Claude "Does Not Support Assistant Message Prefill" 400 Fix
Claude 4.6 and later models reject any request that ends with an assistant turn; Sonnet 4.5 and Haiku 4.5 still accept one. Replace the prefill by its job.
13 min
API Guides · Page 2 of 3
Step-by-step AI API integration: getting and securing API keys, authentication, endpoints and SDKs, OpenAI-compatible setups, and patterns for production use.
- 62 articles
- Updated Oct 10, 2026
Gemini 3 Pro Image Free Tier: Paid API, Free Only in US AI Mode
Gemini 3 Pro Image (Nano Banana Pro) has no free API tier and no free Pro quota in the Gemini app. The one no-cost route is AI Mode in Search for US adults.
14 min
Gemini API Rate Limits 2026: Free vs Paid Tiers and How to Raise
Gemini API rate limits (RPM, TPM, RPD) apply per project, not per key, and your live numbers are in AI Studio. Tier 2 and Tier 3 unlock at $100 and $1,000 paid.
14 min
Gemini Image 429 Rate Limit: How Long It Lasts and How to Fix It
A Gemini image 429 is a per-minute limit (clears in a minute), a daily quota (resets midnight Pacific), a spend cap per 10 minutes, or a free-tier limit of 0.
13 min
Gemini Image API Guide: Python Code, 3 Current Models, Pricing
As of October 5, 2026, the Gemini image API runs on three models, from $0.0336 per image. Image output has no free tier: you need a paid key with $5 prepaid.
12 min
Gemini API Tier 3 (T3) Upgrade: $1,000 + 30 Days, Same API Key
Gemini API Tier 3 (T3) isn't a special key: the billing account upgrades itself after $1,000 in paid Google Cloud spend and 30 days from the first payment.
14 min
OpenAI API Error 429: Diagnose Rate Limits, Quota, and Spend Caps
An OpenAI API 429 can mean temporary throttling, depleted credits, or an enforced account limit. Read the error code before deciding whether to wait, change billing, or reduce traffic.
10 min
OpenAI API Auto Recharge Failed: Restore Access and Check the Cause
If OpenAI API auto recharge fails, restore the correct organization's balance, then check the payment attempt, saved settings, and monthly recharge cap. A successful manual top-up restores funds but does not prove automatic recharge is working.
9 min
Is There a Free AI Video API? What Works Without Paying
As of September 30, 2026, no major video model's API lists a free tier. Magic Hour and Tavus offer free trials; a 5-second Veo 3.1 Lite test costs $0.25.
12 min
Gemini 3.8 Flash TTS API: Model Choice, Cost, and Migration
Both Gemini 3.8 TTS models are GA with a free tier. Flash-Lite replaces 3.1 preview at about $0.54 per audio hour; Flash is $0.81 for studio-grade acting.
16 min
Free Gemini API Key for Students: What Is Free and What Isn't
No student-only Gemini API key exists; students get the same free tier as everyone. The Google AI Pro student year helps API work only after you enable billing.
15 min
OpenRouter Alternatives: Free Models, Fees, and When to Switch
OpenRouter's free models cap at 50 requests a day until a one-time $10 top-up; Vercel, Requesty, Cloudflare, LiteLLM, or direct free tiers each fix one problem.
16 min
Best Free AI API Provider: Pick by Limits, Data Use, and Region
Start with Gemini's free tier unless your prompts are private or you're outside its regions; add Groq or OpenRouter for headroom. As of September 26, 2026.
16 min
OpenAI Base URL Override: Which Setting Wins and What to Paste
In the official Python and Node SDKs, base_url beats OPENAI_BASE_URL and endpoint paths are appended to it, so paste the base ending in /v1, not an endpoint.
10 min
Qwen Image 2.1 Free API: ModelScope Token, Daily Cap, and Code
ModelScope runs a free Qwen-Image-2.1 API once you bind a real-name-verified Alibaba Cloud account. At 1 credit per call, that tops out near 250 calls a day.
12 min
Jev AI Model: What It Is, How It Compares, and How to Use It
Jev from TypeSafe AI returns a choice, score or yes-probability instead of text, for $0.042 per million input tokens. It suits narrow decisions, not writing.
19 min
OpenAI API Credits Expired: Can You Get Them Back?
Purchased OpenAI API credits expire one year after purchase and can't be extended. Refunds cover only billing errors, unauthorized use, or an OpenAI failure.
10 min
How to Get a ChatGPT API Key in 2026—and Prove It Actually Works
A ChatGPT subscription does not issue or fund an API key. The working route is OpenAI Platform: verify your region, create a project secret, activate API billing, load it on a server, and confirm both a Responses output and a Usage record.
6 min
Claude Mythos API Pricing: 5.1 Rates, Cache Costs, and Access
Mythos 5.1 is invitation-only. Its listed rates are $10 per million input tokens, $50 per million output tokens and $0.25 for cache reads. Compare versions and calculate costs.
7 min
Azure OpenAI TPM Rate Limits: Diagnose 429s Below Quota
Azure OpenAI can return 429 while billed token usage looks low. Compare the receiving deployment’s allocation with response headers, account for estimated tokens and request bursts, and verify recovery without hiding failures behind retries.
11 min
Claude Fable 5.1 vs Opus 5: Pricing and Cost per Task
Opus 5 costs half as much for uncached input and output. Fable 5.1 costs half as much for cache reads. Your workload and acceptance rate decide which total is lower.
6 min
GLM-5.3-Flash Guide: Ox Alpha, API Pricing, and Local Deployment
Start with the hosted API unless your GPUs can hold roughly 305.8 GiB of FP8 weights plus runtime and cache headroom. The 18B active-parameter figure is not a memory requirement.
5 min
LLM API Retry vs Fallback: Five Gates Before Another Model Call
Retry only when the failure is transient, the operation is safe to replay, and the workflow budget still fits. Switch only to a fallback that has already passed the same product contract.
7 min
Claude Mythos 5 API Access: Who Can Get It and What to Use Instead
A normal Claude API key does not unlock Mythos 5. This guide separates Preview migration, Glasswing approval, post-approval cloud delivery, and the public Fable 5 route.
7 min