deepseek-chat
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.
text → text · made by DeepSeek
Sold by 6 ways
| Seller | Lane | Rate |
|---|---|---|
| Requesty aggregator | deepseek | $0.14per Mtok in$0.28per Mtok out$0.028per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Nous Research aggregator | standard | $0.26per Mtok in$1.03per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 3 ways | $0.26per Mtok in$1.03per Mtok out | |
| OpenRouter aggregator | standard | $0.26per Mtok in$1.03per Mtok outopenrouter.ai · read 2026-09-10 |
| OpenRouter aggregator | streamlake | $0.26per Mtok in$1.03per Mtok outopenrouter.ai · read 2026-09-04 |
| OpenRouter aggregator | deepinfra/fp4 | $0.32per Mtok in$0.89per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | novita/fp8 | $0.4per Mtok in$1.3per Mtok outopenrouter.ai · read 2026-08-25 |
Measured 7 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 22ndof 72 | Aider polyglot — Epoch AI | Percent correct | 70.2 |
| 102ndof 123 | Lmca — Epoch AI | Score | 15.24 |
| 106thof 161 | Dtbench — Epoch AI | Accuracy | 62.67 |
| 172ndof 313 | GPQA Diamond | mean_score | 71.212 |
| 184thof 290 | OTIS Mock AIME 2024-2025 | mean_score | 48.889 |
| 193rdof 222 | Chess puzzles — Epoch AI | mean_score | 1 |
| 297thof 656 | Epoch capabilities index — Epoch AI | ECI Score | 146.21 |
About
deepseek-chat — a text model from DeepSeek, sold by 3 companies from $0.26 in and $1.03 out per million tokens, placed 22nd of 72 on Aider polyglot — Epoch AI.
It takes text and returns text, with a context window of 163,840 tokens. It was published in December 2025, trained on material up to September 2025. Its sellers say it can call a tool. The catalogue files it under evaluate and reasoning. Three companies sell it. The cheapest is $0.26 in and $1.03 out per million tokens at Nous Research. Beside the standard rate there are regional and separately routed lanes. It has been measured on 7 boards, and stands best at 22nd of 72 on Aider polyglot — Epoch AI.
Every current figure
- Maker
- DeepSeek
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 163,840 tokens
- Published
- December 2025
- Knowledge to
- September 2025
- Sellers
- 3
- Maker's own price
- not read
- Price
- $0.26 in and $1.03 out per million tokens — Nous Research
- Boards
- 7
- Best place
- 22nd of 72 — Aider polyglot — Epoch AI
Known as 1 name
deepseek/deepseek-chat