Anthropic: Claude Opus 4.8262,144 ctx
efficientstack/claude-opus-4.8
self-hosted
textimagevideofiles
Code-Tuned version of Claude 4.8 Opus
Aylo-Lab: Opus-4.8-Unrestricted262,144 ctx
aylo-lab/opus-4.8-unrestricted
self-hosted
textimagevideofiles
Unrestricted version of Opus 4.8
Gemini 3.8 Flash
mv/gemini-3.8-flash
preset
textimageaudiovideofiles
Auto-Router preset to route Gemini 3.8 Flash with auto-fallback between the providers. — $0.75 in / $3.75 out per 1M
Gemini 3.1 Flash Lite (MV)
mv/gemini-3.1-flash-lite
preset
textimageaudiovideofiles
Auto-Router preset to route and load balance Gemini 3.1 Flash Lite between the providers. — $0.28 in / $1.65 out per 1M
Gemini 3.1 Flash Lite (MV) EDEN
mv/gemini-3.1-flash-lite-eden
preset
textimageaudiovideofiles
Auto-Router preset to route and load balance Gemini 3.1 Flash Lite between the providers. — $0.28 in / $1.65 out per 1M
Gemini 3.1 Flash Lite (MV) FLEX
mv/gemini-3.1-flash-lite-flex
preset
textimageaudiovideofiles
Auto-Router preset to route and load balance Gemini 3.1 Flash Lite between the providers. — $0.13 in / $0.75 out per 1M
AB Testing Model
efficientstack/ab-opus4.8-03
preset
textimage
AB Testing Model against Anthropic Opus 4.8 — $0.08 in / $0.30 out per 1M
Claude Sonnet 4.6
llmrgbl/claude-sonnet-4-6
preset
text
Routed preset with automatic failover. — $3.00 in / $1.50 out per 1M
llmrgbl/gemini-3.5-flash-lite
llmrgbl/gemini-3.5-flash-lite
preset
text
Routed preset with automatic failover. — $0.15 in / $1.25 out per 1M
llmrgbl/gemini-3.8-flash
llmrgbl/gemini-3.8-flash
preset
text
Routed preset with automatic failover. — $0.75 in / $3.75 out per 1M
llmrgbl/gemini-2.5-flash-lite
llmrgbl/gemini-2.5-flash-lite
preset
text
Routed preset with automatic failover. — $0.05 in / $0.20 out per 1M
llmrgbl/glm-5.2
llmrgbl/glm-5.2
preset
text
Routed preset with automatic failover. — $0.75 in / $2.40 out per 1M
llmrgbl/gemini-3.7-flash
llmrgbl/gemini-3.7-flash
preset
text
Routed preset with automatic failover. — $0.75 in / $7.75 out per 1M
llmrgbl/grok-4.2
llmrgbl/grok-4.2
preset
text
Routed preset with automatic failover. — $2.00 in / $1.25 out per 1M
llmrgbl/minimax-m3
llmrgbl/minimax-m3
preset
text
Routed preset with automatic failover. — $0.30 in / $1.20 out per 1M
llmrgbl/mimo-v2.5
llmrgbl/mimo-v2.5
preset
text
Routed preset with automatic failover. — $0.14 in / $0.28 out per 1M
llmrgbl/kimi-k3
llmrgbl/kimi-k3
preset
text
Routed preset with automatic failover. — $3.00 in / $1.50 out per 1M
llmrgbl/claude-opus-5-5
llmrgbl/claude-opus-5-5
preset
text
Routed preset with automatic failover. — $4.00 in / $20.00 out per 1M
llmrgbl/claude-sonnet-5
llmrgbl/claude-sonnet-5
preset
text
Routed preset with automatic failover. — $2.00 in / $10.00 out per 1M
@preset/bzai-v1 bzdotai
@preset/bzai-v1
preset
text
Routed preset with automatic failover. — $0.05 in / $0.20 out per 1M
llmrgbl/claude-haiku-4-5
llmrgbl/claude-haiku-4-5
preset
text
Routed preset with automatic failover. — $1.00 in / $5.00 out per 1M
llmrgbl/glm-5-3-flash
llmrgbl/glm-5-3-flash
preset
text
Routed preset with automatic failover. — $0.05 in / $0.17 out per 1M
llmrgbl/glm-5-3
llmrgbl/glm-5-3
preset
text
Routed preset with automatic failover. — $1.14 in / $3.42 out per 1M
llmrgbl/grok-4.3
llmrgbl/grok-4.3
preset
text
Routed preset with automatic failover. — $1.25 in / $2.50 out per 1M
llmrgbl/deepseek-v4-flash
llmrgbl/deepseek-v4-flash
preset
text
Routed preset with automatic failover. — $0.07 in / $0.14 out per 1M
llmrgbl/mistral-medium-3-5
llmrgbl/mistral-medium-3-5
preset
text
Routed preset with automatic failover. — $1.65 in / $8.25 out per 1M
llmrgbl/claude-sonnet-5-5
llmrgbl/claude-sonnet-5-5
preset
text
Routed preset with automatic failover. — $2.00 in / $10.00 out per 1M
llmrgbl/grok-4.7
llmrgbl/grok-4.7
preset
text
Routed preset with automatic failover. — $2.00 in / $6.00 out per 1M
llmrgbl/gemini-2.5-flash
llmrgbl/gemini-2.5-flash
preset
text
Routed preset with automatic failover. — $0.05 in / $0.20 out per 1M
llmrg/nemotron-3-super-120b-a12b
llmrg/nemotron-3-super-120b-a12b
preset
text
Routed preset with automatic failover. — $0.08 in / $0.40 out per 1M
llmrgbl/claude-sonnet-4-5
llmrgbl/claude-sonnet-4-5
preset
text
Routed preset with automatic failover. — $3.00 in / $14.00 out per 1M
llmrgbl/gemma-4-26b-a4b-it
llmrgbl/gemma-4-26b-a4b-it
preset
textimageaudiovideofiles
Routed preset with automatic failover. — $0.06 in / $0.27 out per 1M
llmrgbl/qwen3.5-9b
llmrgbl/qwen3.5-9b
preset
textimageaudiovideofiles
Routed preset with automatic failover. — $0.09 in / $0.13 out per 1M
llmrgbl/gemini-3.1-flash-lite
llmrgbl/gemini-3.1-flash-lite
preset
text
Routed preset with automatic failover. — $0.25 in / $1.50 out per 1M
llmrgbl/jev-1.13.0
llmrgbl/jev-1.13.0
preset
text
Routed preset with automatic failover. — $0.04 in / $0 out per 1M
llmrgbl/claude-haiku-5-5
llmrgbl/claude-haiku-5-5
preset
text
Routed preset with automatic failover. — $0.10 in / $0.50 out per 1M
llmrgbl/deepseek-v4.1-flash
llmrgbl/deepseek-v4.1-flash
preset
text
Routed preset with automatic failover. — $0.15 in / $0.48 out per 1M
llmrgbl/gemini-embedding-001
llmrgbl/gemini-embedding-001
preset
text
Routed preset with automatic failover. — $0.15 in / $0 out per 1M
llmrgbl/mimo-v2.6-flash
llmrgbl/mimo-v2.6-flash
preset
text
Routed preset with automatic failover. — $0.14 in / $0.28 out per 1M
policy/adult_gemini_flash_lite_25
policy/adult_gemini_flash_lite_25
upstream
text
Your dynamic policy. Configure via the Requesty UI.
All features are shown as supported to avoid any restrictions from the application.
Context window and max output tokens are set to the minimal value across policy providers.
Prices are se
policy/adult_gemini_flash_lite_31
policy/adult_gemini_flash_lite_31
upstream
text
Your dynamic policy. Configure via the Requesty UI.
All features are shown as supported to avoid any restrictions from the application.
Context window and max output tokens are set to the minimal value across policy providers.
Prices are se
policy/adult_gemini_flash_lite_35
policy/adult_gemini_flash_lite_35
upstream
text
Your dynamic policy. Configure via the Requesty UI.
All features are shown as supported to avoid any restrictions from the application.
Context window and max output tokens are set to the minimal value across policy providers.
Prices are se
policy/adult_gemini_flash_lite_37
policy/adult_gemini_flash_lite_37
upstream
text
Your dynamic policy. Configure via the Requesty UI.
All features are shown as supported to avoid any restrictions from the application.
Context window and max output tokens are set to the minimal value across policy providers.
Prices are se
anthropic/claude-haiku-5-5
anthropic/claude-haiku-5-5
upstream
text
Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.
bedrock/claude-haiku-5-5
bedrock/claude-haiku-5-5
upstream
text
Claude Haiku 5.5 is the fastest model in the Claude 5.5 family, built for high volume, speed sensitive workloads. It is much stronger than Haiku 4.5 and is the first Haiku with effort levels to control how much it thinks.
mistral/mistral-large-4
mistral/mistral-large-4
upstream
text
Mistral Large 4 is a state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. It features 49B active parameters and 1.05T total parameters, and a 1.6B vision encoder. Public preview, 1
sference/clef
sference/clef
upstream
text
Clef is a 27B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.
cloudflare/clef-flash
cloudflare/clef-flash
upstream
text
Clef-flash is a fast 9B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.
cloudflare/clef
cloudflare/clef
upstream
text
Clef is a 27B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.
perplexity/pplx-decider-v1-27b
perplexity/pplx-decider-v1-27b
upstream
text
Perplexity decision model. Answers typed questions (noul, choice, score) about the provided state with probabilities instead of text.
openai/gpt-6.1-sol
openai/gpt-6.1-sol
upstream
text
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.
openai/gpt-6.1-sol:flex
openai/gpt-6.1-sol:flex
upstream
text
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.
azure/gpt-6.1-sol@eastus2
azure/gpt-6.1-sol@eastus2
upstream
text
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.
azure/gpt-6.1-sol@francecentral
azure/gpt-6.1-sol@francecentral
upstream
text
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.
azure/gpt-6.1-sol@germanywestcentral
azure/gpt-6.1-sol@germanywestcentral
upstream
text
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.
azure/gpt-6.1-sol@swedencentral
azure/gpt-6.1-sol@swedencentral
upstream
text
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.
azure/gpt-6.1-sol@westeurope
azure/gpt-6.1-sol@westeurope
upstream
text
GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It succeeds GPT-6 Sol with the same 1M context and 128K output, cheaper cached input, and reasoning effort from low to max.
bedrock/claude-sonnet-5-5
bedrock/claude-sonnet-5-5
upstream
text
Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on comm
anthropic/claude-sonnet-5-5
anthropic/claude-sonnet-5-5
upstream
text
Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on comm
novita/ling-3.1-flash
novita/ling-3.1-flash
upstream
text
Ling 3.1 Flash is a hybrid reasoning MoE model from inclusionAI with 560B total and 25B active parameters. Served by Novita with a 256K context window and 32K max output, supporting reasoning and function calling. Free tier.
vertex/claude-sonnet-5-5
vertex/claude-sonnet-5-5
upstream
text
Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on comm
vertex/claude-sonnet-5-5@eu
vertex/claude-sonnet-5-5@eu
upstream
text
Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on comm
vertex/claude-sonnet-5-5@us
vertex/claude-sonnet-5-5@us
upstream
text
Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on comm
deepinfra/mimo-v2.6-flash
deepinfra/mimo-v2.6-flash
upstream
text
MiMo-V2.6-Flash is the efficiency-balanced model in Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 309B total and 15B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context w
deepinfra/mimo-v2.6-pro
deepinfra/mimo-v2.6-pro
upstream
text
MiMo-V2.6-Pro is the flagship of Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 1.02T total and 42B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained wit
azure/gpt-6-luna@eastus2
azure/gpt-6-luna@eastus2
upstream
text
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reaso
azure/gpt-6-sol@eastus2
azure/gpt-6-sol@eastus2
upstream
text
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automatio
azure/gpt-6-luna@francecentral
azure/gpt-6-luna@francecentral
upstream
text
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reaso
azure/gpt-6-luna@germanywestcentral
azure/gpt-6-luna@germanywestcentral
upstream
text
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reaso
azure/gpt-6-luna@swedencentral
azure/gpt-6-luna@swedencentral
upstream
text
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reaso
azure/gpt-6-luna@westeurope
azure/gpt-6-luna@westeurope
upstream
text
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reaso
azure/gpt-6-sol@francecentral
azure/gpt-6-sol@francecentral
upstream
text
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automatio
azure/gpt-6-sol@germanywestcentral
azure/gpt-6-sol@germanywestcentral
upstream
text
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automatio
azure/gpt-6-sol@swedencentral
azure/gpt-6-sol@swedencentral
upstream
text
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automatio
azure/gpt-6-sol@westeurope
azure/gpt-6-sol@westeurope
upstream
text
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automatio
openai/gpt-6-luna:flex
openai/gpt-6-luna:flex
upstream
text
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reaso
openai/gpt-6-luna
openai/gpt-6-luna
upstream
text
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reaso
openai/gpt-6-sol:flex
openai/gpt-6-sol:flex
upstream
text
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automatio
openai/gpt-6-sol
openai/gpt-6-sol
upstream
text
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automatio
anthropic/claude-opus-5-5
anthropic/claude-opus-5-5
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
vertex/claude-opus-5-5
vertex/claude-opus-5-5
upstream
text
Claude Opus 5.5 is the first model in Anthropic's Claude 5.5 family and the most capable Opus to date, built for long running autonomous agents, large scale coding, and frontier knowledge work. It improves on Opus 5 in planning, sustained m
vertex/claude-opus-5-5@eu
vertex/claude-opus-5-5@eu
upstream
text
Claude Opus 5.5 is the first model in Anthropic's Claude 5.5 family and the most capable Opus to date, built for long running autonomous agents, large scale coding, and frontier knowledge work. It improves on Opus 5 in planning, sustained m
vertex/claude-opus-5-5@us
vertex/claude-opus-5-5@us
upstream
text
Claude Opus 5.5 is the first model in Anthropic's Claude 5.5 family and the most capable Opus to date, built for long running autonomous agents, large scale coding, and frontier knowledge work. It improves on Opus 5 in planning, sustained m
bedrock/claude-opus-5-5
bedrock/claude-opus-5-5
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
bedrock/claude-opus-5-5@eu-central-1
bedrock/claude-opus-5-5@eu-central-1
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
bedrock/claude-opus-5-5@eu-north-1
bedrock/claude-opus-5-5@eu-north-1
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
bedrock/claude-opus-5-5@eu-west-1
bedrock/claude-opus-5-5@eu-west-1
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
bedrock/claude-opus-5-5@eu-west-3
bedrock/claude-opus-5-5@eu-west-3
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
xiaomi/mimo-v2.6-pro
xiaomi/mimo-v2.6-pro
upstream
text
Xiaomi MiMo V2.6 Pro. Flagship 1T+ parameter MoE, native omni-modal input (text, image, video, audio), text output. 1M token context window, 128K max output. OpenAI-compatible.
xiaomi/mimo-v2.6-flash
xiaomi/mimo-v2.6-flash
upstream
text
Xiaomi MiMo V2.6 Flash. 309B total / 15B active MoE with hybrid attention, native omni-modal input (text, image, video, audio), text output. 1M token context window, 128K max output. OpenAI-compatible.
xiaomi/mimo-v2.6-pro-ultraspeed
xiaomi/mimo-v2.6-pro-ultraspeed
upstream
text
Xiaomi MiMo V2.6 Pro UltraSpeed. Same 1T+ MiMo V2.6 Pro checkpoint served at roughly 10x output speed for latency sensitive workloads. Omni-modal input (text, image, video, audio), text output. 1M token context window, 128K max output. Open
bedrock/claude-opus-5-5@ap-northeast-1
bedrock/claude-opus-5-5@ap-northeast-1
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
bedrock/claude-opus-5-5@ap-northeast-3
bedrock/claude-opus-5-5@ap-northeast-3
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
bedrock/claude-opus-5-5@ap-southeast-2
bedrock/claude-opus-5-5@ap-southeast-2
upstream
text
Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work. It reports back in plain languag
tencent/mimo-v2.6-flash
tencent/mimo-v2.6-flash
upstream
text
MiMo-V2.6-Flash is Xiaomi's fast, cost-efficient multimodal model with a 1M token context window, supporting text, image and video input, deep thinking, function calling and structured output.
tencent/mimo-v2.6-pro
tencent/mimo-v2.6-pro
upstream
text
MiMo-V2.6-Pro is Xiaomi's flagship multimodal model with a 1M token context window, supporting text, image and video input, deep thinking, function calling and structured output.
xai/grok-4.7
xai/grok-4.7
upstream
text
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improv
typesafe/jev-1.13.0
typesafe/jev-1.13.0
upstream
text
Jev is TypeSafe’s flagship model and the first System One model.
tencent/glm-5.3-flashx
tencent/glm-5.3-flashx
upstream
text
GLM-5.3-FlashX is the enhanced, high-speed (~200 tokens/s) variant of GLM-5.3-Flash with a 1M token context window and image, video and file understanding.
runware/deepseek-v4.1-flash
runware/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an
sference/deepseek-v4.1-flash
sference/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost
tensorx/deepseek-v4.1-flash
tensorx/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost
fireworks/deepseek-v4.1-flash
fireworks/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost
novita/deepseek-v4.1-flash
novita/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost
deepseek/deepseek-v4.1-flash
deepseek/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost
melious/deepseek-v4.1-flash
melious/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a 552B MoE hybrid reasoning model with image input and a 1M token context, suited for agentic coding and long context work. Served from the EU by Melious.
tencent/deepseek-v4.1-flash
tencent/deepseek-v4.1-flash
upstream
text
DeepSeek-V4.1-Flash is DeepSeek's efficient production model with a 1M token context window, configurable thinking mode and strong tool calling for high-concurrency, low-latency workloads.
deepinfra/deepseek-v4.1-flash
deepinfra/deepseek-v4.1-flash
upstream
text
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost
deepinfra/deepseek-v4.1-flash:flex
deepinfra/deepseek-v4.1-flash:flex
upstream
text
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost
openai/gpt-6-astra:flex
openai/gpt-6-astra:flex
upstream
text
GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with reasoning effort levels from low up to xhigh and max.
azure/gpt-6-astra@eastus2
azure/gpt-6-astra@eastus2
upstream
text
GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with reasoning effort levels from low up to xhigh and max.
openai/gpt-6-astra
openai/gpt-6-astra
upstream
text
GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with reasoning effort levels from low up to xhigh and max.
vertex/gemini-3.8-flash
vertex/gemini-3.8-flash
upstream
text
Gemini 3.8 Flash is Google's most intelligent workhorse model, delivering significant improvements over 3.7 Flash across software engineering, agentic tasks, and critical multi step reasoning in specialized domains.
vertex/gemini-3.8-flash@eu
vertex/gemini-3.8-flash@eu
upstream
text
Gemini 3.8 Flash is Google's most intelligent workhorse model, delivering significant improvements over 3.7 Flash across software engineering, agentic tasks, and critical multi step reasoning in specialized domains.
anthropic/claude-fable-5.1
anthropic/claude-fable-5.1
upstream
text
Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and an
vertex/claude-fable-5.1
vertex/claude-fable-5.1
upstream
text
Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and an
vertex/claude-fable-5.1@eu
vertex/claude-fable-5.1@eu
upstream
text
Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and an
fireworks/deepseek-v4-flash-vision-exp
fireworks/deepseek-v4-flash-vision-exp
upstream
text
DeepSeek V4 Flash Vision Exp is the first experimental multimodal model in the DeepSeek V4 family. It builds on DeepSeek V4 Flash with added visual modules and continued training for visual understanding, with substantially improved multimo
runware/glm-5.3-flash
runware/glm-5.3-flash
upstream
text
GLM 5.3 Flash is Z.ai's lower-cost model from the GLM 5.3 family for coding and long-horizon agent workflows, with reasoning and efficient long-context serving. Image input is not supported on this deployment. Served via Runware.
tencent/hy4-preview
tencent/hy4-preview
upstream
text
Hy4 preview is Tencent's flagship class MoE model with 770B total parameters and 49B activated, supporting a 1M token context window. It is optimized for agent, coding, and productivity scenarios, with strong task decomposition, context tra
1042 further models are available with JavaScript enabled.