GLM 5.1
z-ai/glm-5.1203k context Compare →- MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $1.96
- Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $2.15
- Offers
- 70
- Providers
- 36
Cheapest right now
Chutes
The provider's published policy: prompts are not used for training.$1.40 blended / 1M tokens
-2.1%7D- in
- $0.90
- out
- $2.90
- Cached input
- $0.09
Public leaderboards
- Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control). #43 of 419Best rank in the source's rank spread, 43rd to 63rd, given the confidence intervals of all ranked models. 54th by score. 1,465 1,462 to 1,469Arena Score · 66,771 votes
- Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #56 of 152Best rank in the source's rank spread, 56th to 66th, given the confidence intervals of all ranked models. 63rd by score. 1,508 1,501 to 1,515Arena Score · 10,647 votes
Source: Arena (opens in a new tab) · Data under the CC BY 4.0 license (creativecommons.org/licenses/by/4.0) · CC BY 4.0 (opens in a new tab) · scores and ranks as published on 28 Oct 2026; the presentation is ours
GLM 5.1 costs from $1.40 per million tokens (at a 3:1 input:output mix): the cheapest of 21 comparable offers, at Chutes, checked on ; 70 offers are listed.
Listed offers, by price
Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.Official list priceOffers not counted in cheapest, median or most expensive (49)
- $1.15 · NanoGPT via NanoGPT · cannot be designated the cheapest
- $1.30 · Avian · cannot be designated the cheapest
- $1.38 · Baidu via OpenRouter · cannot be designated the cheapest
- $1.40 · Alibaba via Eden AI · cannot be designated the cheapest
- $1.40 · Chutes via Kilo Gateway · cannot be designated the cheapest
- $1.40 · Chutes via OpenRouter · another route of the same provider
- $1.48 · Glama via Glama · cannot be designated the cheapest
- $1.48 · Martian via Martian · cannot be designated the cheapest
- $1.58 · UCloud · cannot be designated the cheapest
- $1.58 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
- $1.66 · DeepInfra via Eden AI · cannot be designated the cheapest
- $1.66 · FastRouter via FastRouter · cannot be designated the cheapest
- $1.66 · DeepInfra via LLM Gateway · cannot be designated the cheapest
- $1.66 · DeepInfra via Requesty · another route of the same provider
- $1.83 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
- $1.94 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
- $1.94 · AtlasCloud via OpenRouter · another route of the same provider
- $1.96 · Phala via Kilo Gateway · cannot be designated the cheapest
- $2.04 · Alibaba via Kilo Gateway · cannot be designated the cheapest
- $2.13 · Cortecs via Cortecs · cannot be designated the cheapest
- $2.14 · Novita via Kilo Gateway · cannot be designated the cheapest
- $2.14 · Novita via Vercel AI Gateway · another route of the same provider
- $2.14 · Novita via LLM Gateway · another route of the same provider
- $2.14 · Novita via Requesty · another route of the same provider
- $2.14 · Novita via OpenRouter · another route of the same provider
- $2.15 · Arkanecloud via Eden AI · cannot be designated the cheapest
- $2.15 · Baidu via Kilo Gateway · cannot be designated the cheapest
- $2.15 · Friendli via Kilo Gateway · cannot be designated the cheapest
- $2.15 · GMICloud via Kilo Gateway · cannot be designated the cheapest
- $2.15 · Nebius via Eden AI · cannot be designated the cheapest
- $2.15 · Nebius via Kilo Gateway · cannot be designated the cheapest
- $2.15 · StreamLake via Kilo Gateway · cannot be designated the cheapest
- $2.15 · TensorX via Eden AI · cannot be designated the cheapest
- $2.15 · Z.AI via Eden AI · cannot be designated the cheapest
- $2.15 · Z.AI via Kilo Gateway · cannot be designated the cheapest
- $2.15 · Z.AI via LLM API · cannot be designated the cheapest
- $2.15 · Nous Portal via Nous Portal · cannot be designated the cheapest
- $2.15 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
- $2.15 · Baidu via LLM Gateway · cannot be designated the cheapest
- $2.15 · Z.AI via LLM Gateway · another route of the same provider
- $2.15 · Nebius via LLM Gateway · cannot be designated the cheapest
- $2.15 · Together via LLM Gateway · cannot be designated the cheapest
- $2.15 · Z.AI via Requesty · another route of the same provider
- $2.15 · Friendli via OpenRouter · another route of the same provider
- $2.15 · Nebius via OpenRouter · another route of the same provider
- $2.15 · Z.AI via OpenRouter · another route of the same provider
- $2.15 · io.net · cannot be designated the cheapest
- $2.37 · Venice · another route of the same provider
- $2.37 · Venice via Kilo Gateway · cannot be designated the cheapest
Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-25 | $1.43, Embercloud | $1.58 |
| 2026-10-26 | $1.43, Embercloud | $1.58 |
| 2026-10-27 | $1.40, Chutes | $1.58 |
| 2026-10-28 | $1.40, Chutes | $1.58 |
| 2026-10-29 | $1.40, Chutes | $1.58 |
| 2026-10-30 | $1.40, Chutes | $1.58 |
| 2026-10-31 | $1.40, Chutes | $1.58 |
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-02 | $1.21, NanoGPT | $1.58 |
| 2026-10-03 | $1.21, NanoGPT | $1.58 |
| 2026-10-04 | $1.21, NanoGPT | $1.58 |
| 2026-10-05 | $1.21, NanoGPT | $1.58 |
| 2026-10-06 | $1.21, NanoGPT | $1.58 |
| 2026-10-07 | $1.21, NanoGPT | $1.58 |
| 2026-10-08 | $1.21, NanoGPT | $1.58 |
| 2026-10-09 | $1.21, NanoGPT | $1.58 |
| 2026-10-10 | $1.21, NanoGPT | $1.58 |
| 2026-10-11 | $1.21, NanoGPT | $1.58 |
| 2026-10-12 | $1.21, NanoGPT | $1.58 |
| 2026-10-13 | $1.15, NanoGPT | $1.58 |
| 2026-10-14 | $1.15, NanoGPT | $1.58 |
| 2026-10-15 | $1.15, NanoGPT | $1.58 |
| 2026-10-16 | $1.15, NanoGPT | $1.58 |
| 2026-10-17 | $1.15, NanoGPT | $1.58 |
| 2026-10-18 | $1.15, NanoGPT | $1.58 |
| 2026-10-19 | $1.30, Avian | $1.58 |
| 2026-10-20 | $1.30, Avian | $1.58 |
| 2026-10-21 | $1.30, Avian | $1.58 |
| 2026-10-22 | $1.43, Embercloud | $1.58 |
| 2026-10-23 | $1.43, Embercloud | $1.58 |
| 2026-10-24 | $1.43, Embercloud | $1.58 |
| 2026-10-25 | $1.43, Embercloud | $1.58 |
| 2026-10-26 | $1.43, Embercloud | $1.58 |
| 2026-10-27 | $1.40, Chutes | $1.58 |
| 2026-10-28 | $1.40, Chutes | $1.58 |
| 2026-10-29 | $1.40, Chutes | $1.58 |
| 2026-10-30 | $1.40, Chutes | $1.58 |
| 2026-10-31 | $1.40, Chutes | $1.58 |
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-10-01 | $1.21, NanoGPT | $1.58 |
| 2026-10-02 | $1.21, NanoGPT | $1.58 |
| 2026-10-03 | $1.21, NanoGPT | $1.58 |
| 2026-10-04 | $1.21, NanoGPT | $1.58 |
| 2026-10-05 | $1.21, NanoGPT | $1.58 |
| 2026-10-06 | $1.21, NanoGPT | $1.58 |
| 2026-10-07 | $1.21, NanoGPT | $1.58 |
| 2026-10-08 | $1.21, NanoGPT | $1.58 |
| 2026-10-09 | $1.21, NanoGPT | $1.58 |
| 2026-10-10 | $1.21, NanoGPT | $1.58 |
| 2026-10-11 | $1.21, NanoGPT | $1.58 |
| 2026-10-12 | $1.21, NanoGPT | $1.58 |
| 2026-10-13 | $1.15, NanoGPT | $1.58 |
| 2026-10-14 | $1.15, NanoGPT | $1.58 |
| 2026-10-15 | $1.15, NanoGPT | $1.58 |
| 2026-10-16 | $1.15, NanoGPT | $1.58 |
| 2026-10-17 | $1.15, NanoGPT | $1.58 |
| 2026-10-18 | $1.15, NanoGPT | $1.58 |
| 2026-10-19 | $1.30, Avian | $1.58 |
| 2026-10-20 | $1.30, Avian | $1.58 |
| 2026-10-21 | $1.30, Avian | $1.58 |
| 2026-10-22 | $1.43, Embercloud | $1.58 |
| 2026-10-23 | $1.43, Embercloud | $1.58 |
| 2026-10-24 | $1.43, Embercloud | $1.58 |
| 2026-10-25 | $1.43, Embercloud | $1.58 |
| 2026-10-26 | $1.43, Embercloud | $1.58 |
| 2026-10-27 | $1.40, Chutes | $1.58 |
| 2026-10-28 | $1.40, Chutes | $1.58 |
| 2026-10-29 | $1.40, Chutes | $1.58 |
| 2026-10-30 | $1.40, Chutes | $1.58 |
| 2026-10-31 | $1.40, Chutes | $1.58 |
Cheapest offerOfficial list price
| Rank | Provider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it. | Input $/1M | Output $/1M | Blended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix. | PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. | ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. | ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown. | Signals | Offer |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 0.70 | 2.50 | 1.15 | – | 200k | Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists | |||
| 2 | 0.743 | 2.97 | 1.30 | – | 203k | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | |||
| 3 | 0.899 | 2.82 | promo: Promotion announced by OpenRouter · −36% vs its usual price · end date not published1.38 | fp8 | 203k | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included. | |||
| 4 | 0.91 | 2.86 | 1.40 | fp8 | 203k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 5 | 0.90 | 2.90 | 1.40 | fp8 | 203k | ||||
| 6 | 0.90 | 2.90 | 1.40 | fp8 | 203k | Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest | |||
| 7 | 0.90 | 2.90 | 1.40 | fp8 | 203k | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included. | |||
| 8 | 0.966 | 3.04 | 1.48 | – | 200k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 9 | 0.966 | 3.04 | 1.48 | – | – | worldwide | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | ||
| 10 | 0.966 | 3.04 | 1.48 | fp8 | 200k | Price drop observed: The blended price is 31% lower than before this drop; possibly temporary. · Discount shown by the seller, no end date announced, seen on Oct 30, 2026Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included. | |||
| 11 | 0.878 | 3.51 | 1.54 | – | 200k | prompt up to 32K (31,999) tokens: up to 32K (31,999): $0.878 / $3.51; above that: $1.17 / $4.10 (Input / Output, per million tokens) | |||
| 12 | 0.902 | 3.61 | 1.58 | – | 200k | prompt up to 32K tokens: up to 32K: $0.902 / $3.61; above that: $1.20 / $4.21 (Input / Output, per million tokens) | |||
| 13 | 0.902 | 3.61 | 1.58 | – | – | prompt up to 32K (31,999) tokens: up to 32K (31,999): $0.902 / $3.61; above that: $1.20 / $4.21 (Input / Output, per million tokens) | |||
| 14 | 0.902 | 3.61 | 1.58 | – | – | Unverified. No public page for this offer: listed, not designated cheapestprompt up to 32K tokens: up to 32K: $0.902 / $3.61; up to 200K: $1.20 / $4.21 (Input / Output, per million tokens) | |||
| 15 | 0.902 | 3.61 | 1.58 | – | 200k | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 16 | 1.05 | 3.50 | 1.66 | fp4 | 203k | United States | Unverified. No public page for this offer: listed, not designated cheapest | ||
| 17 | 1.05 | 3.50 | 1.66 | – | 203k | United States | |||
| 18 | 1.05 | 3.50 | 1.66 | – | 203k | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | |||
| 19 | 1.05 | 3.50 | 1.66 | fp4 | – | United States | Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included. | ||
| 20 | 1.05 | 3.50 | 1.66 | fp4 | 203k | United States | Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included. | ||
| 21 | 1.19 | 3.74 | 1.83 | fp8 | 205k | Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest | |||
| 22 | 1.19 | 3.74 | 1.83 | fp8 | 205k | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included. | |||
| 23 | 1.26 | 3.96 | 1.94 | fp8 | 203k | ||||
| 24 | 1.26 | 3.96 | 1.94 | fp8 | 203k | Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest | |||
| 25 | 1.26 | 3.96 | 1.94 | fp8 | 203k | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included. |
No training on promptsPrompts may be used for trainingTraining terms not published
backend not named. The router bills this price itself without naming who serves the model.
-
$1.15NanoGPT
NanoGPT
- in
- $0.70
- out
- $2.50
- Precision
- –
- Context
- 200k
No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer exists
-
$1.30Avian
direct
- in
- $0.743
- out
- $2.97
- Precision
- –
- Context
- 203k
No training on promptsUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
-
promo: Promotion announced by OpenRouter · −36% vs its usual price · end date not published$1.38Baidu
OpenRouter
- in
- $0.899
- out
- $2.82
- Precision
- fp8
- Context
- 203k
Training terms not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
-
$1.40Alibaba
Eden AI
- in
- $0.91
- out
- $2.86
- Precision
- fp8
- Context
- 203k
Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest
Seller's site: Eden AI (opens in a new tab)No public price page for this model -
$1.40Chutes
direct
- in
- $0.90
- out
- $2.90
- Precision
- fp8
- Context
- 203k
No training on prompts
-
$1.40Chutes
Kilo Gateway
- in
- $0.90
- out
- $2.90
- Precision
- fp8
- Context
- 203k
Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway -
$1.40Chutes
OpenRouter
- in
- $0.90
- out
- $2.90
- Precision
- fp8
- Context
- 203k
No training on promptsFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
-
$1.48Glama
Glama
- in
- $0.966
- out
- $3.04
- Precision
- –
- Context
- 200k
No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
Seller's site: Glama (opens in a new tab)No public price page for this model -
$1.48Martian
Martian
- in
- $0.966
- out
- $3.04
- Precision
- –
- Context
- –
Training terms not publishedworldwideUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
-
$1.48StreamLake
OpenRouter
- in
- $0.966
- out
- $3.04
- Precision
- fp8
- Context
- 200k
Training terms not publishedPrice drop observed: The blended price is 31% lower than before this drop; possibly temporary. · Discount shown by the seller, no end date announced, seen on Oct 30, 2026Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
-
$1.54ZenMux
ZenMux
- in
- $0.878
- out
- $3.51
- Precision
- –
- Context
- 200k
Prompts may be used for trainingprompt up to 32K (31,999) tokens: up to 32K (31,999): $0.878 / $3.51; above that: $1.17 / $4.10 (Input / Output, per million tokens)
-
$1.58Qiniu
direct
- in
- $0.902
- out
- $3.61
- Precision
- –
- Context
- 200k
Training terms not publishedprompt up to 32K tokens: up to 32K: $0.902 / $3.61; above that: $1.20 / $4.21 (Input / Output, per million tokens)
-
$1.58Zhipu AI
Zhipu AI
- in
- $0.902
- out
- $3.61
- Precision
- –
- Context
- –
Prompts may be used for trainingprompt up to 32K (31,999) tokens: up to 32K (31,999): $0.902 / $3.61; above that: $1.20 / $4.21 (Input / Output, per million tokens)
-
$1.58UCloud
direct
- in
- $0.902
- out
- $3.61
- Precision
- –
- Context
- –
Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapestprompt up to 32K tokens: up to 32K: $0.902 / $3.61; up to 200K: $1.20 / $4.21 (Input / Output, per million tokens)
Seller's site: UCloud (opens in a new tab)No public price page for this model -
$1.58ShengSuanYun
ShengSuanYun
- in
- $0.902
- out
- $3.61
- Precision
- –
- Context
- 200k
Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapest
Seller's site: ShengSuanYun (opens in a new tab)No public price page for this model -
$1.66DeepInfra
Eden AI
- in
- $1.05
- out
- $3.50
- Precision
- fp4
- Context
- 203k
Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest
Seller's site: Eden AI (opens in a new tab)No public price page for this model -
$1.66DeepInfra
Hugging Face
- in
- $1.05
- out
- $3.50
- Precision
- –
- Context
- 203k
No training on promptsUnited States
See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face -
$1.66FastRouter
FastRouter
- in
- $1.05
- out
- $3.50
- Precision
- –
- Context
- 203k
Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
-
$1.66DeepInfra
LLM Gateway
- in
- $1.05
- out
- $3.50
- Precision
- fp4
- Context
- –
No training on promptsUnited StatesFee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
Go to offer Go to offer at LLM Gateway (opens in a new tab)via LLM Gateway -
$1.66DeepInfra
Requesty
- in
- $1.05
- out
- $3.50
- Precision
- fp4
- Context
- 203k
Prompts may be used for trainingUnited StatesFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
-
$1.83SiliconFlow
Kilo Gateway
- in
- $1.19
- out
- $3.74
- Precision
- fp8
- Context
- 205k
Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway -
$1.83SiliconFlow
OpenRouter
- in
- $1.19
- out
- $3.74
- Precision
- fp8
- Context
- 205k
Training terms not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
-
$1.94AtlasCloud
direct
- in
- $1.26
- out
- $3.96
- Precision
- fp8
- Context
- 203k
Training terms not published
-
$1.94AtlasCloud
Kilo Gateway
- in
- $1.26
- out
- $3.96
- Precision
- fp8
- Context
- 203k
Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer Go to offer at Kilo Gateway (opens in a new tab)via Kilo Gateway -
$1.94AtlasCloud
OpenRouter
- in
- $1.26
- out
- $3.96
- Precision
- fp8
- Context
- 203k
Training terms not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
None of the 25 cheapest offers matches these filters. Show all 70 offers to search them all.
1 flex or batch offer hidden (lower priority, variable latency).
Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.
Monthly cost for your workload
Computed by the API for the three cheapest offers, per 30-day month.- Chutes$97.50per month
- Baidu$96.30per month+$-1.20 vs the cheapest
- ZenMux$105.38per month+$7.88 vs the cheapest
The estimate could not be updated. Try again in a moment.
Compare GLM 5.1 with
Related models
More from Z.ai
Same index family
Use this data
The index is queryable. The API is free to use.curl https://api.inferindex.dev/cheapest?model=z-ai/glm-5.1claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp