Verified 2026-11-18 · rates follow the live catalog
Vercel AI Gateway sends requests to model providers at the provider's list price, with no markup and no platform fee on tokens. You buy AI Gateway Credits, set budgets per team, project, key or member, and pay extra only for opt-in add-ons such as team-wide zero-data-retention routing ($0.10 per 1,000 requests) or regional endpoints (5% of inference cost). Token Pass, in early access for Pro teams, adds $150 of credit for a short list of open-weight models for $30 per team per month. Openference is the choice when you want usage bundled into plans for individuals as well as teams.
Hosted gateway · Pay-as-you-go · Token Pass $30/team/mo · Checked 19 November 2026 against Vercel AI Gateway Pricing.
Pick Vercel if you already deploy there and want no-markup routing with budgets. Pick Openference for plans that bundle usage into one monthly price, for individuals and teams.
| Plan | Price | What it includes |
|---|---|---|
| Free tier | $0 | Free credit on every team account, covering a subset of models, with lower limits than the paid tier. |
| Pay-as-you-go | Provider list price | AI Gateway Credits at the provider's list price. No markup or platform fee on tokens; budgets included; add-ons such as regional endpoints cost extra. |
| Token Pass | $30/team/mo | $150 of monthly credit for featured open-weight models (Kimi K3, Kimi K3.1 Pro, GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash) at list price, with zero data retention. Unused credit expires each period. Early access, Pro teams only. |
| Vercel AI Gateway | Openference | |
|---|---|---|
| Pricing model | Pay-as-you-go credits; optional Token Pass ($30/team/mo for $150 of credit) | Plan-based (included usage) + on-demand credits |
| Fee on top of model rates | None on tokens; opt-in add-ons are priced separately | No per-request fee and no markup on listed rates; 5% processing fee on credit top-ups |
| Open-weight models | Yes | Yes |
| Proprietary frontier models | Yes | Yes |
| Automatic failover across providers | Yes — fallback model chains and provider retries | Yes |
| Who can subscribe | Token Pass needs a Pro team; Enterprise teams can't subscribe | Individual and Team plans |
On the 4 models both list, Vercel AI Gateway has the lower price for a typical request on 1 and Openference on 0; 3 models cost about the same. The widest gap in Vercel AI Gateway's favour is DeepSeek V4.1 Flash (50% lower).
| Model | Vercel AI Gateway per 1M (in / out) | Openference per 1M (in / out) | Vercel AI Gateway, one request | Openference, one request | Lower price |
|---|---|---|---|---|---|
| Kimi K3 | $3 / $15 | $3 / $15 | $0.075 | $0.075 | About the same |
| GLM-5.3 | $1.40 / $4.40 | $1.40 / $4.40 | $0.032 | $0.032 | About the same |
| GLM-5.3-Flash | $0.15 / $0.50 | $0.15 / $0.50 | $0.0035 | $0.0035 | About the same |
| DeepSeek V4.1 Flash | $0.15 / $0.60 | $0.30 / $1.20 | $0.0036 | $0.0072 | Vercel AI Gateway, 50% lower |
A request here is a 20,000-token prompt answered with 1,000 tokens, with no prompt caching. Vercel AI Gateway's rates are as published on Vercel Token Pass, read 19 November 2026. Openference's are read from the live catalog at the highest rate of the day, so a model with a scheduled off-peak discount costs less at other hours than shown. Prices on both sides change; check the sources before you commit.
Pay-as-you-go · Token Pass $30/team/mo. The plan table above lists each tier as Vercel AI Gateway publishes it, read from Vercel AI Gateway Pricing on 19 November 2026.
On the 4 models both list, Vercel AI Gateway has the lower price for a typical request on 1 and Openference on 0; 3 models cost about the same. The table above shows each model; which side is cheaper overall depends on which models you actually run.
Vercel AI Gateway's from its own pages on 19 November 2026; Openference's from its live catalog and public plans. Both change, so confirm on the linked page before you commit.
More on the comparison index, the current plans and the model catalog.
Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API