Fireworks AI
Qwen3.8 2.4T A95B
Canonical ID:
fireworks-ai/accounts/fireworks/models/qwen3p8-2p4t-a95b
Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows
Overview
- Provider
-
Fireworks AI
- Family
- qwen
- Release date
- 2026-08-12
- Last updated
- 2026-08-12
- Input modalities
- text
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $2/1M
- Output
- $6/1M
- Cached input
- N/A
Context and output
- Context window
- 262,144
- Max output tokens
- 131,072
- Qualified ID
- fireworks-ai/accounts/fireworks/models/qwen3p8-2p4t-a95b
Model Summary
Qwen3.8 2.4T A95B is a model listing in the Fireworks AI provider catalog. It is categorized under the qwen family.
The model supports text modalities across input/output paths. Reported context capacity is 262,144. Pricing is listed at $2/1M input and $6/1M output.
More From Fireworks AI
Related models from the same provider catalog.
Fireworks AI
DeepSeek Flash Latest
fireworks-ai/accounts/fireworks/routers/deepseek-flash-latest
Fireworks AI
DeepSeek V4.1 Flash
fireworks-ai/accounts/fireworks/models/deepseek-v4p1-flash
Fireworks AI
DeepSeek V4.1 Flash 1017
fireworks-ai/accounts/fireworks/models/deepseek-v4p1-flash-1017
Fireworks AI
DeepSeek V4.1 Flash 1017 Spot
fireworks-ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot
Fireworks AI
DeepSeek V4.1 Flash Spot
fireworks-ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot
Fireworks AI
Ember-1
fireworks-ai/accounts/fireworks/models/ember-1
Fireworks AI
GLM 5.3
fireworks-ai/accounts/fireworks/models/glm-5p3
Fireworks AI
GLM 5.3 Fast
fireworks-ai/accounts/fireworks/routers/glm-5p3-fast
Same Family: qwen
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
Cogito v1 Preview Qwen 32B
nano-gpt/deepcogito/cogito-v1-preview-qwen-32B
|
NanoGPT
|
128,000 | $1.8/1M | $1.8/1M |
|
|
DeepSeek R1 Distill Qwen 14B
alibaba-cn/deepseek-r1-distill-qwen-14b
|
Alibaba (China)
|
32,768 | $0.144/1M | $0.431/1M |
Reasoning
Tools
|
|
DeepSeek R1 Distill Qwen 1.5B
alibaba-cn/deepseek-r1-distill-qwen-1-5b
|
Alibaba (China)
|
32,768 | $0/1M | $0/1M |
Reasoning
|
|
DeepSeek R1 Distill Qwen 32B
alibaba-cn/deepseek-r1-distill-qwen-32b
|
Alibaba (China)
|
32,768 | $0.287/1M | $0.861/1M |
Reasoning
Tools
|
|
DeepSeek R1 Distill Qwen 7B
alibaba-cn/deepseek-r1-distill-qwen-7b
|
Alibaba (China)
|
32,768 | $0.072/1M | $0.144/1M |
Reasoning
Tools
|
|
DeepSeek R1 Qwen Abliterated
nano-gpt/huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
|
NanoGPT
|
16,384 | $1.4/1M | $1.4/1M |
Reasoning
|
|
EVA-Qwen2.5-32B-v0.2
nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
|
NanoGPT
|
16,384 | $0.799/1M | $0.799/1M |
|
|
EVA-Qwen2.5-72B-v0.2
nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
|
NanoGPT
|
16,384 | $0.799/1M | $0.799/1M |
|
|
Qwen 2.5 32B Abliterated
nano-gpt/huihui-ai/Qwen2.5-32B-Instruct-abliterated
|
NanoGPT
|
32,768 | $0.7/1M | $0.7/1M |
|
|
Qwen2.5 72B
nano-gpt/qwen/qwen-2.5-72b-instruct
|
NanoGPT
|
131,072 | $0.36/1M | $0.4/1M |
Tools
|