ذكاء نماذج الذكاء الاصطناعي

مزود · 2026-08-14

llmgateway

26 نموذج قياسي44 إجمالي السجلات (بما فيها المشتقة)
النموذجإدخال / 1Mإخراج / 1Mالسياقالمزودونالوسوم
GPT OSS 120B$0.032$0.140131K1tools · json · reasoning
GPT OSS 20B$0.040$0.150131K1tools · json · reasoning
Ministral 3B$0.100$0.100131K1json · vision · open-weights
InclusionAI Ling 3.0 Flash$0.060$0.180262K1tools · reasoning
Ministral 8B$0.150$0.150262K1json · vision · open-weights
Seed 1.6 Flash (250715)$0.070$0.300256K1tools · json · reasoning · vision · open-weights
Cosmos 3 Super Reasoner$0.100$0.300262K1tools · reasoning · vision
Ministral 14B$0.200$0.200262K1json · vision · open-weights
MiMo-V2.5$0.140$0.2801M1tools · reasoning · vision · open-weights
Hermes 4 70B$0.130$0.400131K1tools · reasoning
Hy3$0.140$0.580262K1tools · reasoning · open-weights
MiMo-V2.5-Pro$0.435$0.8701M1tools · reasoning · open-weights
ERNIE 4.5 VL 424B A47B$0.420$1.25123K1reasoning · vision
MiniCPM-V 4.5$0.658$1.1132K1tools · vision
Seed 1.8 (251228)$0.250$2.00256K1tools · json · reasoning · vision · open-weights
Seed 1.6 (250915)$0.250$2.00256K1tools · json · reasoning · vision · open-weights
Seed 1.6 (250615)$0.250$2.00256K1tools · json · reasoning · vision · open-weights
Seed 2.1 Turbo$0.500$2.50262K1tools · reasoning
Hermes 4 405B$1.00$3.00131K1tools · reasoning
Muse Spark 1.2$1.25$4.251.05M1tools · json · reasoning · vision
Muse Spark 1.1$1.25$4.251.05M1tools · json · reasoning · vision
o4-mini$1.10$4.40200K1tools · json · reasoning · vision
Fugu Ultra$5.00$30.001M1tools · reasoning · vision
o1$15.00$60.00200K1tools · json · reasoning · vision
Auto Routeغير معروفغير معروف128K1tools · json · vision
Custom Modelغير معروفغير معروف128K1tools · json · vision
GLM-4 32B (0414-128k)مشتق$0.100$0.100128K1tools · json
Gemma 3 27Bمشتق$0.100$0.300110K1tools · vision
GLM-4.6V FlashXمشتق$0.040$0.400128K1tools · json · reasoning · vision
Qwen3 VL Flashمشتق$0.050$0.400262K1tools · json · vision
MiniMax M2.1 Lightningمشتق$0.120$0.480197K1reasoning · open-weights
Nemotron 3 Super 120Bمشتق$0.300$0.900262K1tools · reasoning
MiniMax Text 01مشتق$0.200$1.101M1reasoning · open-weights
Qwen Coder Plusمشتق$0.502$1.00131K1tools · json
Qwen Plus Latestمشتق$0.400$1.201M1tools · json · vision
Nemotron 3 Ultra 550B A55Bمشتق$0.500$2.501.05M1tools · reasoning · open-weights
Qwen3.5 397B-A17Bمشتق$0.600$3.60262K1tools · json · reasoning · vision · open-weights
GLM-4.5 AirXمشتق$1.10$4.50128K1tools · json
GPT-4o Mini Transcribeمشتق$1.25$5.0016K1tools
Grok 4.20 (Non-Reasoning)مشتق$2.00$6.002M1tools · json · vision
Grok 4.20 (Reasoning)مشتق$2.00$6.002M1tools · json · reasoning · vision
GLM-4.5 Xمشتق$2.20$8.90128K1tools · json · reasoning
GPT-4o Transcribeمشتق$2.50$10.0016K1tools
GPT-4o Search Previewمشتق$2.50$10.00128K1vision

Frequently asked questions

How many AI models does llmgateway offer?

We track 26 canonical llmgateway models plus 18 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.

Which llmgateway model is the cheapest?

GPT OSS 120B is currently the lowest-priced llmgateway model, at $0.032 per 1M input tokens and $0.140 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which llmgateway model has the largest context window?

Muse Spark 1.2 leads at 1.05M tokens. This is the total of prompt + completion.

Which llmgateway models support tool calling?

Multiple llmgateway models support tool calling, with GPT OSS 120B being a popular pick. The capability column in the table above marks every model with llmgateway tool-calling support.

Which llmgateway models accept image input?

Ministral 3B accepts image input. Other vision-capable llmgateway models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to llmgateway?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this llmgateway pricing data?

Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

آخر تحديث:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.