RADAR MODELI AI

Porównuj modele AI według tych samych kryteriów

Wszystkie modele obecnie dostępne w OpenRouter wraz ze spójnymi danymi o modalnościach, kontekście, cenach, konfiguracji i dostawcach.

ZAKRES KATALOGU
WSZYSTKIE PUBLICZNE
modele
740
dostawców
101
ostatnia synchronizacja
20 lis 2026
740 modele
qwen logoqwen

Qwen: Qwen3 VL 235B A22B Instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

Kontekst
262K
Wejście
text · image
Wyjście
text
Wejście: $0.21Wyjście: $1.9za milion tokenów
Zobacz szczegóły modelu →
deepseek logodeepseek

DeepSeek: DeepSeek V3.1 Terminus

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

Kontekst
164K
Wejście
text
Wyjście
text
Wejście: $0.27Wyjście: $1za milion tokenów
Zobacz szczegóły modelu →
qwen logoqwen

Qwen: Qwen3 Coder Flash

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

Kontekst
1M
Wejście
text
Wyjście
text
Wejście: $0.195Wyjście: $0.975za milion tokenów
Zobacz szczegóły modelu →
qwen logoqwen

Qwen: Qwen3 Next 80B A3B Instruct

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

Kontekst
262K
Wejście
text
Wyjście
text
Wejście: $0.1Wyjście: $1.1za milion tokenów
Zobacz szczegóły modelu →
moonshotai logomoonshotai

MoonshotAI: Kimi K2 0905

Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Kontekst
262K
Wejście
text
Wyjście
text
Wejście: $0.6Wyjście: $2.5za milion tokenów
Zobacz szczegóły modelu →
nousresearch logonousresearch

Nous: Hermes 4 405B

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

Kontekst
131K
Wejście
text
Wyjście
text
Wejście: $1Wyjście: $3za milion tokenów
Zobacz szczegóły modelu →
deepseek logodeepseek

DeepSeek: DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Kontekst
164K
Wejście
text
Wyjście
text
Wejście: $0.25Wyjście: $0.95za milion tokenów
Zobacz szczegóły modelu →
mistralai logomistralai

Mistral: Mistral Medium 3.1

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

Kontekst
131K
Wejście
text · image · file
Wyjście
text
Wejście: $0.44Wyjście: $2.2za milion tokenów
Zobacz szczegóły modelu →
z-ai logoz-ai

Z.ai: GLM 4.5V

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

Kontekst
66K
Wejście
text · image
Wyjście
text
Wejście: $0.6Wyjście: $1.8za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: GPT-5

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

Kontekst
400K
Wejście
text · image · file
Wyjście
text
Wejście: $1.25Wyjście: $10za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: GPT-5 (batch)

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

Kontekst
400K
Wejście
text · image · file
Wyjście
text
Wejście: $0.625Wyjście: $5za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: GPT-5 Mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

Kontekst
400K
Wejście
text · image · file
Wyjście
text
Wejście: $0.25Wyjście: $2za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: GPT-5 Mini (batch)

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

Kontekst
400K
Wejście
text · image · file
Wyjście
text
Wejście: $0.125Wyjście: $1za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: GPT-5 Nano

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

Kontekst
400K
Wejście
text · image · file
Wyjście
text
Wejście: $0.05Wyjście: $0.4za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: GPT-5 Nano (batch)

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

Kontekst
400K
Wejście
text · image · file
Wyjście
text
Wejście: $0.025Wyjście: $0.2za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Kontekst
131K
Wejście
text
Wyjście
text
Wejście: $0.09Wyjście: $0.36za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: gpt-oss-120b (batch)

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Kontekst
131K
Wejście
text
Wyjście
text
Wejście: $0.0296Wyjście: $0.136za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Kontekst
131K
Wejście
text
Wyjście
text
Wejście: $0.018Wyjście: $0.09za milion tokenów
Zobacz szczegóły modelu →
openai logoopenai

OpenAI: gpt-oss-20b (batch)

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Kontekst
131K
Wejście
text
Wyjście
text
Wejście: $0.024Wyjście: $0.112za milion tokenów
Zobacz szczegóły modelu →
anthropic logoanthropic

Anthropic: Claude Opus 4.1

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

Kontekst
200K
Wejście
image · text · file
Wyjście
text
Wejście: $15Wyjście: $75za milion tokenów
Zobacz szczegóły modelu →
anthropic logoanthropic

Anthropic: Claude Opus 4.1 (batch)

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

Kontekst
200K
Wejście
image · text · file
Wyjście
text
Wejście: $7.5Wyjście: $37.5za milion tokenów
Zobacz szczegóły modelu →
mistralai logomistralai

Mistral: Codestral 2508

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post

Kontekst
256K
Wejście
text · file
Wyjście
text
Wejście: $0.3Wyjście: $0.9za milion tokenów
Zobacz szczegóły modelu →
qwen logoqwen

Qwen: Qwen3 Coder 30B A3B Instruct

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

Kontekst
262K
Wejście
text
Wyjście
text
Wejście: $0.15Wyjście: $0.6za milion tokenów
Zobacz szczegóły modelu →
qwen logoqwen

Qwen: Qwen3 30B A3B Instruct 2507

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

Kontekst
262K
Wejście
text
Wyjście
text
Wejście: $0.1Wyjście: $0.3za milion tokenów
Zobacz szczegóły modelu →