LIVE Base · USDCx402 v2
Surplus Live
Pay-per-request AI inference, settled in USDC on Base.
OpenAI-compatible inference marketplace with x402 pay-per-request access. Credit-package purchases are deprecated.
Models advertised
150
96 with a live provider
Inference providers
10
211 provider routes
API endpoints
8
6 inference · 2 resource
Resource markets
2
2/2 healthy · avg 3.5% off
Surplus token market
Contract: 0xC52a…CBa3 ↗ · source: DexScreener Base pairs.
Price
$0.0001
24h +85.17%
FDV
$6.28M
market cap $6.28M
Liquidity
$1.39M
top pool
24h volume
$3.28M
6K txns
Pairs tracked
8
Base / Uniswap
| Pair | Price | Liquidity | 24h vol | 24h |
|---|---|---|---|---|
| Surplus/WETH ↗uniswap | $0.0001 | $1.39M | $3.28M | +85.17% |
| Surplus/USDC ↗uniswap | $0.0001 | $21.8K | $14.9K | +79.29% |
| Surplus/USDC ↗uniswap | $0.0001 | $9.3K | $69.9K | +70.53% |
| Surplus/USDC ↗uniswap | $0.0000 | $1.6K | $4.1K | -7.24% |
| Surplus/USDC ↗uniswap | $0.0000 | $1.5K | $396.55 | +0.50% |
| Surplus/USDC ↗uniswap | $0.0000 | $1.4K | $423.60 | +63.70% |
| Surplus/USDC ↗uniswap | $0.0000 | $815.81 | $0.00 | — |
| Surplus/USDC ↗uniswap | $0.0000 | $602.95 | $100.29 | +0.41% |
x402 payment rails
LIVENetwork
eip155:8453
Base (chainId 8453)
Facilitator
Coinbase CDP x402
https://api.cdp.coinbase.com/platform/v2/x402
Schemes
upto · preferredexact
upto settles actual usage · exact settles the estimate
Headers
PAYMENT-REQUIRED
PAYMENT-SIGNATURE
PAYMENT-RESPONSE
Settlement flow
- 1. POST inference request, no Authorization.
- 2. Receive HTTP 402 with payment requirements.
- 3. Pick upto (or exact) and sign.
- 4. Resend with PAYMENT-SIGNATURE header.
- 5. Receive inference + PAYMENT-RESPONSE.
Marketplace pricing
Source: /api/inference/v1/prices. Provider list prices in USD per 1M tokens (matches public provider rate cards).
Cheapest input
best $/1M prompt
GPT OSS 20B
OpenAI
$0.050
Venice AI
Qwen 2.5 7B
Alibaba
$0.050
Venice AI
GPT 5 Nano
OpenAI
$0.050
Bankr
Qwen 3.5 9B
Alibaba
$0.050
Venice AI
OpenAI GPT OSS 120B
OpenAI
$0.070
Venice AI
NVIDIA Nemotron 3 Nano 30B
NVIDIA
$0.075
Venice AI
Cheapest output
best $/1M completion
Qwen 2.5 7B
Alibaba
$0.130
Venice AI
Qwen 3.5 9B
Alibaba
$0.150
Venice AI
GPT OSS 20B
OpenAI
$0.190
Venice AI
Mistral Small 3.2 24B Instruct
Mistral AI
$0.250
Venice AI
NVIDIA Nemotron 3 Nano 30B
NVIDIA
$0.300
Venice AI
OpenAI GPT OSS 120B
OpenAI
$0.300
Venice AI
Premium frontier
highest $/1M completion
GPT-5.4 Pro
OpenAI
$225.0
in $37.5
GPT-5.5 Pro
OpenAI
$225.0
in $37.5
Claude Opus 4.6 Fast
Anthropic
$180.0
in $36.0
GPT-5.5
OpenAI
$37.5
in $6.25
Claude Opus 4.5
Anthropic
$25.0
in $5.00
Claude Opus 4.6
Anthropic
$25.0
in $5.00
Most competitive
most providers competing
Mistral Small 3.2 24B Instruct
Mistral AI
6×
best in $0.094
DeepSeek V3.2
DeepSeek
6×
best in $0.150
Llama 3.3 70B
Meta
5×
best in $0.100
Gemma 3 27B
Google
5×
best in $0.140
Llama 3.2 3B
Meta
5×
best in $0.150
DeepSeek R1
DeepSeek
5×
best in $0.550
Modality coverage
Models grouped by what they ingest/produce. Source: /x402/api/inference/v1/models · architecture.modality.
Text → text
75
75/75 routable
in: GPT OSS 20B$0.050
out: Qwen 2.5 7B$0.130
Image generation
31
0/31 routable
No active provider offers.
Vision (image → text)
21
21/21 routable
in: Gemma 4 26B A4B IT$0.130
out: Gemma 4 26B A4B IT$0.400
Music
11
0/11 routable
No active provider offers.
Audio → text
4
0/4 routable
No active provider offers.
Video
4
0/4 routable
No active provider offers.
Text → audio
3
0/3 routable
No active provider offers.
Embedding
1
0/1 routable
No active provider offers.
Provider coverage & pricing spread
Per inference provider, how many models they serve plus the min / median / max input price they charge (USD per 1M tokens).
| Provider | Models | Min in | Median in | Max in | Median out |
|---|---|---|---|---|---|
| Venice AIvenice | 81 | $0.050 | $0.500 | $37.5 | $2.75 |
| OpenRouteropenrouter | 48 | $0.094 | $0.555 | $37.5 | $3.00 |
| Bankrbankr | 33 | $0.050 | $0.600 | $5.00 | $2.80 |
| Together AItogether | 20 | $0.050 | $0.335 | $1.10 | $1.34 |
| Fireworks AIfireworks | 12 | $0.094 | $0.340 | $1.10 | $1.32 |
| Anthropicanthropic | 6 | $1.00 | $4.30 | $5.00 | $21.5 |
| Groqgroq | 4 | $0.094 | $0.350 | $0.700 | $1.40 |
| Googlegoogle | 3 | $0.140 | $0.700 | $2.50 | $3.75 |
| DeepSeekdeepseek | 2 | $0.280 | $0.415 | $0.550 | $1.30 |
| Mistral AImistral | 2 | $0.094 | $0.297 | $0.500 | $1.13 |
Multi-provider model routes
Models with the most provider competition. Pill = provider · best $/1M in / out.
mistral-small-3.2-24b-instructMistral Small 3.2 24B Instruct · Mistral AI
best $0.094 in · $0.250 out · 256K ctx
Venice AI·$0.094/$0.250OpenRouter·$0.094/$0.250Mistral AI·$0.094/$0.250Groq·$0.094/$0.250Together AI·$0.094/$0.250Fireworks AI·$0.094/$0.250
deepseek-v3.2DeepSeek V3.2 · DeepSeek
best $0.150 in · $0.380 out · 160K ctx
Bankr·$0.260/$0.380DeepSeek·$0.280/$0.420Venice AI·$0.330/$0.480Fireworks AI·$0.330/$0.480Together AI·$0.330/$0.480OpenRouter·$0.150/$0.750
llama-3.3-70b-instructLlama 3.3 70B · Meta
best $0.100 in · $0.320 out · 128K ctx
OpenRouter·$0.100/$0.320Venice AI·$0.700/$2.80Together AI·$0.700/$2.80Fireworks AI·$0.700/$2.80Groq·$0.700/$2.80
gemma-3-27b-itGemma 3 27B · Google
best $0.140 in · $0.500 out · 40K ctx
Venice AI·$0.140/$0.500OpenRouter·$0.140/$0.500Google·$0.140/$0.500Together AI·$0.140/$0.500Fireworks AI·$0.140/$0.500
llama-3.2-3b-instructLlama 3.2 3B · Meta
best $0.150 in · $0.600 out · 128K ctx
Venice AI·$0.150/$0.600OpenRouter·$0.150/$0.600Groq·$0.150/$0.600Together AI·$0.150/$0.600Fireworks AI·$0.150/$0.600
deepseek-r1DeepSeek R1 · DeepSeek
best $0.550 in · $2.19 out · 160K ctx
OpenRouter·$0.550/$2.19DeepSeek·$0.550/$2.19Together AI·$0.550/$2.19Fireworks AI·$0.550/$2.19Groq·$0.550/$2.19
Largest context windows
grok-4
xAI
2.0M
$2.00 in · $6.00 out
grok-4.20-beta
xAI
2.0M
$2.00 in · $6.00 out
grok-4.20-multi-agent-beta
xAI
2.0M
$2.50 in · $7.50 out
gemini-2.5-flash
Google
1.0M
$0.300 in · $2.50 out
gemini-2.5-pro
Google
1.0M
$1.25 in · $10.0 out
gemini-3.1-flash-lite
Google
1.0M
$0.250 in · $1.50 out
Model families on Surplus
Venice AI58OpenAI16Alibaba15Zhipu AI12Google11Anthropic7xAI6DeepSeek4Moonshot4MiniMax4Meta3Mistral AI3NVIDIA2Alibaba Cloud2Aion Labs1Inception Labs1Arcee AI1
17 families served via 10 inference providers — one OpenAI-compatible endpoint, one wallet, no per-provider API keys.
Resource markets
Non-inference APIs sold per request via x402 — agents discover and buy without holding upstream keys. Source: /api/resource/markets.
twitter_api · v2
1/1 healthy offers
2.0%
best discount
Read-only X/Twitter API v2 proxy backed by seller-supplied app-only bearer tokens. Sellers configure a discount/multiplier vs Twitter API prices. Write/action endpoints are intentionally not supported.
Route templates (14)
/x402/api/twitter/v2/tweets
/x402/api/twitter/v2/tweets/:tweetId
/x402/api/twitter/v2/tweets/search/recent
/x402/api/twitter/v2/tweets/search/all
/x402/api/twitter/v2/tweets/counts/recent
/x402/api/twitter/v2/tweets/counts/all
/x402/api/twitter/v2/tweets/:tweetId/quote_tweets
/x402/api/twitter/v2/users
… +6 more
0x8581...c402
twitter-api-v2-2pct-offer
2.0% off
healthy · ×0.98
venice_rpc · crypto-rpc
1/1 healthy offers
5.0%
best discount
Venice crypto JSON-RPC proxy backed by seller-supplied Venice API keys. Sellers configure a proportion of Venice RPC prices.
Supported networks (23)
ethereum-mainnetethereum-sepoliaethereum-holeskybase-mainnetbase-sepoliaarbitrum-mainnetarbitrum-sepoliaoptimism-mainnetoptimism-sepoliapolygon-mainnetpolygon-amoylinea-mainnet+11 more
0x8581...c402
test-venice-rpc-offer
5.0% off
healthy · ×0.95
All models & prices
Every model returned by Surplus, sorted by cheapest input. Models without a live provider are at the bottom.
| Model | Family | Modality | Ctx | Best in | Best out | Providers |
|---|---|---|---|---|---|---|
e2ee-gpt-oss-20b-p GPT OSS 20B | OpenAI | Text → text | 128K | $0.050 | $0.190 | 2 |
e2ee-qwen-2-5-7b-p Qwen 2.5 7B | Alibaba | Text → text | 32K | $0.050 | $0.130 | 1 |
gpt-5-nano GPT 5 Nano | OpenAI | Text → text | 400K | $0.050 | $0.400 | 1 |
qwen3-5-9b Qwen 3.5 9B | Alibaba | Text → text | 256K | $0.050 | $0.150 | 1 |
openai-gpt-oss-120b OpenAI GPT OSS 120B | OpenAI | Text → text | 128K | $0.070 | $0.300 | 2 |
nvidia-nemotron-3-nano-30b-a3b NVIDIA Nemotron 3 Nano 30B | NVIDIA | Text → text | 128K | $0.075 | $0.300 | 1 |
mistral-small-3.2-24b-instruct Mistral Small 3.2 24B Instruct | Mistral AI | Text → text | 256K | $0.094 | $0.250 | 6 |
llama-3.3-70b-instruct Llama 3.3 70B | Meta | Text → text | 128K | $0.100 | $0.320 | 5 |
qwen3.5-flash Qwen3.5 Flash | Alibaba Cloud | Text → text | 1.0M | $0.100 | $0.400 | 1 |
e2ee-glm-4.7-flash GLM 4.7 Flash E2EE | Zhipu AI | Text → text | 198K | $0.130 | $0.550 | 1 |
e2ee-gpt-oss-120b-p GPT OSS 120B | OpenAI | Text → text | 128K | $0.130 | $0.650 | 1 |
gemma-4-26b-a4b-it Gemma 4 26B A4B IT | Vision (image → text) | 262K | $0.130 | $0.400 | 2 | |
glm-4.7-flash GLM 4.7 Flash | Zhipu AI | Text → text | 198K | $0.130 | $0.550 | 2 |
e2ee-gemma-3-27b Gemma 3 27B E2EE | Text → text | 40K | $0.140 | $0.500 | 1 | |
gemma-3-27b-it Gemma 3 27B | Text → text | 40K | $0.140 | $0.500 | 5 | |
gemma-4-31b-it Gemma 4 31B IT | Vision (image → text) | 262K | $0.140 | $0.400 | 2 | |
glm-4.7-flash-heretic GLM 4.7 Flash Heretic | Zhipu AI | Text → text | 200K | $0.140 | $0.800 | 1 |
nvidia-nemotron-cascade-2-30b-a3b NVIDIA Nemotron Cascade 2 30B | NVIDIA | Text → text | 256K | $0.140 | $0.800 | 1 |
deepseek-v3.2 DeepSeek V3.2 | DeepSeek | Text → text | 160K | $0.150 | $0.380 | 6 |
llama-3.2-3b-instruct Llama 3.2 3B | Meta | Text → text | 128K | $0.150 | $0.600 | 5 |
qwen3-235b-a22b-2507 Qwen 3 235B A22B Instruct 2507 | Alibaba | Text → text | 128K | $0.150 | $0.750 | 4 |
gemma-4-uncensored Gemma 4 Uncensored | Vision (image → text) | 256K | $0.163 | $0.500 | 1 | |
deepseek-v4-flash DeepSeek V4 Flash | DeepSeek | Text → text | 1.0M | $0.170 | $0.350 | 2 |
gpt-4o-mini GPT-4o Mini | OpenAI | Text → text | 128K | $0.188 | $0.750 | 2 |
mistral-small-4 Mistral Small 4 | Mistral AI | Vision (image → text) | 256K | $0.188 | $0.750 | 2 |
qwen3-30b-a3b Qwen3 30B A3B | Alibaba | Text → text | 256K | $0.190 | $0.690 | 4 |
gpt-5.4-nano GPT 5.4 Nano | OpenAI | Vision (image → text) | 400K | $0.200 | $1.25 | 1 |
grok-4.1-fast Grok 4.1 Fast | xAI | Text → text | 1.0M | $0.200 | $0.500 | 3 |
venice-uncensored Venice Uncensored 1.1 | Venice AI | Text → text | 32K | $0.200 | $0.900 | 1 |
venice-uncensored-1.2 Venice Uncensored 1.2 | Venice AI | Vision (image → text) | 128K | $0.200 | $0.900 | 1 |
e2ee-venice-uncensored-24b-p Venice Uncensored 1.1 | Venice AI | Text → text | 32K | $0.250 | $1.15 | 1 |
gemini-3.1-flash-lite Gemini 3.1 Flash Lite | Vision (image → text) | 1.0M | $0.250 | $1.50 | 1 | |
gpt-5-mini GPT 5 Mini | OpenAI | Text → text | 400K | $0.250 | $2.00 | 1 |
grok-code-fast-1 Grok Code Fast 1 | xAI | Text → text | 256K | $0.250 | $1.87 | 2 |
qwen3-vl-235b-a22b-thinking Qwen3 VL 235B | Alibaba | Text → text | 256K | $0.250 | $1.50 | 3 |
qwen3-vl-30b-a3b-thinking Qwen3 VL 30B A3B | Alibaba | Text → text | 128K | $0.250 | $0.900 | 3 |
qwen3.5-plus Qwen3.5 Plus | Alibaba Cloud | Text → text | 1.0M | $0.260 | $1.56 | 1 |
gemini-2.5-flash Gemini 2.5 Flash | Vision (image → text) | 1.0M | $0.300 | $2.50 | 1 | |
minimax-m2.5 MiniMax M2.5 | MiniMax | Text → text | 198K | $0.300 | $1.19 | 4 |
minimax-m2.7 MiniMax M2.7 | MiniMax | Text → text | 198K | $0.300 | $1.20 | 3 |
mercury-2 Mercury 2 | Inception Labs | Text → text | 128K | $0.313 | $0.938 | 1 |
qwen3-5-35b-a3b Qwen 3.5 35B A3B | Alibaba | Text → text | 256K | $0.313 | $1.25 | 1 |
trinity-large-thinking Trinity Large Thinking | Arcee AI | Text → text | 256K | $0.313 | $1.13 | 1 |
qwen3.6-27b Qwen 3.6 27B | Alibaba | Vision (image → text) | 256K | $0.325 | $3.25 | 1 |
minimax-m2.1 MiniMax M2.1 | MiniMax | Text → text | 198K | $0.350 | $1.50 | 2 |
qwen3-coder-turbo Qwen 3 Coder 480B Turbo | Alibaba | Text → text | 256K | $0.350 | $1.50 | 1 |
qwen3-next-80b-a3b-instruct Qwen 3 Next 80b | Alibaba | Text → text | 256K | $0.350 | $1.90 | 4 |
kimi-k2 Kimi K2 | Moonshot | Text → text | 256K | $0.450 | $2.20 | 1 |
kimi-k2.5 Kimi K2.5 | Moonshot | Text → text | 256K | $0.450 | $2.80 | 4 |
qwen3-235b-a22b-thinking-2507 Qwen 3 235B A22B Thinking 2507 | Alibaba | Text → text | 128K | $0.450 | $3.50 | 3 |
e2ee-qwen3-5-122b-a10b Qwen3.5 122B A10B | Alibaba | Text → text | 128K | $0.500 | $4.00 | 1 |
gemini-3-flash-preview Gemini 3 Flash Preview | Text → text | 256K | $0.500 | $3.00 | 4 | |
mistral-large Venice Medium | Mistral AI | Text → text | 128K | $0.500 | $1.50 | 4 |
venice-uncensored-role-play Venice Role Play Uncensored | Venice AI | Text → text | 128K | $0.500 | $2.00 | 1 |
deepseek-r1 DeepSeek R1 | DeepSeek | Text → text | 160K | $0.550 | $2.19 | 5 |
minimax-m2.7-highspeed MiniMax M2.7 Highspeed | MiniMax | Text → text | 205K | $0.600 | $2.40 | 1 |
qwen3-coder Qwen 3 Coder 480b | Alibaba | Text → text | 256K | $0.600 | $2.40 | 4 |
qwen3.6-plus-uncensored Qwen 3.6 Plus Uncensored | Alibaba | Vision (image → text) | 1.0M | $0.625 | $3.75 | 1 |
glm-5 GLM 5 | Zhipu AI | Text → text | 198K | $0.720 | $2.30 | 5 |
gpt-5.4-mini GPT-5.4 Mini | OpenAI | Text → text | 400K | $0.750 | $4.50 | 3 |
kimi-k2-thinking Kimi K2 Thinking | Moonshot | Text → text | 256K | $0.750 | $3.20 | 2 |
qwen3.5-397b-a17b Qwen 3.5 397B | Alibaba | Vision (image → text) | 128K | $0.750 | $4.50 | 1 |
glm-4.6 GLM 4.6 | Zhipu AI | Text → text | 198K | $0.850 | $2.75 | 2 |
kimi-k2.6 Kimi K2.6 | Moonshot | Vision (image → text) | 256K | $0.850 | $4.66 | 2 |
aion-labs.aion-2-0 Aion 2.0 | Aion Labs | Text → text | 128K | $1.00 | $2.00 | 1 |
claude-haiku-4.5 Claude Haiku 4.5 | Anthropic | Vision (image → text) | 200K | $1.00 | $5.00 | 2 |
e2ee-glm-4.7 GLM 4.7 E2EE | Zhipu AI | Text → text | 128K | $1.10 | $4.15 | 1 |
e2ee-glm-5 GLM 5 E2EE | Zhipu AI | Text → text | 198K | $1.10 | $4.15 | 1 |
e2ee-glm-5.1 GLM 5.1 E2EE | Zhipu AI | Text → text | 200K | $1.10 | $4.15 | 1 |
glm-4.7 GLM 4.7 | Zhipu AI | Text → text | 128K | $1.10 | $4.15 | 2 |
hermes-3-llama-3.1-405b Hermes 3 Llama 3.1 405b | Meta | Text → text | 128K | $1.10 | $3.00 | 3 |
glm-5-turbo GLM-5 Turbo | Zhipu AI | Text → text | 200K | $1.20 | $4.00 | 2 |
gemini-2.5-pro Gemini 2.5 Pro | Vision (image → text) | 1.0M | $1.25 | $10.0 | 1 | |
grok-4.3 Grok 4.3 | xAI | Vision (image → text) | 1.0M | $1.42 | $2.83 | 1 |
glm-5v-turbo GLM 5V Turbo | Zhipu AI | Vision (image → text) | 200K | $1.50 | $5.00 | 1 |
deepseek-v4-pro DeepSeek V4 Pro | DeepSeek | Text → text | 1.0M | $1.73 | $3.80 | 2 |
glm-5.1 GLM 5.1 | Zhipu AI | Text → text | 200K | $1.75 | $5.50 | 1 |
gpt-5.2 GPT-5.2 | OpenAI | Text → text | 256K | $1.75 | $14.0 | 3 |
gpt-5.2-codex GPT-5.2 Codex | OpenAI | Text → text | 256K | $1.75 | $14.0 | 3 |
gemini-3.1-pro Gemini 3.1 Pro | Vision (image → text) | 1.0M | $2.00 | $12.0 | 1 | |
gemini-3.1-pro-preview Gemini 3.1 Pro Preview | Text → text | 1.0M | $2.00 | $12.0 | 4 | |
grok-4 Grok 4 | xAI | Vision (image → text) | 2.0M | $2.00 | $6.00 | 1 |
grok-4.20-beta Grok 4.20 Beta | xAI | Text → text | 2.0M | $2.00 | $6.00 | 3 |
gpt-5.3-codex GPT-5.3 Codex | OpenAI | Text → text | 400K | $2.19 | $17.5 | 2 |
gpt-5.4 GPT-5.4 | OpenAI | Text → text | 1.0M | $2.50 | $15.0 | 3 |
grok-4.20-multi-agent-beta Grok 4.20 Multi-Agent Beta | xAI | Text → text | 2.0M | $2.50 | $7.50 | 2 |
claude-sonnet-4.5 Claude Sonnet 4.5 | Anthropic | Text → text | 198K | $3.00 | $15.0 | 4 |
claude-sonnet-4.6 Claude Sonnet 4.6 | Anthropic | Text → text | 1.0M | $3.00 | $15.0 | 4 |
gpt-4o GPT-4o | OpenAI | Text → text | 128K | $3.13 | $12.5 | 2 |
claude-opus-4.5 Claude Opus 4.5 | Anthropic | Text → text | 198K | $5.00 | $25.0 | 4 |
claude-opus-4.6 Claude Opus 4.6 | Anthropic | Text → text | 1.0M | $5.00 | $25.0 | 4 |
claude-opus-4.7 Claude Opus 4.7 | Anthropic | Text → text | 1.0M | $5.00 | $25.0 | 4 |
gpt-5.5 GPT-5.5 | OpenAI | Vision (image → text) | 1.0M | $6.25 | $37.5 | 1 |
claude-opus-4.6-fast Claude Opus 4.6 Fast | Anthropic | Vision (image → text) | 1.0M | $36.0 | $180.0 | 1 |
gpt-5.4-pro GPT-5.4 Pro | OpenAI | Text → text | 1.0M | $37.5 | $225.0 | 2 |
gpt-5.5-pro GPT-5.5 Pro | OpenAI | Vision (image → text) | 1.0M | $37.5 | $225.0 | 1 |
venice-ace-step-15 ACE-Step 1.5 (Venice) | Venice AI | Music | — | — | — | — |
venice-bria-bg-remover Background Remover (Venice) | Venice AI | Image generation | — | — | — | — |
venice-chroma Chroma (Venice) | Venice AI | Image generation | — | — | — | — |
venice-elevenlabs-music ElevenLabs Music (Venice) | Venice AI | Music | — | — | — | — |
venice-elevenlabs-sound-effects-v2 ElevenLabs Sound Effects v2 (Venice) | Venice AI | Music | — | — | — | — |
venice-elevenlabs-tts-multilingual-v2 ElevenLabs TTS Multilingual v2 (Venice audio) | Venice AI | Music | — | — | — | — |
venice-elevenlabs-tts-turbo-v2-5 ElevenLabs Turbo v2.5 TTS (Venice) | Venice AI | Text → audio | — | — | — | — |
venice-elevenlabs-tts-v3 ElevenLabs TTS v3 (Venice audio) | Venice AI | Music | — | — | — | — |
venice-embed-1 Venice Embeddings 1 | Venice AI | Embedding | — | — | — | — |
venice-flux-1.1 Flux 1.1 (Venice, legacy) | Venice AI | Image generation | — | — | — | — |
venice-flux-1.1-pro Flux 1.1 Pro (Venice, legacy) | Venice AI | Image generation | — | — | — | — |
venice-flux-2-max Flux 2 Max (Venice) | Venice AI | Image generation | — | — | — | — |
venice-flux-2-pro Flux 2 Pro (Venice) | Venice AI | Image generation | — | — | — | — |
venice-gpt-image-1.5 GPT Image 1.5 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-gpt-image-2 GPT Image 2 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-grok-imagine Grok Imagine (Venice) | Venice AI | Image generation | — | — | — | — |
venice-grok-imagine-pro Grok Imagine Pro (Venice) | Venice AI | Image generation | — | — | — | — |
venice-grok-imagine-quality Grok Imagine High Quality (Venice) | Venice AI | Image generation | — | — | — | — |
venice-hunyuan-image-v3 Hunyuan Image 3.0 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-imagineart-1.5-pro ImagineArt 1.5 Pro (Venice) | Venice AI | Image generation | — | — | — | — |
venice-kokoro-tts Kokoro Text to Speech (Venice) | Venice AI | Text → audio | — | — | — | — |
venice-lustify-sdxl Lustify SDXL (Venice) | Venice AI | Image generation | — | — | — | — |
venice-lustify-v7 Lustify v7 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-lustify-v8 Lustify v8 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-minimax-music-v2 MiniMax Music 2.0 (Venice) | Venice AI | Music | — | — | — | — |
venice-minimax-music-v25 MiniMax Music 2.5 (Venice) | Venice AI | Music | — | — | — | — |
venice-minimax-music-v26 MiniMax Music 2.6 (Venice) | Venice AI | Music | — | — | — | — |
venice-mmaudio-v2-text-to-audio MMAudio V2 Text-to-Audio (Venice) | Venice AI | Music | — | — | — | — |
venice-music-gen Venice Music Gen (legacy alias) | Venice AI | Music | — | — | — | — |
venice-nano-banana-2 Nano Banana 2 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-nano-banana-pro Nano Banana Pro (Venice) | Venice AI | Image generation | — | — | — | — |
venice-parakeet-asr Parakeet ASR (Venice) | Venice AI | Audio → text | — | — | — | — |
venice-pixverse-c1-t2v PixVerse C1 Text-to-Video (Venice) | Venice AI | Video | — | — | — | — |
venice-qwen-image Qwen Image (Venice) | Venice AI | Image generation | — | — | — | — |
venice-qwen-image-2 Qwen Image 2 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-qwen-image-2-pro Qwen Image 2 Pro (Venice) | Venice AI | Image generation | — | — | — | — |
venice-recraft-v4 Recraft V4 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-recraft-v4-pro Recraft V4 Pro (Venice) | Venice AI | Image generation | — | — | — | — |
venice-runway-gen4-5-text Runway Gen-4.5 Text-to-Video (Venice) | Venice AI | Video | — | — | — | — |
venice-sd35 Venice SD35 | Venice AI | Image generation | — | — | — | — |
venice-sdxl Stable Diffusion XL (Venice, legacy) | Venice AI | Image generation | — | — | — | — |
venice-seedance-2-fast-t2v Seedance 2.0 Fast Text-to-Video (Venice) | Venice AI | Video | — | — | — | — |
venice-seedream-v4 Seedream V4.5 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-seedream-v5-lite Seedream V5 Lite (Venice) | Venice AI | Image generation | — | — | — | — |
venice-stable-audio-25 Stable Audio 2.5 (Venice) | Venice AI | Music | — | — | — | — |
venice-tts-1 Venice TTS 1 (legacy alias) | Venice AI | Text → audio | — | — | — | — |
venice-video-gen Venice Video Gen (legacy alias) | Venice AI | Video | — | — | — | — |
venice-wai-illustrious Anime WAI (Venice) | Venice AI | Image generation | — | — | — | — |
venice-wan-2.7 Wan 2.7 (Venice) | Venice AI | Image generation | — | — | — | — |
venice-wan-2.7-pro Wan 2.7 Pro (Venice) | Venice AI | Image generation | — | — | — | — |
venice-whisper-1 Whisper 1 (Venice, legacy alias) | Venice AI | Audio → text | — | — | — | — |
venice-whisper-large-v3 Whisper Large V3 (Venice) | Venice AI | Audio → text | — | — | — | — |
venice-xai-stt-v1 xAI Speech to Text v1 (Venice) | Venice AI | Audio → text | — | — | — | — |
venice-z-image-turbo Z-Image Turbo (Venice) | Venice AI | Image generation | — | — | — | — |
All discovered endpoints
From /api/x402/info. Every endpoint accepts x402 challenges.
Inference (6)
POST/x402/api/inference/v1/chat/completions
OpenAI-compatible chat completions. Supports streaming and non-streaming responses.
POST/x402/api/inference/v1/completions
OpenAI-compatible legacy text completions.
POST/api/inference/v1/embeddings
OpenAI-compatible embeddings.
POST/api/inference/v1/images/generations
Image generation.
POST/api/inference/v1/audio/speech
Text-to-speech.
POST/api/inference/v1/audio/transcriptions
Speech-to-text transcription.
Resource (2)
GET/x402/api/twitter/v2/{...path}
Read-only X/Twitter API v2 proxy backed by seller-supplied app-only bearer tokens. Sellers configure a discount/multiplier vs Twitter API prices. Write/action endpoints are intentionally not supported.
POST/x402/api/venice/crypto/rpc/{network}
Venice crypto JSON-RPC proxy backed by seller-supplied Venice API keys. Sellers configure a proportion of Venice RPC prices.
Discovery surfaces
Crawled at build time, each fetch reported with real HTTP status. These are the files an agent reads to bootstrap against Surplus.
/.well-known/x402.jsonLIVE
OpenAI-compatible inference, Twitter/X API, and Venice crypto RPC marketplace with x402 pay-per-request access. Pricing is market-based; final amount is returned in each HTTP 402 challenge.
x402 version2
Resources7
Networkeip155:8453
/openapi.jsonLIVE
OpenAI-compatible inference marketplace with x402 pay-per-request access on Base.
Version3.1.0
Paths11
Schemas6
/llms.txtLIVE
Surplus Intelligence
Bytes12013
Sections10
Code samples9
Source fetches
Every URL this build fetched, with the actual HTTP status and bytes. No data on this page comes from anywhere else.
| URL | Status | HTTP | Bytes | Error |
|---|---|---|---|---|
| /api/x402/info | LIVE | 200 | 10K | |
| /x402/api/inference/v1/models | LIVE | 200 | 98K | |
| /api/inference/v1/prices | LIVE | 200 | 52K | |
| /api/resource/markets | LIVE | 200 | 633 | |
| DexScreener token pairs | LIVE | 200 | 18K | |
| /.well-known/x402.json | LIVE | 200 | 4K | |
| /openapi.json | LIVE | 200 | 23K | |
| /llms.txt | LIVE | 200 | 12K |