azureFoundry/azureml-fireworks/FW-DeepSeek-V3.1@1
DeepSeek V3.1 is a 685B-parameter Mixture-of-Experts model with dual-mode thinking and non-thinking chat, featuring two-phase long context extension up to 163K tokens.
- Context window
- 163,840
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-DeepSeek-V3.2@1
DeepSeek V3.2 is a 675.2B-parameter Mixture-of-Experts model that combines high computational efficiency with superior reasoning and agent performance, supporting a 163.8K token context window.
- Context window
- 163,840
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-DeepSeek-V4.1-Flash-1017@1
DeepSeek V4.1 Flash 1017 is a multimodal update to DeepSeek V4.1 Flash with improved reasoning, coding, agentic, and visual performance, reduced task execution time and output length, and a 1,048,576-token context window on Fireworks.
- Context window
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
azureFoundry/azureml-fireworks/FW-DeepSeek-V4.1-Flash@1
DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters, native image and text input, and a 1,048,576-token context window on Fireworks. Its Causal Encoder-Decoder architecture activates 8B parameters during prefill and 1
- Context window
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
azureFoundry/azureml-fireworks/FW-DeepSeek-V4-Flash-0731@1
DeepSeek V4 Flash 0731 is the official 304B-parameter release of DeepSeek V4 Flash, with a 1M-token context window, DSpark speculative decoding, and substantially enhanced agentic capabilities.
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-DeepSeek-V4-Flash@1
DeepSeek V4 Flash is a 284B-parameter Mixture-of-Experts model with 13B activated parameters, supporting a 1M token context window with highly efficient long-context intelligence.
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-DeepSeek-V4-Pro@1
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B activated parameters, supporting a 1M token context window with highly efficient long-context intelligence.
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
cheaperInference/ember-1
- Context window
- 1,048,576
- Maximum output
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, structuredOutputs, toolCalling, visionInput
Inference prices
vercelAIGatewayCatalog/fireworks/ember-1
Ember-1 is Fireworks’ research-preview reasoning model built on Kimi K3 for coding and agentic workflows. It supports image input, function calling, and a 1M-token context window. Fireworks reports approximately 40% fewer generated tokens while maintaining comparable quality acro
- Context window
- 1,048,576
- Maximum output
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, toolCalling, visionInput
Inference prices
fireworks/ember-1-20260923
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintainin
- Context window
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Inference prices
azureFoundry/azureml-fireworks/FW-Gemma-4-26B-A4B-IT@1
Gemma 4 26B A4B IT is an instruction-tuned multimodal Mixture-of-Experts (MoE) model with 25.2B total parameters and 3.8B active parameters, supporting text-and-image input, 256K context, multilingual use in over 140 languages, and configurable thinking mo
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-Gemma-4-31B-IT@1
Gemma 4 31B IT is a 30.7B-parameter dense multimodal model with a ~550M vision encoder, text-and-image input, text output, configurable thinking modes for reasoning, and a 256K-token context window.
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GLM-4.7@1
GLM 4.7 is a general-purpose model optimized for coding, reasoning, and agentic workflows, featuring advanced thinking controls with interleaved, preserved, and turn-level thinking modes.
- Context window
- 204,800
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GLM-5.1@1
GLM 5.1 is zAI's next-generation flagship model for agentic engineering with 754B total parameters (40B activated), achieving state-of-the-art performance on SWE-Bench Pro and leading on NL2Repo and Terminal-Bench 2.0.
- Context window
- 202,752
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GLM-5.2@1
GLM 5.2 is zAI's latest flagship model for long-horizon tasks, offering a solid 1M-token context, stronger coding with flexible effort levels, and an IndexShare-enhanced GLM MoE DSA architecture with 744B total parameters and 40B active.
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GLM-5.2-Fast@1
GLM 5.2 Fast is Fireworks' high-throughput serverless path for GLM 5.2, using the same weights and quality as Standard with the full 1M-token context and about 2x Standard throughput.
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GLM-5.3@1
GLM 5.3 is zAI's flagship model for complex software engineering and agent capabilities, using the same 744B-parameter Mixture-of-Experts base model as GLM 5.2 with 40B active parameters, a 1M-token context window, a 128K-token maximum output, and always-o
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, toolCalling
azureFoundry/azureml-fireworks/FW-GLM-5.3-Flash@1
GLM 5.3 Flash is Z.ai's first natively multimodal GLM-5 model, with 320B total parameters and 18B active parameters, a hybrid sparse and linear attention architecture, Manifold-Constrained Hyper-Connections, text and image input, function calling, and a 1,
- Context window
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, toolCalling, visionInput