VerifiedChat
DeepSeek-V4-Flash-0731
by 0G Foundation
Lightweight MoE (284B total / 13B active) tuned for fast, low-cost, high-throughput text work; function calling, web search, and thinking on by default (disable with enable_thinking:false); 1M context, up to 384K output. Currently served as the pinned 2026-07-31 snapshot.
openaianthropicTool CallingModalities
Context
1M
1,000,000 tokens
Max Output
393K
393,216 tokens
Input
$0.1379
per 1M tokens
Output
$0.275
per 1M tokens
Provider
6 endpoints across 2 providersAliyun (CN)TEE (dstack)TeeTLS
Input / 1M
$0.1379 ·0.71200G/M
Output / 1M
$0.275 ·1.41000G/M
Cache Read / 1M
$0.0276 ·0.14240G/M
Aliyun (CN)TEE (dstack)TeeTLS
Input / 1M
$0.1379 ·0.71300G/M
Output / 1M
$0.275 ·1.42000G/M
Cache Read / 1M
$0.0276 ·0.14260G/M
Tencent (CN)TEE (dstack)TeeTLS
Input / 1M
$0.14 ·0.72200G/M
Output / 1M
$0.28 ·1.44000G/M
Cache Read / 1M
$0.0028 ·0.01440G/M
Tencent (CN)TEE (dstack)TeeTLS
Input / 1M
$0.14 ·0.72400G/M
Output / 1M
$0.28 ·1.44000G/M
Cache Read / 1M
$0.0028 ·0.01440G/M
OpenRouter (CN)TEE (dstack)TeeTLS
Input / 1M
$0.1999 ·1.03000G/M
Output / 1M
$0.3999 ·2.06000G/M
Cache Read / 1M
$0.04 ·0.20600G/M
OpenRouter (CN)TEE (dstack)TeeTLS
Input / 1M
$0.1999 ·1.03000G/M
Output / 1M
$0.3999 ·2.06000G/M
Cache Read / 1M
$0.04 ·0.20600G/M
API
POSThttps://router-api.0g.ai/v1/chat/completions
curl "https://router-api.0g.ai/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-d '{
"model": "deepseek-v4-flash",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": true
}'Additional Features
TEE Verification
Request on-chain signature verification with verify_tee. The response includes a tee_verified field in the trace.
{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello!"}],
"verify_tee": true
}Provider Routing
Control which provider handles your request using the X-0G-Provider-* request headers.
X-0G-Provider-Address pins a provider; X-0G-Provider-Identity pins which of its upstreams to route through — both values come from the address and provider_identity fields of GET /v1/providers. Together they address one specific upstream of one provider. Send neither and the router picks by price and health, exactly as before.
curl "https://router-api.0g.ai/v1/chat/completions" \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-H "X-0G-Provider-Address: <PROVIDER_ADDRESS>" \
-H "X-0G-Provider-Identity: <UPSTREAM>" \
-H "X-0G-Provider-Sort: latency" \
-H "X-0G-Provider-Allow-Fallbacks: true" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello!"}]
}'