Интерфейс моделей ИИ

Провайдер · 2026-05-12

llmgateway

20 канонических моделей39 записей всего (включая производные)
МодельВход / 1MВыход / 1MКонтекстПровайдерыТеги
Ministral 3B$0.100$0.100131K1json · vision · open-weights
Ministral 8B$0.150$0.150262K1json · vision · open-weights
Seed 1.6 Flash (250715)$0.070$0.300256K1tools · json · reasoning · vision · open-weights
Ministral 14B$0.200$0.200262K1json · vision · open-weights
MiMo-V2-Flash$0.100$0.300262K1tools · reasoning · open-weights
GPT OSS 20B$0.100$0.500131K1tools · json · reasoning
GPT OSS 120B$0.150$0.750131K1tools · json · reasoning
Seed 1.6 (250615)$0.250$2.00256K1tools · json · reasoning · vision · open-weights
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
MiMo-V2-Omni$0.400$2.00262K1tools · reasoning · vision
MiMo-V2.5$0.400$2.001.05M1tools · reasoning · vision · open-weights
QwQ Plus$0.800$2.40131K1tools · reasoning
MiMo-V2.5-Pro$1.00$3.001.05M1tools · reasoning · open-weights
MiMo-V2-Pro$1.00$3.001.05M1tools · reasoning
o4-mini$1.10$4.40200K1tools · json · reasoning · vision
Pixtral Large (latest)$2.00$6.00128K1tools · vision · open-weights
o1$15.00$60.00200K1tools · json · reasoning · vision
Auto RouteНеизвестноНеизвестно128K1tools · json · vision
Custom ModelНеизвестноНеизвестно128K1tools · json · vision
Qwen3 4B FP8производная$0.030$0.050131K1tools · json · reasoning · open-weights
Qwen2.5 Coder 7Bпроизводная$0.050$0.050131K1json · open-weights
Gemma 2 27B ITпроизводная$0.080$0.0808K1open-weights
GLM-4 32B (0414-128k)производная$0.100$0.100128K1tools · json
Gemma 3 1B ITпроизводная$0.080$0.3001M1open-weights
GLM-4.6V FlashXпроизводная$0.040$0.400128K1tools · json · reasoning · vision
Qwen3 VL Flashпроизводная$0.050$0.4001M1tools · json · vision
Gemma 3 27Bпроизводная$0.270$0.270128K1vision · open-weights
MiniMax M2.1 Lightningпроизводная$0.120$0.480197K1reasoning · open-weights
Qwen Plus Latestпроизводная$0.300$0.900131K1tools · json · vision
MiniMax Text 01производная$0.200$1.101M1reasoning · open-weights
Qwen Coder Plusпроизводная$0.500$1.00131K1tools · json
Qwen3.5 397B-A17Bпроизводная$0.600$3.60262K1tools · json · reasoning · vision · open-weights
GLM-4.5 AirXпроизводная$1.10$4.50128K1tools · json
Qwen Max Latestпроизводная$1.60$6.4033K1tools · json · vision
Grok 4.20 (Non-Reasoning)производная$2.00$6.002M1tools · vision
Grok 4.20 (Reasoning)производная$2.00$6.002M1tools · reasoning · vision
GLM-4.5 Xпроизводная$2.20$8.90128K1tools · json · reasoning
Gemini Pro Latestпроизводная$2.00$12.001.05M1tools · json · reasoning · vision

Frequently asked questions

How many AI models does llmgateway offer?

We track 20 canonical llmgateway models plus 19 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which llmgateway model is the cheapest?

Ministral 3B is currently the lowest-priced llmgateway model, at $0.100 per 1M input tokens and $0.100 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which llmgateway model has the largest context window?

MiMo-V2.5 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 Seed 1.6 Flash (250715) 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 pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

Последнее обновление:

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

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.