokens Out $2.5000 / 1M tokens | text
Output: text | ReasoningSystem messages | 8.2K | Text covered Overall 84% |
| mistral-large azure_ai | In $4.0000 / 1M tokens Out $12.0000 / 1M tokens | text
Output: text | Low overlap | 8.2K | Text covered Overall 73% |
| mistral-large-2402 Mistral | In $4.0000 / 1M tokens Out $12.0000 / 1M tokens | text
Output: text | Low overlap | 8.2K | Text covered Overall 73% |
| MAI-DS-R1 azure_ai | In $1.3500 / 1M tokens Out $5.4000 / 1M tokens | text
Output: text | Reasoning | 8.2K | Text covered Overall 73% |
| deepseek-r1 azure_ai | In $1.3500 / 1M tokens Out $5.4000 / 1M tokens | text
Output: text | Reasoning | 8.2K | Text covered Overall 73% |
| qwen3-235b-a22b-fp8 novita | In $0.2000 / 1M tokens Out $0.8000 / 1M tokens | text
Output: text | ReasoningSystem messages | 20.0K | Text covered Overall 73% |
| o1-mini replicate | In $1.1000 / 1M tokens Out $4.4000 / 1M tokens | text
Output: text | ReasoningSystem messages | N/A | Same provider Overall 72% |
| us.writer.palmyra-x4-v1:0 bedrock_converse | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | text pdf
Output: text | Low overlap | 8.2K | Text covered Overall 72% |
| writer.palmyra-x4-v1:0 bedrock_converse | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | text pdf
Output: text | Low overlap | 8.2K | Text covered Overall 72% |
| qwen3-32b-fp8 novita | In $0.1000 / 1M tokens Out $0.4500 / 1M tokens | text
Output: text | ReasoningSystem messages | 20.0K | Text covered Overall 72% |
| deepseek-r1-0528-qwen3-8b novita | In $0.0600 / 1M tokens Out $0.0900 / 1M tokens | text
Output: text | ReasoningSystem messages | 32.0K | Text covered Overall 69% |
| deepseek-v3 replicate | In $1.4500 / 1M tokens Out $1.4500 / 1M tokens | text
Output: text | System messages | 8.2K | Same provider Overall 68% |
| ernie-4.5-21B-a3b-thinking novita | In $0.0700 / 1M tokens Out $0.2800 / 1M tokens | text
Output: text | ReasoningSystem messages | 65.5K | Text covered Overall 67% |
| deepseek-v3.1 replicate | In $0.6720 / 1M tokens Out $2.0160 / 1M tokens | text
Output: text | ReasoningSystem messages | 163.8K | Same provider Overall 61% |
| o4-mini replicate | In $1.0000 / 1M tokens Out $4.0000 / 1M tokens | text image
Output: text | ReasoningSystem messages | N/A | Same provider Overall 60% |
| llama-3-70b replicate | In $0.6500 / 1M tokens Out $2.7500 / 1M tokens | text
Output: text | Low overlap | 8.2K | Same provider Overall 60% |
| llama-3-70b-instruct replicate | In $0.6500 / 1M tokens Out $2.7500 / 1M tokens | text
Output: text | Low overlap | 8.2K | Same provider Overall 60% |
| openai replicate | In $15.0000 / 1M tokens Out $60.0000 / 1M tokens | text image
Output: text | ReasoningSystem messages | N/A | Same provider Overall 57% |
| gpt-4o-2024-08-06 Azure | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | text image
Output: text | Low overlap | 16.4K | Text covered Overall 53% |
| gpt-4o-2024-11-20 Azure | In $2.5000 / 1M tokens Out $10.0000 / 1M tokens | text image
Output: text | Low overlap | 16.4K | Text covered Overall 53% |
| mistral-large watsonx | In $3.0000 / 1M tokens Out $10.0000 / 1M tokens | text
Output: unknown | System messages | 16.4K | Partial I/O overlap Overall 30% Missing text |
| mistral-medium-2505 watsonx | In $3.0000 / 1M tokens Out $10.0000 / 1M tokens | text
Output: unknown | Low overlap | 128.0K | Partial I/O overlap Overall 19% Missing text |
No models match this filter.