DeepSeek Coder 33B
DeepSeek Coder 33B is worth evaluating for coding, classification, and json / tool use when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, classification, and json / tool use
- Workloads that can use a 16k context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Family
- DeepSeek Coder
- Released
- 2024-03-07
- Context
- 16k
- Parameters
- 33B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2023-03
- Specialization
- code
- Openness
- Open weights
- License
- DeepSeek LicenseCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 3 routes · Fireworks AI
About
DeepSeek Coder 33B is DeepSeek's DeepSeek Coder model focused on code generation and software engineering. It offers a 16K-token context window with weights openly available for self-hosting and scores 57.1 on HumanEval.
DeepSeek Coder 33B is an open-weight model in the DeepSeek Coder family. The structured metadata tracks a 16k-token context window and structured outputs. This page tracks provider routes through Together AI, Alibaba Cloud PAI-EAS, and Fireworks AI, with the cheapest tracked route listed at $0.8 input and $0.8 output per 1M tokens. Headline tracked benchmarks include HumanEval 57.1 and Massive Multitask Language Understanding 73.8.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ C1 relevant benchmark in the decision map.
Classification
Q/$ C1 relevant benchmark in the decision map.
JSON / Tool use
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 3Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Fireworks AI | $0.900 | $0.900 | Provisioned |
| Alibaba Cloud PAI-EAS | - | - | ServerlessPartial |
Available via routers & gateways(1)
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(2)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| HumanEval | 57.1 | pass@1Observed 2026-03-06 | — | Source |
| Massive Multitask Language Understanding | 73.8 | 5-shotObserved 2026-03-06 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of DeepSeek Coder 33B?
DeepSeek Coder 33B has a context window of 16k tokens.
How much does DeepSeek Coder 33B cost?
DeepSeek Coder 33B pricing ranges from $0.8/1M to $0.90/1M input tokens depending on the provider.
When was DeepSeek Coder 33B released?
DeepSeek Coder 33B was released on 2024-03-07.
Which providers offer DeepSeek Coder 33B?
DeepSeek Coder 33B is available from 3 providers: Together AI, Alibaba Cloud PAI-EAS, Fireworks AI.
What benchmarks has DeepSeek Coder 33B been tested on?
DeepSeek Coder 33B has been evaluated on 2 benchmarks, including HumanEval, Massive Multitask Language Understanding.
Cheapest of 3 routes · Fireworks AI