The agent-native inference API
Built for agents. Priced for the world.
Fikra API is the first agent-native inference API: one OpenAI-compatible surface with pinned DeepSeek checkpoints, agent-assisted accounts for humans, x402 pay-per-call, MCP and A2A. Agents can create an account, get a key, top up, call models and read usage from a terminal, with no browser session and no formal UI.
We are the best in the world on fresh input and output price for the DeepSeek V4.1 Flash line among the global gateways we track, and we publish usage and status so you do not have to trust our word. The comparison is below, with sources.
TRACK 1
For humans
Create an account, generate a key, call the OpenAI-compatible API. Start with /authentication.
TRACK 2
Agents for humans
An agent creates a provisional account for a human, gets a 6-hour token, creates keys, tops up, and hands over a claim link. No signup credit.
TRACK 3
Agent-native
x402 pay-per-call, MCP, A2A, API keys, terminal-first flows, no browser and no UI required.
DeepSeek V4.1 Flash: global price comparison
USD per 1M tokens. Competitors are global gateways, not regional resellers. Fikra is the cheapest on fresh input and output in this set; on cache-heavy traffic some competitors have cheaper cached input. We publish both, because the rate card is the bill.
| Gateway | Fresh input | Cached input | Output | Note |
|---|---|---|---|---|
| Fikra API | $0.05 | $0.025 | $0.11 | Pinned 1017 build, 1M context |
| NanoGPT | $0.13 | $0.006 | $0.52 | Route-dependent for 1017 |
| OpenRouter | $0.056 | not listed | $0.12 | V4.1 Flash |
| DeepInfra | $0.14 | $0.004 | $0.42 | Promo pricing observed |
| Fireworks AI | $0.30 | $0.006 | $1.20 | Serverless |
| Together AI | $0.30 | $0.006 | $1.20 | Serverless |
| SiliconFlow | $0.15 | $0.003 | $0.60 | V4.1 Flash |
| Novita AI | $0.30 | not listed | $1.20 | V4.1 Flash |
Sources: each provider's public pricing or model page, checked 2026-10-24. Fikra figures from fikraapi.co.ke/pricing and the live /v1/models feed. Prices change; verify before routing volume.
Trust the platform, not just the page: usage and uptime and status.
Core Architecture & Compatibility
Our infrastructure is engineered to strictly adhere to the OpenAI v1 REST specification. You only need to update your base URL and authenticate with your Fikra API Key to achieve a 100% drop-in replacement for existing pipelines.
| Specification Parameter | Production Value | Implementation Detail |
|---|---|---|
| Base URL | https://api.fikraapi.co.ke/v1 | The global endpoint for all inference routing. |
| Authentication Scheme | Authorization: Bearer | Requires active `fk_live_...` key generation. |
| SDK Compatibility | OpenAI SDK v1.0+ | Native support for Python, Node.js, Go, and REST. |
The Engine Matrix
The Fikra engine matrix lists every chat model published on GET /v1/models.
This table is generated live from the model registry: it always matches the API.
Rates are USD per 1M tokens; every model includes automatic high-availability routing behind Fikra.
| Model | Best for | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| deepseek-v4.1-flash | $ 0.05 | $ 0.11 | 1,048,576 tok | |
| deepseek-v4.1-flash-1017 | The latest DeepSeek V4.1 Flash update (Oct 17 build): better reasoning, coding, agentic and | $ 0.05 | $ 0.11 | 1,048,576 tok |
| deepseek-v4-flash-0731 | $ 0.045 | $ 0.17 | 1,048,576 tok | |
| glm-5.3-flash | $ 0.155 | $ 0.49 | 327,680 tok | |
| kimi-k3 | $ 2.1 | $ 10.5 | 1,113,088 tok | |
| step-5-preview | $ 1.25 | $ 3.3 | 1,048,576 tok | |
| mimo-v2.6-pro | Xiaomi MiMo-V2.6-Pro: the top-scoring open-weight model on the Artificial Analysis index rig | $ 0.5 | $ 1.0 | 1,048,576 tok |
| glm-5.3 | Z.ai flagship GLM-5.3: large-scale reasoning for complex software engineering and long-horiz | $ 1.05 | $ 3.35 | 327,680 tok |
| gemini-4-argon | $ 2.5 | $ 12.0 | 1,048,576 tok | |
| nvidia-nemotron-3.5-super-vl | $ 0.5 | $ 1.25 | 1,048,576 tok | |
| qwen3.8-27b | Fast 27B-class multimodal model with automatic prompt caching. Pay $0.10/M on cached input. | $ 0.045 | $ 0.35 | 1,001,536 tok |
| glm-5.2 | Z.ai GLM-5.2 on a 1M context: strong coding and reasoning at a lower price than GLM-5.3. The | $ 0.75 | $ 1.65 | 262,144 tok |
| fikra-pro-20b | $ 0.2 | $ 0.2 | 131,072 tok | |
| fikra-pro-120b | $ 0.3 | $ 0.3 | 131,072 tok | |
| fikra-qwen-27b | $ 0.045 | $ 0.35 | 262,144 tok | |
| fikra-qwen-max | $ 6.0 | $ 12.0 | 1,048,576 tok | |
| fikra-auto | $ 0.045 | $ 0.35 | 262,144 tok | |
| fikra-auto-pro | $ 6.0 | $ 12.0 | 1,048,576 tok | |
| fikra-code-35b | $ 0.045 | $ 0.33 | 262,144 tok |
Speech and text utilities ship as separate endpoints:
fikra-embed
(embeddings, $0.05/1M tokens),
fikra-stt
(transcription, $0.001/min) and
fikra-tts
(speech, $25/1M characters).
Decoupled Production Scaling
Fikra API employs a Redis-backed Token Bucket algorithm to decouple consumer limits from upstream hardware thresholds. Your throughput capacity (RPM) scales securely based on your account tier, shielding you from backend rate limits.
| Account Tier | Request Limit | Access Condition |
|---|---|---|
| Unverified | 30 RPM · 300 req/day | Default free-evaluation state. Tokens: 100,000 TPM · 1,000,000 TPD. |
| Trusted | 3000 RPM · 250,000 req/day | Unlocked permanently on your first wallet top-up. Tokens: 0 TPM · 0 TPD. |
How do I send my first inference request?
Because we map exactly to the OpenAI spec, you do not need to learn a new library. Simply initialize the client with the Fikra base URL and your `fk_live_` key.