DeepSeek V3.1
DeepSeek V3.1 is worth evaluating for coding, agents, and vision when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, agents, and vision
- Workloads that can use a 64k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- DeepSeek V3
- Released
- 2025-08-21
- Context
- 64k
- Parameters
- 671B total, 37B active (MoE)
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Open source
- License
- MITOSI-approvedCommercial use: permitted
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 8 routes · Novita AI
About
Enhanced reasoning and grounded retrieval model from DeepSeek with multimodal text and image understanding.
DeepSeek V3.1 is an open-source model in the DeepSeek V3 family. The structured metadata tracks a 64k-token context window, multimodal input, structured outputs, and code execution. This page tracks provider routes through Microsoft Foundry, Fireworks AI, NVIDIA NIM, and 5 more, with the cheapest tracked route listed at $0.27 input and $1 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 66.0 and MMLU PRO 83.3.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ C1 relevant benchmark in the decision map.
Agents
Q/$ B1 relevant benchmark in the decision map.
Vision
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 8Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| Novita AI | $0.270 | $1.00 | - | Serverless |
| Fireworks AI | $0.560 | $1.68 | - | Serverless |
| Vercel AI Gateway | $0.560 | $1.68 | read $0.280 | Serverless |
| Together AI | $0.600 | $1.70 | - | Serverless |
Available via routers & gateways(8)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(2)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Verified | 66.0 | 2025 | https://www.swebench.com/ |
| MMLU PRO | 83.3 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(1)
Compare DeepSeek V3.1 with other models
Comparison and alternatives
Browse all comparisons →Show all 50 popular comparisonssorted by 7-day search impressions
Frequently asked questions
What is the context window of DeepSeek V3.1?
DeepSeek V3.1 has a context window of 64k tokens.
How much does DeepSeek V3.1 cost?
DeepSeek V3.1 pricing ranges from $0.27/1M to $0.672/1M input tokens depending on the provider.
When was DeepSeek V3.1 released?
DeepSeek V3.1 was released on 2025-08-21.
Which providers offer DeepSeek V3.1?
DeepSeek V3.1 is available from 8 providers: Microsoft Foundry, Fireworks AI, NVIDIA NIM, Together AI, AWS Bedrock, Replicate API, Vercel AI Gateway, Novita AI.
What benchmarks has DeepSeek V3.1 been tested on?
DeepSeek V3.1 has been evaluated on 2 benchmarks, including SWE-bench Verified, MMLU PRO.
Cheapest of 8 routes · Novita AI