> Openference API
OpenInference - open-source LLM relay with a single OpenAI-compatible endpoint (Anthropic-format root also available at https://api.openference.com/), API-key auth, automatic provider failover and a zero-data-retention option; free to start, paid plans from USD 1/mo; documented per-model on-demand USD/1M pricing on openference.com/models.
Value taken from the provider’s own published free-tier terms, expressed in USD.
note: Free plan: 3-day trial with open-source models — no credit card required
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier | free | — | — | — | Free tier (source-reported) |
| Pay-as-you-go | payg | — | Free | Free | Cheapest tracked model rate (OpenRouter-normalized). |
| Free (3-day trial) | free | — | — | — | 350 requests per week during the trial period. |
| Promo | subscription | $1.00/mo | — | — | USD 1/mo: 2-day trial of all models, then Qwen3.8 and Llama 3.2 only, 10 rpm. |
| Pro | subscription | $30.00/mo | — | — | USD 30/mo: 800 req/5h, 13,000 req/wk; Kimi included. |
| Pro+ | subscription | $45.00/mo | — | — | USD 45/mo: 1,200 req/5h, 19,500 req/wk. |
| Lite | subscription | $15.00/mo | — | — | USD 15/mo: 400 req/5h, 7,500 req/wk; excludes Kimi models. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| GLM-4.7-Flash | $0.060 | $0.400 | 203k |
| glm-5.3-flash | $0.150 | $0.500 | 1.3M |
| MiniMax-M3 | $0.300 | $1.20 | 1.0M |
| deepseek-v4-flash-0731 | $0.440 | $1.32 | 1.3M |
| DeepSeek V4 Flash Vision Exp | $0.440 | $1.32 | 1.0M |
| Qwen3.8 27B | $0.450 | $3.20 | 1M |
| Nemotron 3 Super | $0.500 | $1.50 | 262k |
| kimi-k2.6 | $0.950 | $4.00 | 262k |
| Kimi K2.7 Code | $0.950 | $4.00 | 262k |
| GLM 5 | $1.00 | $3.20 | 198k |
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 1.0M |
| glm-5.3 | $1.40 | $4.40 | 1.3M |
| GLM-5.1 | $1.40 | $4.40 | 205k |
| GLM 5.2 | $1.40 | $4.40 | 1.0M |
| kimi-k3 | $2.70 | $13.50 | 1.0M |
$ Does Openference API have a free tier?
Yes — Openference API offers a free tier that we value at roughly $5.00 in free credits. Always confirm current limits on Openference API's official pricing page — free tiers change without notice.
$ How much does Openference API cost per 1M tokens?
The cheapest model we track at Openference API is $0.060 per 1M input tokens and $0.400 per 1M output tokens. This is normalized from Openference API's published pricing — verify with the provider before purchasing, since prices change frequently.
$ Is Openference API safe to use?
Uprouter rates Openference API as medium risk. Third-party relay for upstream model APIs (unofficial channel); upstream ToS and data-handling considerations apply; ZDR option offered. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
current: unknownNo probes recorded yet.
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Third-party relay for upstream model APIs (unofficial channel); upstream ToS and data-handling considerations apply; ZDR option offered.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# Openference API's own API — get a key from their dashboard
curl https://api.openference.com/v1/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5-3",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.