Kimi K3 served on Fireworks' low-latency Fast router, trading a higher token price for faster generation.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Kimi K3 served on Fireworks' low-latency Fast router, trading a higher token price for faster generation. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Kimi K3 Fast on OffRail starts at $4.50 per million input tokens and $22.50 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Kimi K3 Fast supports a context window of up to 1,040,384 tokens on its largest provider deployment.
Kimi K3 Fast is served by Fireworks AI through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Kimi K3 Fast supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
Kimi K3 Fast was released on July 16, 2026.
Kimi K3
1,048,576 context$3.00 in / $15.00 out per 1M
Kimi K2.7 Code
262,144 context$0.95 in / $4.00 out per 1M
Kimi K2.7 Code Highspeed
262,144 context$1.90 in / $8.00 out per 1M
Kimi K2.6
262,144 context$0.22 in / $1.14 out per 1M
Kimi K2.5
262,144 context$0.40 in / $1.98 out per 1M
Kimi K2 Thinking
262,144 context$0.60 in / $2.50 out per 1M