Skip to content
ModelCap

Inference provider

StreamLake: AI models and API pricing

Every tracked model StreamLake serves through OpenRouter, with StreamLake's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

StreamLake serves 22 tracked models through 22 endpoints as of 1 October 2026; the highest-ranked is DeepSeek V4.1 Flash (ModelCap Index #15); mean measured uptime is 99.24%.

Models served
22
On the ModelCap Index
12
Cheapest output price
$0.084/1M

Language models on StreamLake (22)

Ranked models first, in ModelCap Index order. Prices are the lowest StreamLake lists for the model; the endpoint count shows how many deployments carry it.

Language models served by StreamLake, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1DeepSeek V4.1 FlashDeepSeek#1579.3$0.141$0.5641Mfp899.60%1Open weights
2GLM 5.3 FlashZ.ai#1778.9$0.087$0.291Mfp899.26%1Open weights
3DeepSeek V4 Pro 0813DeepSeek#2476.4$0.66$1.981M—99.74%1Open weights
4MiniMax M3MiniMax#4068.5$0.30$1.201Mfp899.39%1
5Qwen3.5 397B A17BQwen#4368.0$0.60$3.60256K—100.0%1Open weights
6MiMo-V2.5Xiaomi#4468.0$0.168$0.3361M—96.29%1Open weights
7Kimi K2.7 CodeMoonshot AI#4965.9$0.712$3.00256K—100.0%1
8Qwen3 235B A22B Instruct 2507Qwen#6462.1$0.21$0.84128K—99.02%1Open weights
9R1 0528DeepSeek#6761.5$0.571$2.29128K—100.0%1Open weights
10DeepSeek V3.1 TerminusDeepSeek#7659.7$0.343$1.03128K—100.0%1Open weights
11Qwen3 Coder NextQwen#11053.3$0.18$0.90256K—96.01%1Open weights
12Qwen3 30B A3B Instruct 2507Qwen#12050.6$0.048$0.193128K—99.47%1Open weights
13DeepSeek V3DeepSeek—$0.257$1.03128K—99.33%1
14DeepSeek V4 Flash 0423DeepSeek—$0.042$0.0841Mfp898.80%1Open weights
15DeepSeek V4 Flash 0731DeepSeek—$0.044$0.1321Mfp899.72%1Open weights
16DeepSeek V4 Pro 0423DeepSeek—$0.209$0.4181Mfp899.52%1Open weights
17GLM 5Z.ai—$0.60$1.92198Kfp899.85%1Open weights
18GLM 5.1Z.ai—$0.966$3.04200Kfp8100.0%1Open weights
19GLM 5.2Z.ai—$0.56$1.761Mfp899.57%1Open weights
20Kimi K2.6Moonshot AI—$0.598$2.52256Kfp898.57%1
21MiMo-V2.5-ProXiaomi—$0.522$1.041M——1Open weights
22MiniMax M2.5MiniMax—$0.27$1.08200K—100.0%1

StreamLake on ModelCap: common questions

How many AI models does StreamLake serve?

22 tracked models as of 1 October 2026: 22 language models (12 with a public ModelCap Index position), across 22 live endpoints observed through OpenRouter.

What is the best model available on StreamLake?

DeepSeek V4.1 Flash from DeepSeek is the highest-ranked language model StreamLake serves, at ModelCap Index position #15 and $0.564 per 1M output tokens on StreamLake. The table lists every model in Index order.

What is the cheapest model on StreamLake?

DeepSeek V4 Flash 0423 at $0.084 per 1M output tokens ($0.042 per 1M input), the lowest positive language-token price StreamLake lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which StreamLake model has the largest context window?

DeepSeek V4.1 Flash, served with a 1M-token context window on StreamLake. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is StreamLake?

Mean measured uptime across StreamLake endpoints is 99.24% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the StreamLake prices come from?

From the OpenRouter catalogue entry for each StreamLake endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where StreamLake exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 1 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further