1endpoint
Console

Every model. Every harness.

One API that speaks OpenAI and Anthropic natively — drop it into any compatible harness without rewriting a client.

Base URL

/api/v1/chat/completions

Start building How it works
  • Prompt Caching
  • Spend Tracking
  • Never Downgraded

From $0.0294 / 1M1,000 credits = $1

jev-1.14$0.0294USD per 1M input tokensqwen3.8-flash$0.0300USD per 1M input tokensglm-5.3-flash$0.0345USD per 1M input tokensgpt-6-luna$0.0350USD per 1M input tokensgpt-5.6-luna$0.0400USD per 1M input tokensdeepseek-v4.1-flash-1017$0.0525USD per 1M input tokensminimax-m3.1-flash$0.0525USD per 1M input tokensdeepseek-v4-flash-0731$0.0550USD per 1M input tokensminimax-m3$0.0600USD per 1M input tokensmimo-v2.6-flash$0.0630USD per 1M input tokensglm-5.3$0.0630USD per 1M input tokensdeepseek-v4-pro-0813$0.0660USD per 1M input tokensgemini-3.8-flash$0.0750USD per 1M input tokensqwen3.8-omni-flash$0.0750USD per 1M input tokensgpt-6.1-terra$0.1000USD per 1M input tokenstext-embedding-3-large$0.1300USD per 1M input tokensgpt-5.6-terra$0.1600USD per 1M input tokensmimo-v2.6-pro$0.1740USD per 1M input tokensgemini-4-argon$0.2000USD per 1M input tokensgpt-6-sol$0.2000USD per 1M input tokensgpt-6.1-sol$0.2000USD per 1M input tokensgrok-4.6$0.2000USD per 1M input tokensgrok-4.7$0.2000USD per 1M input tokenskimi-k3.1-pro$0.2000USD per 1M input tokensqwen3.8-max-0902$0.2000USD per 1M input tokenskimi-k3$0.2400USD per 1M input tokensgpt-5.6-sol$0.2500USD per 1M input tokensgpt-6-astra$0.3000USD per 1M input tokens
867.8Mtokens routed in the last 24 hours
6,716API requests in the last 24 hours
Referral rewardsEarn 10% in credits whenever someone you refer tops up.
01Model catalog

Compare the numbers.

Input, cached input, and output are priced independently. No blended platform fee hidden in the rate.

USD per 1M tokens
Relative
Jev 1.14 (TypeSafe)0.02940.00000.00000.00882
Qwen 3.8 Flash0.03000.00320.09400.03474
GLM 5.3 Flash0.03450.00690.11500.04393
GPT-6 Luna0.03500.00350.17500.0567
GPT 5.6 Luna0.04000.00400.24000.0748

Blended assumes 70% of input served from cache and output equal to 25% of input volume — a reference mix for comparison only, not a billed rate. The gateway records usage after a successful response; rates shown are the currently configured rates.

02Compatible by design

Change one base URL.

Keep the request shape your application already understands. Change the model ID when the workload changes.

Gateway base URL
1endpointone base URL
  • Chat CompletionsPOST /chat/completions
  • ResponsesPOST /responses
  • MessagesPOST /messages
03Rate anatomy

Cache decides the bill.

In this illustration, message 12 costs 5.5× less than without cache, assuming all previous input is a cache hit.

Cost per message as the conversation growsUSD per 1,000 requests
estimated costsaved by cache
message 1$1.20
message 12$2.41
without cache: $13.30

$2.41instead of $13.30 without cache. The first message has nothing cached yet, so it is billed in full.

Illustration only, using hypothetical rates per 1M tokens: $0.1000 input, $0.0100 cached input and $0.2000 output. Each of 12 requests adds 10,000 input and 1,000 output tokens, assuming all prior messages are cached. Amounts are per 1,000 equivalent requests. Actual model rates and cache usage vary.

Spend less on every token.

Pay only for what you use. Input starts at $0.0294 per 1M tokens — lower cache rates are applied automatically, per model.

Get an API key Quick setup

Usage-based pricing · 1,000 credits = $1