DeepSeek Chat
DeepSeekReleased Dec 26, 2024Open weights · MITdeepseek-chat
- Intelligence (Epoch)
- 146 · 56th of 111
- Reasoning
- no
- Knowledge cutoff
- March 2026
- Context
- 164k tokens
- Max output
- 16k tokens
- API features
- tools, structured outputs, JSON mode, seed
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from DeepSeek · cutoff: aiknowledgecutoff.com
Intelligence for the price
6 models score higher for the same price or less; it ranks 7 of the 41 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 146 with an interval of 144 to 147.
Against its rivals
The best of its price range and the top score
- DeepSeek Chatthis model$1.21146
- Claude Opus 5.5top score$24.00169
- GLM-5.3same price range$2.36156
- GPT-5.6 Lunasame price range$1.40156
Same level for 7.6× less: Qwen3.7 Flash at Alibaba, $0.16 per M input + output · their Epoch intervals overlap (144 against 146).
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
- Parameters
- 671B
- 37B active per token (MoE)
- Memory needed
- 403 GB
- in INT4 · 805 GB in INT8
- Smallest cloud setup
- 8× H100
- 640 GB · $17.20/h, about $12,556 a month
- Worth it above
- 10B tokens
- a month, against the cheapest API at $1.21 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 403 GB | 8× H100 · $17.20/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 805 GB | multi-node, over 640 GB | near-lossless |
| FP16 (full) | 1610 GB | multi-node, over 640 GB | reference quality |
At home: 403 GB in INT4 is beyond any desktop or Mac in our machines table, so it means a multi-GPU server.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| DeepInfrafp4 · 160K ctx · 16K out | $0.32 | $0.89 | — | 18 | 0.68 s | 95.1% | Oct 23 |
| StreamLakeprecision not read: host terms · 125K ctx (160K) · 16K out−10% | $0.26 | $1.03 | — | 28 | 1.56 s | 100% | Oct 23 |
2 of 2 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · −N%: a discount off the host's list price · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| DeepInfra | fp4 | 160K | 16K | yes | yes | no |
| StreamLake | not read: host terms | 125K | 16K | yes | yes | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
DeepSeek Chat spec sheet, field by field, with sources
DeepSeek Chat spec sheetmaker-declared
What the maker declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- to verify
- Parameters
- to verify
- Active experts
- to verify
- Weight precision
- to verify
- License
- MIT — open weights, permissiveScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ March 2026 third-party estimate — not the maker's figurecurated
- Modalities
- to verify
- Max output (official)
- to verify
- Release date
- to verify≈ December 26, 2024 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
huggingface.co · maker's documentation · read 2026-09-07 · 1 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Oct 22 | DeepInfra | $0.26 → $0.32 | $0.71 → $0.89 | +25% |
| Oct 16 | DeepInfra | $0.32 → $0.26 | $0.89 → $0.71 | −20% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $0.76 | $3.00 | $2.17 |
| StreamLake | $0.77 | $2.57 | $2.06 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other DeepSeek models · all its models, hosts and history ›
- DeepSeek V4.1 Flash29 providers · from $0.47
- DeepSeek V4 Flash 073125 providers · from $0.21
- DeepSeek V4 Pro 081323 providers · from $2.50
- DeepSeek V4.1 Flash 101722 providers · from $0.39
- DeepSeek V4 Pro 042315 providers · from $2.40
- DeepSeek V3.214 providers · from $0.52