DeepSeek-V4-Flash vs GPT-5.1-Codex
API pricing, benchmark indices and specs — updated 19 October 2026.
deepseek-ai · A · Open weights
Params
158.1 B
Context
1,048,576
30d
809 K
mit · commercial OK
openai · B · API-only
Input / 1M
$1.25
Output / 1M
$10.00
AA index
23.7
proprietary · 400K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash | GPT-5.1-Codex |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 158.1 B | n/a — API-only |
| Architecture | DeepseekV4ForCausalLM | n/a — API-only |
| Context length | 1,048,576 | 400,000 |
| Licence | mit | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 809,273 | n/a — API-only |
| Downloads all time | 12.9 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2026-04-22 | n/a — API-only |
| API input price / 1M tokens | $0.091 | $1.25 |
| API output price / 1M tokens | $0.18 | $10.00 |
| Est. cost per 1M input + 1M output tokens | $0.27 | $11.25 |
| Cached input / 1M tokens | $0.018 | $0.13 |
| AA Intelligence Index | 24.4 | 23.7 |
| AA Coding Index | 52 | — |
| AA Agentic Index | 26.3 | — |
| Max output tokens | 943,717 | 128,000 |
| API providers | 15 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
DeepSeek-V4-Flash
$0.27
GPT-5.1-Codex
$11.25
DeepSeek-V4-Flash is 41.2× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V4-Flash · fp16 @ 1024K ctx
3,211.0 GB / 24 GB