Speed First
The fastest agentic models
MiMo V2.5 Pro UltraSpeed peaks at 1,000 tokens/second. GLM 5.2 Fast runs at roughly twice standard throughput. Built for agents that cannot wait around.
Browse modelsThe fastest agentic AI models. One API.
Run DeepSeek, GLM and MiMo UltraSpeed through a single OpenAI-compatible endpoint, at cost + 10% with transparent pay-as-you-go pricing.
Works with Hermes Agent, OpenClaw, OpenCode and other OpenAI-compatible tools.
client.ts
Drop in1
2
3
4
5
6
7
8
9
// Before: your existing OpenAI client
const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY })
// After: point at gateway.fast, keep everything else
const client = new OpenAI({
apiKey: process.env.GATEWAY_API_KEY,
baseURL: "https://api.gateway.fast/v1"
})Direct Access
Choose your model
Call any model directly by name: DeepSeek V4 Flash and Pro, GLM 5.2 standard and Fast, MiMo V2.5 Pro UltraSpeed. Buy dollar packs, no subscriptions, full control.
Browse modelsCost + 10%
Transparent pass-through pricing
You pay exactly what the upstream provider charges plus a flat 10% — on every token class, including cache hits. No hidden margins, no rounding games.
See pricingDrop-in
OpenAI-compatible endpoint
Point your existing OpenAI client at https://api.gateway.fast/v1 and keep everything else. Streaming, tool calls, and structured output all work out of the box.
Read the docsLive models. Honest pricing.
Direct access to the current gateway.fast catalog, with separate cache-hit pricing where upstream providers report it.
DeepSeek V4 FlashCheapest
T1DeepSeek1 million
- $ In / 1M
- $0.154
- $ Out / 1M
- $0.308
- Cached input / 1M
- $0.0031
DeepSeek V4 Pro
T2DeepSeek1 million
- $ In / 1M
- $0.4785
- $ Out / 1M
- $0.957
- Cached input / 1M
- $0.004
GLM 5.2
T2Fireworks1 million
- $ In / 1M
- $1.54
- $ Out / 1M
- $4.84
- Cached input / 1M
- $0.154
GLM 5.2 FastFast router
T3Fireworks1 million
- $ In / 1M
- $2.31
- $ Out / 1M
- $7.26
- Cached input / 1M
- $0.231
MiMo V2.5 Pro UltraSpeedUltraSpeed
T3Xiaomi MiMo1 million
- $ In / 1M
- $1.5231
- $ Out / 1M
- $3.0462
- Cached input / 1M
- $0.0127
| Model | Provider | Tier | Context | $ In / 1M tokens | $ Cached in / 1M | $ Out / 1M tokens |
|---|---|---|---|---|---|---|
DeepSeek V4 FlashCheapest | DeepSeek | T1 | 1 million | $0.154 | $0.0031 | $0.308 |
DeepSeek V4 Pro | DeepSeek | T2 | 1 million | $0.4785 | $0.004 | $0.957 |
GLM 5.2 | Fireworks | T2 | 1 million | $1.54 | $0.154 | $4.84 |
GLM 5.2 FastFast router | Fireworks | T3 | 1 million | $2.31 | $0.231 | $7.26 |
MiMo V2.5 Pro UltraSpeedUltraSpeed | Xiaomi MiMo | T3 | 1 million | $1.5231 | $0.0127 | $3.0462 |
Simple pricing. No subscriptions.
Buy prepaid credit and spend it directly on tokens. No seats, no monthly commitment.
Starter
$10
For testing and small projects
Popular
Builder
$20
For active development
Scale
$50
For production workloads
Credits are metered in micro-dollars at the per-model rates above.
Add credit.
Start calling models.
Checkout creates your account, sends your API key, and opens the dashboard for usage and balance history.