Token Index & Prices
CCIR Vercel Volume Token Index (VVTI)
Construction & source
VVTI is the volume-weighted average of posted output-token prices: Vercel AI Gateway daily token shares (“AI Gateway Leaderboard Data”, CC BY 4.0) multiplied by the posted first-party prices recorded on this page, renormalized daily over the priced set. 58–89% of gateway volume is priced across the window; the remainder sits in the leaderboard’s own “Other” bucket. CCIR calculation; Vercel publishes shares only. Weights re-fix daily with the gateway's published shares: composition change is part of what the index measures.
Each day is requested from the leaderboard on its own and priced against the posted record for that same day. Only complete days are requested, so the series runs to the previous day.
The leaderboard names the models carrying the largest share of that day’s traffic and buckets the rest as “Other”. A named model joins the priced set on any day its first-party price is on the record. Coverage states the priced share on every day.
Rows carrying an n are served medians across that many providers. The rest are the model owners' posted prices. Two constructions, never pooled.
Frontier posted — first-party
from the owners' price listsOpenAIstandard tier
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| gpt-6-astra | $10.00 | $1.00 | $50.00 | none in record | |
| gpt-6-sol | $2.00 | $0.20 | $10.00 | none in record | |
| gpt-6-luna | $0.10 | $0.01 | $0.50 | none in record | |
| gpt-5.6-terra | $2.00 | $0.20 | $12.00 | 2026-07-30 (-20%) | |
| gpt-5.5 | $5.00 | $0.50 | $30.00 | none in record | |
| gpt-5.5-pro | $30.00 | — | $180.00 | none in record | |
| gpt-5.4-mini | $0.75 | $0.07 | $4.50 | none in record | |
| gpt-5.4-nano | $0.20 | $0.02 | $1.25 | none in record | |
| gpt-4o | $2.50 | $1.25 | $10.00 | none in record | |
| gpt-4o-mini | $0.15 | $0.07 | $0.60 | none in record | |
| o3-pro | $20.00 | — | $80.00 | none in record | |
| o3 | $2.00 | $0.50 | $8.00 | none in record | |
| o4-mini | $1.10 | $0.28 | $4.40 | none in record | |
| gpt-4-turbo-2024-04-09 | $10.00 | — | $30.00 | none in record | |
| gpt-3.5-turbo-instruct | $1.50 | — | $2.00 | none in record |
Anthropicmodel table
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| Claude Fable 5.1 | $10.00 | $0.25 | $50.00 | none in record | |
| Claude Mythos 5.1 | $10.00 | $0.25 | $50.00 | none in record | |
| Claude Opus 5.5 | $4.00 | $0.20 | $20.00 | none in record | |
| Claude Sonnet 5 | $2.00 | $0.20 | $10.00 | none in record | |
| Claude Haiku 4.5 | $1.00 | $0.10 | $5.00 | none in record |
Googlestandard tier
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| gemini-3.8-flash | $0.75 | $0.07 | $3.75 | none in record | |
| gemini-3.8-live | $0.75 | — | $4.50 | none in record | |
| gemini-3.5-transcribe-live | $3.50 | — | $21.00 | none in record | |
| gemini-3.5-transcribe | $2.00 | — | $12.00 | none in record | |
| gemini-3.5-flash-lite | $0.30 | $0.03 | $2.50 | none in record | |
| gemini-3.1-pro-preview | $2.00 | $0.20 | $12.00 | none in record | |
| gemini-3-flash-preview | $0.50 | $0.05 | $3.00 | none in record | |
| gemini-2.5-pro | $1.25 | $0.13 | $10.00 | none in record | |
| gemini-robotics-er-2 | $1.00 | $0.10 | $5.00 | 2026-09-09 (-50%) | |
| gemini-robotics-er-2-streaming | $1.00 | — | $5.00 | 2026-09-09 (-50%) | |
| gemini-2.5-computer-use-preview-10-2025 | $1.25 | — | $10.00 | none in record |
DeepSeekstandard price
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| deepseek-flash | $0.30 | $0.01 | $1.20 | none in record | |
| deepseek-v4-pro | $1.32 | $0.04 | $3.96 | 2026-08-17 (355%) |
Moonshotper-model pages
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| kimi-k3 | $3.00 | $0.30 | $15.00 | none in record | |
| kimi-k2.7-code | $0.95 | $0.19 | $4.00 | none in record | |
| kimi-k2.7-code-highspeed | $1.90 | $0.38 | $8.00 | none in record |
xAImodel catalog
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| grok-build-0.1 | $1.00 | $0.20 | $2.00 | none in record | |
| grok-4.20-0309-reasoning | $1.25 | $0.20 | $2.50 | none in record | |
| grok-4.20-0309-non-reasoning | $1.25 | $0.20 | $2.50 | none in record | |
| grok-4.7 | $2.00 | $0.50 | $6.00 | none in record | |
| grok-4.20-multi-agent-0309 | $1.25 | $0.20 | $2.50 | none in record |
Metastandard tier
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| muse-spark-1.3 | $1.25 | $0.15 | $4.25 | none in record | |
| muse-spark-1.3-contributor | $0.10 | $0.00 | $0.20 | none in record |
Alibabainternational storefront
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| qwen3.8-max | $2.00 | — | $6.00 | none in record | |
| qwen3.7-max-preview | $2.50 | — | $7.50 | none in record | |
| qwen3.7-plus | $0.40 | — | $1.60 | none in record | |
| qwen-plus-latest | $0.40 | — | $1.20 | none in record | |
| qwen-turbo | $0.05 | — | $0.20 | none in record |
Z.AImodel table
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| GLM-5.3-Flash | $0.15 | $0.03 | $0.50 | 2026-09-10 (100%) | |
| GLM-5.3-FlashX | $0.37 | $0.07 | $1.25 | none in record | |
| GLM-5.3 | $1.40 | $0.26 | $4.40 | none in record | |
| GLM-4.5-X | $2.20 | $0.45 | $8.90 | none in record | |
| GLM-4.5-Air | $0.20 | $0.03 | $1.10 | none in record | |
| GLM-4.5-AirX | $1.10 | $0.22 | $4.50 | none in record | |
| GLM-4-32B-0414-128K | $0.10 | — | $0.10 | none in record | |
| GLM-4.6V | $0.30 | $0.05 | $0.90 | none in record | |
| GLM-OCR | $0.03 | — | $0.03 | none in record | |
| GLM-4.6V-FlashX | $0.04 | $0.00 | $0.40 | none in record |
MiniMaxstandard tier
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| MiniMax-M3 | $0.30 | $0.06 | $1.20 | none in record | |
| MiniMax-M2.7-highspeed | $0.60 | $0.06 | $2.40 | none in record |
MistralAPI price list
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| mistral medium 3.5 | $1.50 | — | $7.50 | none in record | |
| mistral small 4 | $0.15 | — | $0.60 | none in record | |
| mistral large 3 | $0.50 | — | $1.50 | none in record | |
| codestral | $0.30 | — | $0.90 | none in record | |
| ministral 3 14b | $0.20 | — | $0.20 | none in record |
Thinking Machinesserverless inference
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| Inkling-Small | $0.30 | $0.06 | $1.20 | none in record | |
| Inkling | $1.00 | $0.17 | $4.05 | none in record |
Xiaomioverseas price list
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| mimo-v2.6-pro | $0.43 | $0.00 | $0.87 | none in record | |
| mimo-v2.6-flash | $0.14 | $0.00 | $0.28 | none in record | |
| mimo-v2.6-pro-ultraspeed | $4.35 | $0.04 | $8.70 | none in record |
stepfun
| Model | Input | Cached | Output | 30d | Last reprice |
|---|---|---|---|---|---|
| step-5-preview | $1.04 | $0.05 | $2.98 | none in record | |
| step-3.7-flash | $0.20 | $0.04 | $1.21 | none in record | |
| step-1o-turbo-vision | $0.37 | $0.07 | $1.19 | none in record |
Scope
Standard self-serve rates, the price a buyer pays without a contract. Batch, provisioned-throughput and committed-spend tiers are separate prices and are not pooled into these figures, so a large buyer's realized rate sits below them. Cached input is shown wherever the owner posts it.
One vendor, one day, three tiers: on 2026-07-30 the posted output price fell 80% on luna and 20% on terra while sol held.
Open-weight models — by serving breadth
cross-provider medians · n ≥ 3 · 2026-09-27| Model | Providers | Input median | Output median | Output range |
|---|---|---|---|---|
| gpt-oss-120b | 9 | $0.15 | $0.60 | $0.17 – $0.75 |
| MiniMax M3 | 8 | $0.30 | $1.20 | $0.96 – $2.40 |
| DeepSeek V4-Pro | 7 | $1.32 | $3.20 | $1.20 – $3.96 |
| GLM-5 | 7 | $1.00 | $3.20 | $2.08 – $3.20 |
| Llama 3.3 70B (FP8) | 7 | $0.71 | $0.71 | $0.40 – $1.04 |
| DeepSeek-V3.2 | 6 | $0.57 | $1.68 | $0.38 – $4.50 |
| Kimi K3 | 6 | $3.00 | $15.00 | $14.25 – $15.00 |
| GLM-5.2 | 6 | $1.40 | $4.40 | $2.40 – $4.40 |
| Kimi K2 Thinking | 6 | $0.60 | $2.50 | $2.00 – $2.50 |
| DeepSeek V3.1 | 6 | $0.57 | $1.68 | $0.95 – $4.94 |
| MiniMax-M2 | 6 | $0.30 | $1.20 | $1.02 – $1.20 |
| DeepSeek V4-Flash-0731 | 6 | $0.18 | $0.47 | $0.18 – $1.32 |
| DeepSeek V4-Flash | 6 | $0.14 | $0.28 | $0.18 – $0.51 |
| gpt-oss-20b | 6 | $0.06 | $0.23 | $0.14 – $0.50 |
| Deepseek R1 | 5 | $1.35 | $5.40 | $2.40 – $5.40 |
| GLM-5.3 | 5 | $1.40 | $4.40 | $4.00 – $4.40 |
Each row is a median across independent providers of the same model, n disclosed. A wide range is dispersion in the serving market.
Some models sit in both sections: the owner posts a price and independent providers also serve the open weights. The two numbers are different measurements, not a restatement. deepseek-v4-pro is posted at $3.96 per 1M output tokens above, and the median of independent providers here is $3.20. What a model owner asks and what the serving market charges are separate facts, and neither is pooled into the other.
Method
- USD per 1 million tokens, as posted. Record runs from 2026-07-03.
- Posted rows come from the model owners' own price lists, captured daily; a reprice appears on the day the list changed.
- Served rows are medians across independent providers of the same open-weight model, published at n ≥ 3.
- The two are never pooled. A posted price and a cross-provider median answer different questions.
- The VVTI weights each posted output price by its model’s daily share of Vercel AI Gateway token volume (CC BY 4.0, attributed above), renormalized over the priced set with coverage disclosed.
- Token prices are not evidence about GPU rental rates. The link between them is serving efficiency, a vendor variable rather than a market price. CCIR publishes the GPU-hour record separately.