# Models

> Serve frontier open models, or your own post-trained versions of them, on an engine optimized at every layer.

## Models

Model Library

Serve frontier open models, or your own post-trained versions of them, on an engine optimized at every layer.

- **[Kimi K3.1 Pro](https://fireworks.ai/models/fireworks/kimi-k3p1-pro)**: New · Vision • Serverless · $2/M Input • $10/M Output • 1048576 Context
- **[DeepSeek V4.1 Flash](https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash)**: Vision • Serverless · $0.3/M Input • $1.2/M Output • 1048576 Context
- **[DeepSeek V4.1 Flash 1017](https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash-1017)**: Vision • Serverless · $0.3/M Input • $1.2/M Output • 1048576 Context
- **[Ember-1](https://fireworks.ai/models/fireworks/ember-1)**: New · Vision • Serverless · $3/M Input • $15/M Output • 1048576 Context
- **[MiniMax M3.1 Flash](https://fireworks.ai/models/fireworks/minimax-m3p1-flash)**: New · Vision • Serverless · $0.15/M Input • $0.6/M Output • 1048576 Context
- **[GLM 5.3 Flash](https://fireworks.ai/models/fireworks/glm-5p3-flash)**: Vision • Serverless · $0.15/M Input • $0.5/M Output • 1048576 Context
- **[GLM-5.3](https://fireworks.ai/models/fireworks/glm-5p3)**: LLM • Serverless · $1.4/M Input • $4.4/M Output • 1048576 Context
- **[MiMo-V2.6-Pro-RL](https://fireworks.ai/models/fireworks/mimo-v2p6-pro-rl)**: Vision · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[Qwen3.8 Flash Next FP4](https://fireworks.ai/models/fireworks/qwen3p8-flash-next-nvfp4)**: Vision · $1.2/M Input • $1.2/M Output • 262144 Context
- **[Qwen3.8 Flash Next FP8](https://fireworks.ai/models/fireworks/qwen3p8-flash-next-fp8)**: Vision · $1.2/M Input • $1.2/M Output • 262144 Context
- **[Muse Spark Open](https://fireworks.ai/models/fireworks/muse-spark-open)**: New · Vision • Serverless · $1.25/M Input • $4.25/M Output • 1048576 Context
- **[Kimi K3](https://fireworks.ai/models/fireworks/kimi-k3)**: Vision • Serverless · $3/M Input • $15/M Output • 1048576 Context
- **[DeepSeek-V4-Flash-0731](https://fireworks.ai/models/deepseek-ai/deepseek-v4-flash-0731)**: LLM · $0.22/M Input • $0.66/M Output • 1048576 Context
- **[DeepSeek-V4-Pro](https://fireworks.ai/models/fireworks/deepseek-v4-pro)**: LLM · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[DeepSeek-V4-Pro-0813](https://fireworks.ai/models/deepseek-ai/deepseek-v4-pro-0813)**: LLM · $1.32/M Input • $3.96/M Output • 1048576 Context
- **[GLM 5.2](https://fireworks.ai/models/fireworks/glm-5p2)**: LLM · $1.4/M Input • $4.4/M Output • 1048576 Context
- **[Kimi K2.7 Code](https://fireworks.ai/models/fireworks/kimi-k2p7-code)**: Vision · $0.95/M Input • $4/M Output • 262144 Context
- **[Minimax M3](https://fireworks.ai/models/fireworks/minimax-m3)**: LLM • Serverless · $0.3/M Input • $1.2/M Output • 512000 Context
- **[Muse Glimmer 30B](https://fireworks.ai/models/fireworks/muse-glimmer-30b)**: Vision · $0.35/M Input • $1.5/M Output • 131072 Context
- **[Qwen 3.8 Max](https://fireworks.ai/models/fireworks/qwen3p8-max)**: Vision • Serverless · $2/M Input • $6/M Output
- **[Qwen3.6 Plus](https://fireworks.ai/models/fireworks/qwen3p6-plus)**: Vision · $0.5/M Input • $3/M Output
- **[Qwen3.7 Max](https://fireworks.ai/models/fireworks/qwen3p7-max)**: LLM · $0.1/M Input • $0.1/M Output
- **[DeepSeek V3.1](https://fireworks.ai/models/fireworks/deepseek-v3p1)**: LLM · $0.56/M Input • $1.68/M Output • 163840 Context
- **[Gemma 4 31B IT NVFP4](https://fireworks.ai/models/fireworks/gemma-4-31b-it-nvfp4)**: Vision · $0.9/M Input • $0.9/M Output • 262144 Context
- **[GLM-5](https://fireworks.ai/models/fireworks/glm-5)**: LLM · $1/M Input • $3.2/M Output • 202752 Context
- **[Kimi K2 Instruct 0905](https://fireworks.ai/models/fireworks/kimi-k2-instruct-0905)**: LLM · $0.6/M Input • $2.5/M Output • 262144 Context
- **[OpenAI gpt-oss-120b](https://fireworks.ai/models/fireworks/gpt-oss-120b)**: LLM · $0.15/M Input • $0.6/M Output • 131072 Context
- **[OpenAI gpt-oss-20b](https://fireworks.ai/models/fireworks/gpt-oss-20b)**: LLM · $0.5/M Input • $0.5/M Output • 131072 Context
- **[Qwen3 235B A22B](https://fireworks.ai/models/fireworks/qwen3-235b-a22b)**: LLM · $0.22/M Input • $0.88/M Output • 131072 Context
- **[Qwen3 VL 235B A22B Instruct](https://fireworks.ai/models/fireworks/qwen3-vl-235b-a22b-instruct)**: Vision · $0.22/M Input • $0.88/M Output • 262144 Context
- **[Qwen3 VL 235B A22B Thinking](https://fireworks.ai/models/fireworks/qwen3-vl-235b-a22b-thinking)**: Vision · $0.22/M Input • $0.88/M Output • 262144 Context
- **[GLM-4.6](https://fireworks.ai/models/fireworks/glm-4p6)**: LLM · $0.55/M Input • $2.19/M Output • 202752 Context
- **[Kimi K2 Thinking](https://fireworks.ai/models/fireworks/kimi-k2-thinking)**: LLM · $0.6/M Input • $2.5/M Output • 262144 Context
- **[Llama 3.3 70B Instruct](https://fireworks.ai/models/fireworks/llama-v3p3-70b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[NVIDIA Nemotron 3 Super 120B A12B FP8](https://fireworks.ai/models/fireworks/nvidia-nemotron-3-super-120b-a12b-fp8)**: LLM · $0.9/M Input • $0.9/M Output • 262144 Context
- **[NVIDIA Nemotron 3 Super 120B A12B NVFP4](https://fireworks.ai/models/fireworks/nvidia-nemotron-3-super-120b-a12b-nvfp4)**: LLM · $1.2/M Input • $1.2/M Output • 262144 Context
- **[NVIDIA Nemotron 3 Ultra BF16](https://fireworks.ai/models/fireworks/nemotron-3-ultra-bf16)**: LLM · $1.2/M Input • $1.2/M Output • 262144 Context
- **[NVIDIA Nemotron 3 Ultra NVFP4](https://fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4)**: LLM · $0.6/M Input • $2.4/M Output • 262144 Context
- **[Qwen3 235B A22B Instruct 2507](https://fireworks.ai/models/fireworks/qwen3-235b-a22b-instruct-2507)**: LLM · $0.22/M Input • $0.88/M Output • 262144 Context
- **[Qwen3 Coder 480B A35B Instruct](https://fireworks.ai/models/fireworks/qwen3-coder-480b-a35b-instruct)**: LLM · $0.45/M Input • $1.8/M Output • 262144 Context
- **[DeepSeek R1 (Fast)](https://fireworks.ai/models/fireworks/deepseek-r1)**: LLM · $1.35/M Input • $5.4/M Output • 163840 Context
- **[Deepseek R1 05/28](https://fireworks.ai/models/fireworks/deepseek-r1-0528)**: LLM · $1.35/M Input • $5.4/M Output • 163840 Context
- **[MiniMax-M2.1](https://fireworks.ai/models/fireworks/minimax-m2p1)**: LLM · $0.3/M Input • $1.2/M Output • 196608 Context
- **[MiniMax-M2.5](https://fireworks.ai/models/fireworks/minimax-m2p5)**: LLM · $0.3/M Input • $1.2/M Output • 196608 Context
- **[Qwen3 Coder 30B A3B Instruct](https://fireworks.ai/models/fireworks/qwen3-coder-30b-a3b-instruct)**: LLM · $0.15/M Input • $0.6/M Output • 262144 Context
- **[Beam-1.0-501B-A23B-NVFP4](https://fireworks.ai/models/fireworks/beam-1p0-501b-a23b-nvfp4)**: New · LLM · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[BGE-M3](https://fireworks.ai/models/fireworks/bge-m3)**: New · $0/M Input • $0/M Output • 8192 Context
- **[Chronos Hermes 13B v2](https://fireworks.ai/models/fireworks/chronos-hermes-13b-v2)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Code Llama 13B](https://fireworks.ai/models/fireworks/code-llama-13b)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[Code Llama 13B Instruct](https://fireworks.ai/models/fireworks/code-llama-13b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[Code Llama 13B Python](https://fireworks.ai/models/fireworks/code-llama-13b-python)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[Code Llama 34B](https://fireworks.ai/models/fireworks/code-llama-34b)**: LLM · $0.9/M Input • $0.9/M Output • 16384 Context
- **[Code Llama 34B Instruct](https://fireworks.ai/models/fireworks/code-llama-34b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 16384 Context
- **[Code Llama 34B Python](https://fireworks.ai/models/fireworks/code-llama-34b-python)**: LLM · $0.9/M Input • $0.9/M Output • 16384 Context
- **[Code Llama 70B](https://fireworks.ai/models/fireworks/code-llama-70b)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Code Llama 70B Instruct](https://fireworks.ai/models/fireworks/code-llama-70b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Code Llama 70B Python](https://fireworks.ai/models/fireworks/code-llama-70b-python)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Code Llama 7B](https://fireworks.ai/models/fireworks/code-llama-7b)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[Code Llama 7B Instruct](https://fireworks.ai/models/fireworks/code-llama-7b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[Code Llama 7B Python](https://fireworks.ai/models/fireworks/code-llama-7b-python)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[CodeGemma 2B](https://fireworks.ai/models/fireworks/codegemma-2b)**: LLM · $0.1/M Input • $0.1/M Output • 8192 Context
- **[CodeGemma 7B](https://fireworks.ai/models/fireworks/codegemma-7b)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[CodeQwen 1.5 7B](https://fireworks.ai/models/fireworks/code-qwen-1p5-7b)**: LLM · $0.2/M Input • $0.2/M Output • 65536 Context
- **[Cogito 671B v2.1](https://fireworks.ai/models/cogito/cogito-671b-v2-p1)**: LLM · $1.2/M Input • $1.2/M Output • 163840 Context
- **[Cogito v1 Preview Llama 3B](https://fireworks.ai/models/fireworks/cogito-v1-preview-llama-3b)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Cogito v1 Preview Llama 70B](https://fireworks.ai/models/fireworks/cogito-v1-preview-llama-70b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Cogito v1 Preview Llama 8B](https://fireworks.ai/models/fireworks/cogito-v1-preview-llama-8b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Cogito v1 Preview Qwen 14B](https://fireworks.ai/models/fireworks/cogito-v1-preview-qwen-14b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Cogito v1 Preview Qwen 32B](https://fireworks.ai/models/fireworks/cogito-v1-preview-qwen-32b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[DBRX Instruct](https://fireworks.ai/models/fireworks/dbrx-instruct)**: LLM · $1.2/M Input • $1.2/M Output • 32768 Context
- **[DeepSeek Coder 1.3B Base](https://fireworks.ai/models/fireworks/deepseek-coder-1b-base)**: LLM · $0.1/M Input • $0.1/M Output • 16384 Context
- **[DeepSeek Coder 33B Instruct](https://fireworks.ai/models/fireworks/deepseek-coder-33b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 16384 Context
- **[DeepSeek Coder 7B Base](https://fireworks.ai/models/fireworks/deepseek-coder-7b-base)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[DeepSeek Coder 7B Base v1.5](https://fireworks.ai/models/fireworks/deepseek-coder-7b-base-v1p5)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[DeepSeek Coder 7B Instruct v1.5](https://fireworks.ai/models/fireworks/deepseek-coder-7b-instruct-v1p5)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[DeepSeek Coder V2 Instruct](https://fireworks.ai/models/fireworks/deepseek-coder-v2-instruct)**: LLM · $1.2/M Input • $1.2/M Output • 32768 Context
- **[DeepSeek Coder V2 Lite Base](https://fireworks.ai/models/fireworks/deepseek-coder-v2-lite-base)**: LLM · $0.5/M Input • $0.5/M Output • 163840 Context
- **[DeepSeek Coder V2 Lite Instruct](https://fireworks.ai/models/fireworks/deepseek-coder-v2-lite-instruct)**: LLM · $0.5/M Input • $0.5/M Output • 163840 Context
- **[DeepSeek Prover V2](https://fireworks.ai/models/fireworks/deepseek-prover-v2)**: LLM · $1.2/M Input • $1.2/M Output • 163840 Context
- **[DeepSeek R1 (Basic)](https://fireworks.ai/models/fireworks/deepseek-r1-basic)**: LLM · $0.55/M Input • $2.19/M Output • 163840 Context
- **[DeepSeek R1 0528 Distill Qwen3 8B](https://fireworks.ai/models/fireworks/deepseek-r1-0528-distill-qwen3-8b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[DeepSeek R1 Distill Llama 70B](https://fireworks.ai/models/fireworks/deepseek-r1-distill-llama-70b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[DeepSeek R1 Distill Llama 8B](https://fireworks.ai/models/fireworks/deepseek-r1-distill-llama-8b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[DeepSeek R1 Distill Qwen 1.5B](https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-1p5b)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[DeepSeek R1 Distill Qwen 14B](https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-14b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[DeepSeek R1 Distill Qwen 32B](https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-32b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[DeepSeek R1 Distill Qwen 7B](https://fireworks.ai/models/fireworks/deepseek-r1-distill-qwen-7b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[DeepSeek V2 Lite Chat](https://fireworks.ai/models/fireworks/deepseek-v2-lite-chat)**: LLM · $0.5/M Input • $0.5/M Output • 163840 Context
- **[DeepSeek V2.5](https://fireworks.ai/models/fireworks/deepseek-v2p5)**: LLM · $1.2/M Input • $1.2/M Output • 32768 Context
- **[DeepSeek V3](https://fireworks.ai/models/fireworks/deepseek-v3)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Deepseek V3 03-24](https://fireworks.ai/models/fireworks/deepseek-v3-0324)**: LLM · $0.9/M Input • $0.9/M Output • 163840 Context
- **[DeepSeek V3.1 Terminus](https://fireworks.ai/models/deepseek-ai/deepseek-v3p1-terminus)**: LLM · $0.56/M Input • $1.68/M Output • 163840 Context
- **[Deepseek v3.2](https://fireworks.ai/models/fireworks/deepseek-v3p2)**: LLM · $0.56/M Input • $1.68/M Output • 163840 Context
- **[DeepSeek-V4-Flash](https://fireworks.ai/models/fireworks/deepseek-v4-flash)**: LLM · $0.14/M Input • $0.28/M Output • 1048576 Context
- **[DeepSeek-V4-Flash-Vision-Exp](https://fireworks.ai/models/deepseek-ai/deepseek-v4-flash-vision-exp)**: Vision · $0.22/M Input • $0.66/M Output • 1048576 Context
- **[Devstral Small 2 24B Instruct 2512](https://fireworks.ai/models/fireworks/devstral-small-2-24b-instruct-2512)**: Vision · $0.9/M Input • $0.9/M Output
- **[Devstral-Small-2505](https://fireworks.ai/models/fireworks/devstral-small-2505)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Dobby Mini Unhinged Plus Llama 3.1 8B](https://fireworks.ai/models/sentientfoundation-serverless/dobby-mini-unhinged-plus-llama-3-1-8b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Dobby-Unhinged-Llama-3.3-70B](https://fireworks.ai/models/sentientfoundation/dobby-unhinged-llama-3-3-70b-new)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Dolphin 2.6 Mixtral 8x7b](https://fireworks.ai/models/fireworks/dolphin-2p6-mixtral-8x7b)**: LLM · $0.5/M Input • $0.5/M Output • 32768 Context
- **[Dolphin 2.9.2 Qwen2 72B](https://fireworks.ai/models/fireworks/dolphin-2-9-2-qwen2-72b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Drex 2.0](https://fireworks.ai/models/fireworks/drex-v2-0)**: New · LLM · $0.9/M Input • $0.9/M Output • 262144 Context
- **[ERNIE-4.5-21B-A3B-PT](https://fireworks.ai/models/fireworks/ernie-4p5-21b-a3b-pt)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[ERNIE-4.5-300B-A47B-PT](https://fireworks.ai/models/fireworks/ernie-4p5-300b-a47b-pt)**: LLM · $1.2/M Input • $1.2/M Output • 131072 Context
- **[FARE-20B](https://fireworks.ai/models/fireworks/fare-20b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[FireFunction V1](https://fireworks.ai/models/fireworks/firefunction-v1)**: LLM · $0.5/M Input • $0.5/M Output • 32768 Context
- **[FireFunction V2](https://fireworks.ai/models/fireworks/firefunction-v2)**: LLM · $0.9/M Input • $0.9/M Output
- **[FireLLaVA 13B](https://fireworks.ai/models/fireworks/firellava-13b)**: Vision · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Firesearch OCR V6](https://fireworks.ai/models/fireworks/firesearch-ocr-v6)**: Vision · $0.2/M Input • $0.2/M Output • 8192 Context
- **[FLUX.1 \[dev\] ControlNet](https://fireworks.ai/models/fireworks/flux-1-dev-controlnet-union)**: LLM · $0.001/step Input • $0.001/step Output
- **[FLUX.1 \[schnell\]](https://fireworks.ai/models/fireworks/flux-1-schnell)**: LLM · $0.1/M Input • $0.1/M Output
- **[Gemma 2 9B Instruct](https://fireworks.ai/models/fireworks/gemma2-9b-it)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[Gemma 2B Instruct](https://fireworks.ai/models/fireworks/gemma-2b-it)**: LLM · $0.1/M Input • $0.1/M Output • 8192 Context
- **[Gemma 3 12B Instruct](https://fireworks.ai/models/fireworks/gemma-3-12b-it)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Gemma 3 1B Instruct](https://fireworks.ai/models/fireworks/gemma-3-1b-it)**: LLM · $0.1/M Input • $0.1/M Output
- **[Gemma 3 27B Instruct](https://fireworks.ai/models/fireworks/gemma-3-27b-it)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Gemma 3 4B Instruct](https://fireworks.ai/models/fireworks/gemma-3-4b-it)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Gemma 4 26B A4B IT](https://fireworks.ai/models/fireworks/gemma-4-26b-a4b-it)**: Vision · $0.5/M Input • $0.5/M Output • 262144 Context
- **[Gemma 4 31B IT](https://fireworks.ai/models/fireworks/gemma-4-31b-it)**: Vision · $0.9/M Input • $0.9/M Output • 262144 Context
- **[Gemma 4 E4B](https://fireworks.ai/models/fireworks/gemma-4-e4b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Gemma 7B](https://fireworks.ai/models/fireworks/gemma-7b)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[Gemma 7B Instruct](https://fireworks.ai/models/fireworks/gemma-7b-it)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[GLM 5.1](https://fireworks.ai/models/fireworks/glm-5p1)**: LLM · $1.4/M Input • $4.4/M Output • 202752 Context
- **[GLM 5.2 FP8](https://fireworks.ai/models/fireworks/glm-5p2-fp8)**: LLM · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[GLM-4.5](https://fireworks.ai/models/fireworks/glm-4p5)**: LLM · $0.55/M Input • $2.19/M Output • 131072 Context
- **[GLM-4.5-Air](https://fireworks.ai/models/fireworks/glm-4p5-air)**: LLM · $0.22/M Input • $0.88/M Output • 131072 Context
- **[GLM-4.5V](https://fireworks.ai/models/fireworks/glm-4p5v)**: Vision · $1.2/M Input • $1.2/M Output • 131072 Context
- **[GLM-4.7](https://fireworks.ai/models/fireworks/glm-4p7)**: LLM · $0.6/M Input • $2.2/M Output • 202752 Context
- **[GLM-4.7 Flash](https://fireworks.ai/models/fireworks/glm-4p7-flash)**: LLM · $0.5/M Input • $0.5/M Output • 202752 Context
- **[Hermes 2 Pro Mistral 7B](https://fireworks.ai/models/fireworks/hermes-2-pro-mistral-7b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Inkling](https://fireworks.ai/models/fireworks/inkling)**: Vision · $1/M Input • $4.05/M Output • 1048576 Context
- **[Inkling Small](https://fireworks.ai/models/fireworks/inkling-small)**: Vision · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[InternVL3 38B](https://fireworks.ai/models/fireworks/internvl3-38b)**: Vision · $0.9/M Input • $0.9/M Output • 16384 Context
- **[InternVL3 78B](https://fireworks.ai/models/fireworks/internvl3-78b)**: Vision · $0.9/M Input • $0.9/M Output • 16384 Context
- **[InternVL3 8B](https://fireworks.ai/models/fireworks/internvl3-8b)**: Vision · $0.2/M Input • $0.2/M Output • 16384 Context
- **[Kalshi-tuned Muse Glimmer 30B](https://fireworks.ai/models/fireworks/kalshi-glimmer-decision-v1)**: New · LLM · $0.35/M Input • $1.5/M Output
- **[KAT Coder](https://fireworks.ai/models/fireworks/kat-coder)**: LLM · $0.9/M Input • $0.9/M Output • 262144 Context
- **[KAT Dev 32B](https://fireworks.ai/models/fireworks/kat-dev-32b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[KAT Dev 72B Exp](https://fireworks.ai/models/fireworks/kat-dev-72b-exp)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Kimi K2 Instruct](https://fireworks.ai/models/fireworks/kimi-k2-instruct)**: LLM · $0.6/M Input • $2.5/M Output • 131072 Context
- **[Kimi K2.5](https://fireworks.ai/models/fireworks/kimi-k2p5)**: Vision · $0.6/M Input • $3/M Output • 262144 Context
- **[Kimi K2.6](https://fireworks.ai/models/fireworks/kimi-k2p6)**: Vision · $0.95/M Input • $4/M Output • 262144 Context
- **[Ling 3 Flash](https://fireworks.ai/models/fireworks/ling-3-flash)**: LLM · $0/M Input • $0/M Output • 256000 Context
- **[Ling 3 Flash Fin](https://fireworks.ai/models/fireworks/ling-3-flash-fin)**: LLM · $0/M Input • $0/M Output • 262144 Context
- **[Llama 2 13B](https://fireworks.ai/models/fireworks/llama-v2-13b)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Llama 2 13B Chat](https://fireworks.ai/models/fireworks/llama-v2-13b-chat)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Llama 2 70B](https://fireworks.ai/models/fireworks/llama-v2-70b)**: LLM · $0.1/M Input • $0.1/M Output • 4096 Context
- **[Llama 2 70B Chat](https://fireworks.ai/models/fireworks/llama-v2-70b-chat)**: LLM · $0.9/M Input • $0.9/M Output • 2048 Context
- **[Llama 2 7B](https://fireworks.ai/models/fireworks/llama-v2-7b)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Llama 2 7B Chat](https://fireworks.ai/models/fireworks/llama-v2-7b-chat)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Llama 3 70B Instruct](https://fireworks.ai/models/fireworks/llama-v3-70b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 8192 Context
- **[Llama 3 70B Instruct (HF version)](https://fireworks.ai/models/fireworks/llama-v3-70b-instruct-hf)**: LLM · $0.9/M Input • $0.9/M Output • 8192 Context
- **[Llama 3 8B](https://fireworks.ai/models/fireworks/llama-v3-8b)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[Llama 3 8B Instruct (HF version)](https://fireworks.ai/models/fireworks/llama-v3-8b-instruct-hf)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[Llama 3.1 405B Instruct](https://fireworks.ai/models/fireworks/llama-v3p1-405b-instruct)**: LLM · $3/M Input • $3/M Output • 131072 Context
- **[Llama 3.1 405B Instruct Long](https://fireworks.ai/models/fireworks/llama-v3p1-405b-instruct-long)**: LLM · $0.1/M Input • $0.1/M Output
- **[Llama 3.1 70B Instruct](https://fireworks.ai/models/fireworks/llama-v3p1-70b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Llama 3.1 70B Instruct 1B](https://fireworks.ai/models/fireworks/llama-v3p1-70b-instruct-1b)**: LLM · $0.1/M Input • $0.1/M Output
- **[Llama 3.1 8B Instruct](https://fireworks.ai/models/fireworks/llama-v3p1-8b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Llama 3.1 Nemotron 70B](https://fireworks.ai/models/fireworks/llama-v3p1-nemotron-70b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Llama 3.2 11B Vision Instruct](https://fireworks.ai/models/fireworks/llama-v3p2-11b-vision-instruct)**: Vision · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Llama 3.2 1B](https://fireworks.ai/models/fireworks/llama-v3p2-1b)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Llama 3.2 1B Instruct](https://fireworks.ai/models/fireworks/llama-v3p2-1b-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Llama 3.2 3B](https://fireworks.ai/models/fireworks/llama-v3p2-3b)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Llama 3.2 3B Instruct](https://fireworks.ai/models/fireworks/llama-v3p2-3b-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Llama 3.2 90B Vision Instruct](https://fireworks.ai/models/fireworks/llama-v3p2-90b-vision-instruct)**: Vision · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Llama 4 Maverick Instruct (Basic)](https://fireworks.ai/models/fireworks/llama4-maverick-instruct-basic)**: Vision · $0.22/M Input • $0.88/M Output • 1048576 Context
- **[Llama 4 Scout Instruct (Basic)](https://fireworks.ai/models/fireworks/llama4-scout-instruct-basic)**: Vision · $0.15/M Input • $0.6/M Output • 1048576 Context
- **[Llama Guard 3 8B](https://fireworks.ai/models/fireworks/llama-guard-3-8b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Llama Guard 7B](https://fireworks.ai/models/fireworks/llamaguard-7b)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Llama Guard v2 8B](https://fireworks.ai/models/fireworks/llama-guard-2-8b)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[Llama Guard v3 1B](https://fireworks.ai/models/fireworks/llama-guard-3-1b)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[LLaVA V1.6 Yi 34B](https://fireworks.ai/models/fireworks/llava-yi-34b)**: Vision · $0.9/M Input • $0.9/M Output • 4096 Context
- **[MiniMax M2.7](https://fireworks.ai/models/fireworks/minimax-m2p7)**: LLM · $1.2/M Input • $1.2/M Output • 196608 Context
- **[MiniMax-M1-80k](https://fireworks.ai/models/fireworks/minimax-m1-80k)**: LLM · $0.1/M Input • $0.1/M Output
- **[MiniMax-M2](https://fireworks.ai/models/fireworks/minimax-m2)**: LLM · $0.3/M Input • $1.2/M Output • 196608 Context
- **[Ministral 3 14B Instruct 2512](https://fireworks.ai/models/fireworks/ministral-3-14b-instruct-2512)**: Vision · $0.2/M Input • $0.2/M Output • 256000 Context
- **[Ministral 3 3B Instruct 2512](https://fireworks.ai/models/fireworks/ministral-3-3b-instruct-2512)**: Vision · $0.1/M Input • $0.1/M Output • 256000 Context
- **[Ministral 3 8B Instruct 2512](https://fireworks.ai/models/fireworks/ministral-3-8b-instruct-2512)**: Vision · $0.2/M Input • $0.2/M Output • 256000 Context
- **[MiroThinker-1.7](https://fireworks.ai/models/fireworks/mirothinker-1p7)**: LLM · $1.2/M Input • $1.2/M Output • 262144 Context
- **[Mistal 7B Instruct V0.1](https://fireworks.ai/models/fireworks/mistral-7b-instruct-4k)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Mistral 7B](https://fireworks.ai/models/fireworks/mistral-7b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Mistral 7B Instruct v0.2](https://fireworks.ai/models/fireworks/mistral-7b-instruct-v0p2)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Mistral 7B Instruct v0.3](https://fireworks.ai/models/fireworks/mistral-7b-instruct-v3)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Mistral 7B OpenOrca](https://fireworks.ai/models/fireworks/openorca-7b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Mistral 7B v0.2](https://fireworks.ai/models/fireworks/mistral-7b-v0p2)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Mistral Large 3 675B Instruct 2512](https://fireworks.ai/models/fireworks/mistral-large-3-fp8)**: Vision · $1.2/M Input • $1.2/M Output • 256000 Context
- **[Mistral Nemo Base 2407](https://fireworks.ai/models/fireworks/mistral-nemo-base-2407)**: LLM · $0.2/M Input • $0.2/M Output • 128000 Context
- **[Mistral Nemo Instruct 2407](https://fireworks.ai/models/fireworks/mistral-nemo-instruct-2407)**: LLM · $0.2/M Input • $0.2/M Output • 128000 Context
- **[Mistral Small 24B Instruct 2501](https://fireworks.ai/models/fireworks/mistral-small-24b-instruct-2501)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Mixtral 8x7B v0.1](https://fireworks.ai/models/fireworks/mixtral-8x7b)**: LLM · $0.5/M Input • $0.5/M Output • 32768 Context
- **[Mixtral Moe 8x22B](https://fireworks.ai/models/fireworks/mixtral-8x22b)**: LLM · $1.2/M Input • $1.2/M Output • 65536 Context
- **[Mixtral MoE 8x22B Instruct](https://fireworks.ai/models/fireworks/mixtral-8x22b-instruct)**: LLM · $1.2/M Input • $1.2/M Output • 65536 Context
- **[Mixtral MoE 8x7B Instruct](https://fireworks.ai/models/fireworks/mixtral-8x7b-instruct)**: LLM · $0.5/M Input • $0.5/M Output • 32768 Context
- **[Mixtral MoE 8x7B Instruct (HF version)](https://fireworks.ai/models/fireworks/mixtral-8x7b-instruct-hf)**: LLM · $0.5/M Input • $0.5/M Output • 32768 Context
- **[Molmo2-4B](https://fireworks.ai/models/fireworks/molmo2-4b)**: Vision · $0.1/M Input • $0.1/M Output • 36864 Context
- **[Molmo2-8B](https://fireworks.ai/models/fireworks/molmo2-8b)**: Vision · $0.2/M Input • $0.2/M Output • 36864 Context
- **[Muse Spark Open 816B-A42B NVFP4](https://fireworks.ai/models/fireworks/muse-spark-open-nvfp4)**: Vision · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[MythoMax L2 13B](https://fireworks.ai/models/fireworks/mythomax-l2-13b)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Nemotron 3 Embed 8B](https://fireworks.ai/models/fireworks/nemotron-3-embed-8b-bf16)**: $0/M Input • $0/M Output • 32768 Context
- **[Nemotron Lightning 3.5 30B A3B](https://fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b)**: New · LLM • Serverless · $0.05/M Input • $0.2/M Output • 262144 Context
- **[Nous Capybara 7B V1.9](https://fireworks.ai/models/fireworks/nous-capybara-7b-v1p9)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Nous Hermes 2 Yi 34B](https://fireworks.ai/models/fireworks/nous-hermes-2-yi-34b)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Nous Hermes Llama2 13B](https://fireworks.ai/models/fireworks/nous-hermes-llama2-13b)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Nous Hermes Llama2 70B](https://fireworks.ai/models/fireworks/nous-hermes-llama2-70b)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Nous Hermes Llama2 7B](https://fireworks.ai/models/fireworks/nous-hermes-llama2-7b)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Nouse Capybara 34B V1.9](https://fireworks.ai/models/fireworks/yi-34b-200k-capybara)**: LLM · $0.9/M Input • $0.9/M Output • 200000 Context
- **[Nouse Hermes 2 Mixtral 8x7B DPO](https://fireworks.ai/models/fireworks/nous-hermes-2-mixtral-8x7b-dpo)**: LLM · $0.5/M Input • $0.5/M Output • 32768 Context
- **[NVIDIA Nemotron 3 Nano Omni 30B A3B](https://fireworks.ai/models/fireworks/nvidia-nemotron-3-nano-omni-30b-a3b)**: LLM · $0.9/M Input • $0.9/M Output • 262144 Context
- **[NVIDIA Nemotron 3 Super 120B A12B BF16](https://fireworks.ai/models/fireworks/nemotron-3-super-120b-a12b-bf16)**: LLM · $0.9/M Input • $0.9/M Output • 262144 Context
- **[NVIDIA Nemotron 3.5 Super VL 120B A12B BF16](https://fireworks.ai/models/fireworks/nvidia-nemotron-3p5-super-vl-120b-a12b-bf16)**: Vision · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4](https://fireworks.ai/models/fireworks/nvidia-nemotron-3p5-super-vl-120b-a12b-nvfp4)**: Vision · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[NVIDIA Nemotron Nano 12B v2](https://fireworks.ai/models/fireworks/nvidia-nemotron-nano-12b-v2)**: LLM · $0.2/M Input • $0.2/M Output • 128000 Context
- **[NVIDIA Nemotron Nano 2 VL](https://fireworks.ai/models/fireworks/nemotron-nano-v2-12b-vl)**: Vision · $0.2/M Input • $0.2/M Output • 131072 Context
- **[NVIDIA Nemotron Nano 3 30B A3B](https://fireworks.ai/models/fireworks/nemotron-nano-3-30b-a3b)**: LLM · $0.5/M Input • $0.5/M Output
- **[NVIDIA Nemotron Nano 9B v2](https://fireworks.ai/models/fireworks/nvidia-nemotron-nano-9b-v2)**: LLM · $0.2/M Input • $0.2/M Output • 128000 Context
- **[OpenAI gpt-oss-safeguard-120b](https://fireworks.ai/models/fireworks/gpt-oss-safeguard-120b)**: LLM · $1.2/M Input • $1.2/M Output • 131072 Context
- **[OpenAI gpt-oss-safeguard-20b](https://fireworks.ai/models/fireworks/gpt-oss-safeguard-20b)**: LLM · $0.5/M Input • $0.5/M Output • 131072 Context
- **[OpenChat 3.5 0106](https://fireworks.ai/models/fireworks/openchat-3p5-0106-7b)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[OpenHermes 2 Mistral 7B](https://fireworks.ai/models/fireworks/openhermes-2-mistral-7b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[OpenHermes 2.5 Mistral 7B](https://fireworks.ai/models/fireworks/openhermes-2p5-mistral-7b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[PaddleOCR VL 1.6](https://fireworks.ai/models/fireworks/paddleocr-vl-1-6)**: Vision · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Phi-2 3B](https://fireworks.ai/models/fireworks/phi-2-3b)**: LLM · $0.1/M Input • $0.1/M Output • 2048 Context
- **[Phi-3 Mini 128k Instruct](https://fireworks.ai/models/fireworks/phi-3-mini-128k-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Phi-3.5 Vision Instruct](https://fireworks.ai/models/fireworks/phi-3-vision-128k-instruct)**: Vision · $0.2/M Input • $0.2/M Output • 32064 Context
- **[Phind CodeLlama 34B Python v1](https://fireworks.ai/models/fireworks/phind-code-llama-34b-python-v1)**: LLM · $0.9/M Input • $0.9/M Output • 16384 Context
- **[Phind CodeLlama 34B v1](https://fireworks.ai/models/fireworks/phind-code-llama-34b-v1)**: LLM · $0.9/M Input • $0.9/M Output • 16384 Context
- **[Phind CodeLlama 34B v2](https://fireworks.ai/models/fireworks/phind-code-llama-34b-v2)**: LLM · $0.9/M Input • $0.9/M Output • 16384 Context
- **[Pythia 12B](https://fireworks.ai/models/fireworks/pythia-12b)**: LLM · $0.2/M Input • $0.2/M Output • 2048 Context
- **[Qwen 3 4B Instruct 2507](https://fireworks.ai/models/fireworks/qwen3-4b-instruct-2507)**: LLM · $0.2/M Input • $0.2/M Output • 262144 Context
- **[Qwen 3.5 122B A10B](https://fireworks.ai/models/fireworks/qwen3p5-122b-a10b)**: Vision · $1.2/M Input • $1.2/M Output • 262144 Context
- **[Qwen 3.5 35B A3B](https://fireworks.ai/models/fireworks/qwen3p5-35b-a3b)**: LLM · $0.5/M Input • $0.5/M Output • 262144 Context
- **[Qwen QWQ 32B Preview](https://fireworks.ai/models/fireworks/qwen-qwq-32b-preview)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen1.5 72B Chat](https://fireworks.ai/models/fireworks/qwen1p5-72b-chat)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2 72B Instruct](https://fireworks.ai/models/fireworks/qwen2-72b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2 7B Instruct](https://fireworks.ai/models/fireworks/qwen2-7b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2-VL 2B Instruct](https://fireworks.ai/models/fireworks/qwen2-vl-2b-instruct)**: Vision · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2-VL 72B Instruct](https://fireworks.ai/models/fireworks/qwen2-vl-72b-instruct)**: Vision · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2-VL 7B Instruct](https://fireworks.ai/models/fireworks/qwen2-vl-7b-instruct)**: Vision · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2.5 0.5B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-0p5b-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5 1.5B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-1p5b-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5 14B](https://fireworks.ai/models/fireworks/qwen2p5-14b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Qwen2.5 14B Instruct](https://fireworks.ai/models/fireworks/qwen-v2p5-14b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2.5 32B](https://fireworks.ai/models/fireworks/qwen2p5-32b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Qwen2.5 32B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-32b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2.5 72B](https://fireworks.ai/models/fireworks/qwen2p5-72b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Qwen2.5 72B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-72b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2.5 7B](https://fireworks.ai/models/fireworks/qwen-v2p5-7b)**: LLM · $0.2/M Input • $0.2/M Output • 131072 Context
- **[Qwen2.5 7B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-7b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2.5-Coder 0.5B](https://fireworks.ai/models/fireworks/qwen2p5-coder-0p5b)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5-Coder 0.5B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-coder-0p5b-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5-Coder 1.5B](https://fireworks.ai/models/fireworks/qwen2p5-coder-1p5b)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5-Coder 1.5B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-coder-1p5b-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5-Coder 14B](https://fireworks.ai/models/fireworks/qwen2p5-coder-14b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2.5-Coder 14B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-coder-14b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2.5-Coder 32B](https://fireworks.ai/models/fireworks/qwen2p5-coder-32b)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2.5-Coder 32B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2.5-Coder 32B Instruct 128K](https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct-128k)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Qwen2.5-Coder 32B Instruct 32K RoPE](https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct-32k-rope)**: LLM · $0.9/M Input • $0.9/M Output • 32768 Context
- **[Qwen2.5-Coder 32B Instruct 64k](https://fireworks.ai/models/fireworks/qwen2p5-coder-32b-instruct-64k)**: LLM · $0.9/M Input • $0.9/M Output • 65536 Context
- **[Qwen2.5-Coder 3B](https://fireworks.ai/models/fireworks/qwen2p5-coder-3b)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5-Coder 3B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-coder-3b-instruct)**: LLM · $0.1/M Input • $0.1/M Output • 32768 Context
- **[Qwen2.5-Coder 7B](https://fireworks.ai/models/fireworks/qwen2p5-coder-7b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2.5-Coder 7B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-coder-7b-instruct)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Qwen2.5-Math 72B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-math-72b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Qwen2.5-VL 32B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-vl-32b-instruct)**: Vision · $0.9/M Input • $0.9/M Output • 128000 Context
- **[Qwen2.5-VL 3B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-vl-3b-instruct)**: Vision · $0.2/M Input • $0.2/M Output • 128000 Context
- **[Qwen2.5-VL 72B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-vl-72b-instruct)**: Vision · $0.9/M Input • $0.9/M Output • 128000 Context
- **[Qwen2.5-VL 7B Instruct](https://fireworks.ai/models/fireworks/qwen2p5-vl-7b-instruct)**: Vision · $0.2/M Input • $0.2/M Output • 128000 Context
- **[Qwen3 0.6B](https://fireworks.ai/models/fireworks/qwen3-0p6b)**: LLM · $0.1/M Input • $0.1/M Output • 40960 Context
- **[Qwen3 1.7B](https://fireworks.ai/models/fireworks/qwen3-1p7b)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Qwen3 1.7B fp8 model used for drafting](https://fireworks.ai/models/fireworks/qwen3-1p7b-fp8-draft)**: LLM · $0.1/M Input • $0.1/M Output • 262144 Context
- **[Qwen3 1.7B fp8 model used for drafting for 131072 context](https://fireworks.ai/models/fireworks/qwen3-1p7b-fp8-draft-131072)**: LLM · $0.1/M Input • $0.1/M Output • 131072 Context
- **[Qwen3 1.7B fp8 model used for drafting for 40960 context length](https://fireworks.ai/models/fireworks/qwen3-1p7b-fp8-draft-40960)**: LLM · $0.1/M Input • $0.1/M Output • 40960 Context
- **[Qwen3 14B](https://fireworks.ai/models/fireworks/qwen3-14b)**: LLM · $0.2/M Input • $0.2/M Output • 40960 Context
- **[Qwen3 30B A3B Instruct 2507](https://fireworks.ai/models/fireworks/qwen3-30b-a3b-instruct-2507)**: LLM · $0.5/M Input • $0.5/M Output • 262144 Context
- **[Qwen3 30B A3B Thinking 2507](https://fireworks.ai/models/fireworks/qwen3-30b-a3b-thinking-2507)**: LLM · $0.9/M Input • $0.9/M Output • 262144 Context
- **[Qwen3 30B-A3B](https://fireworks.ai/models/fireworks/qwen3-30b-a3b)**: LLM · $0.15/M Input • $0.6/M Output • 131072 Context
- **[Qwen3 32B](https://fireworks.ai/models/fireworks/qwen3-32b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Qwen3 4B](https://fireworks.ai/models/fireworks/qwen3-4b)**: LLM · $0.2/M Input • $0.2/M Output • 40960 Context
- **[Qwen3 8B](https://fireworks.ai/models/fireworks/qwen3-8b)**: LLM · $0.2/M Input • $0.2/M Output • 40960 Context
- **[Qwen3 Coder 480B Instruct BF16](https://fireworks.ai/models/fireworks/qwen3-coder-480b-instruct-bf16)**: LLM · $1.2/M Input • $1.2/M Output • 262144 Context
- **[Qwen3 Embedding 0.6B](https://fireworks.ai/models/fireworks/qwen3-embedding-0p6b)**: LLM · $0/M Input • $0/M Output • 32768 Context
- **[Qwen3 Embedding 4B](https://fireworks.ai/models/fireworks/qwen3-embedding-4b)**: LLM · $0/M Input • $0/M Output • 40960 Context
- **[Qwen3 Embedding 8B](https://fireworks.ai/models/fireworks/qwen3-embedding-8b)**: LLM • Serverless · $0.1/M Input • $0/M Output • 40960 Context
- **[Qwen3 Next 80B A3B Instruct](https://fireworks.ai/models/fireworks/qwen3-next-80b-a3b-instruct)**: LLM · $0.9/M Input • $0.9/M Output
- **[Qwen3 Next 80B A3B Thinking](https://fireworks.ai/models/fireworks/qwen3-next-80b-a3b-thinking)**: LLM · $0.9/M Input • $0.9/M Output
- **[Qwen3 Omni 30B A3B Instruct](https://fireworks.ai/models/fireworks/qwen3-omni-30b-a3b-instruct)**: Vision · $0.5/M Input • $0.5/M Output • 65536 Context
- **[Qwen3 Reranker 0.6B](https://fireworks.ai/models/fireworks/qwen3-reranker-0p6b)**: LLM · $0/M Input • $0/M Output • 40960 Context
- **[Qwen3 Reranker 4B](https://fireworks.ai/models/fireworks/qwen3-reranker-4b)**: LLM · $0/M Input • $0/M Output • 40960 Context
- **[Qwen3 Reranker 8B](https://fireworks.ai/models/fireworks/qwen3-reranker-8b)**: LLM • Serverless · $0/M Input • $0/M Output • 40960 Context
- **[Qwen3 VL 30B A3B Instruct](https://fireworks.ai/models/fireworks/qwen3-vl-30b-a3b-instruct)**: Vision · $0.15/M Input • $0.6/M Output • 262144 Context
- **[Qwen3 VL 30B A3B Thinking](https://fireworks.ai/models/fireworks/qwen3-vl-30b-a3b-thinking)**: Vision · $0.15/M Input • $0.6/M Output • 262144 Context
- **[Qwen3 VL 32B Instruct](https://fireworks.ai/models/fireworks/qwen3-vl-32b-instruct)**: Vision · $0.9/M Input • $0.9/M Output
- **[Qwen3-VL-8B-Instruct](https://fireworks.ai/models/fireworks/qwen3-vl-8b-instruct)**: Vision · $0.2/M Input • $0.2/M Output • 262144 Context
- **[Qwen3.5 27B](https://fireworks.ai/models/fireworks/qwen3p5-27b)**: Vision · $0.9/M Input • $0.9/M Output • 262144 Context
- **[Qwen3.5 397B A17B](https://fireworks.ai/models/fireworks/qwen3p5-397b-a17b)**: Vision · $0.6/M Input • $3.6/M Output • 262144 Context
- **[Qwen3.5 4B](https://fireworks.ai/models/fireworks/qwen3p5-4b)**: LLM · $0.2/M Input • $0.2/M Output • 262144 Context
- **[Qwen3.5 9B](https://fireworks.ai/models/fireworks/qwen3p5-9b)**: Vision · $0.2/M Input • $0.2/M Output • 262144 Context
- **[Qwen3.6 27B](https://fireworks.ai/models/fireworks/qwen3p6-27b)**: Vision · $0.9/M Input • $0.9/M Output • 262144 Context
- **[Qwen3.6-35B-A3B](https://fireworks.ai/models/fireworks/qwen3p6-35b-a3b)**: Vision · $0.5/M Input • $0.5/M Output • 262144 Context
- **[Qwen3.7 Plus](https://fireworks.ai/models/fireworks/qwen3p7-plus)**: Vision · $0.4/M Input • $1.6/M Output
- **[Qwen3.8 27B](https://fireworks.ai/models/fireworks/qwen3p8-27b)**: Vision · $0.9/M Input • $0.9/M Output • 262144 Context
- **[Qwen3.8-2.4T-A95B](https://fireworks.ai/models/fireworks/qwen3p8-2p4t-a95b)**: LLM · $2/M Input • $6/M Output • 262144 Context
- **[QWQ 32B](https://fireworks.ai/models/fireworks/qwq-32b)**: LLM · $0.9/M Input • $0.9/M Output • 131072 Context
- **[Reflection Beam-1.0-501B-A23B](https://fireworks.ai/models/fireworks/beam-1p0-501b-a23b)**: LLM · $1.2/M Input • $1.2/M Output • 1048576 Context
- **[Ripple-65B Preview](https://fireworks.ai/models/fireworks/ripple-65b-preview)**: New · LLM · $0.9/M Input • $0.9/M Output • 1048576 Context
- **[Rolm OCR](https://fireworks.ai/models/fireworks/rolm-ocr)**: Vision · $0.2/M Input • $0.2/M Output • 128000 Context
- **[Rune 26B-A4B](https://fireworks.ai/models/fireworks/rune)**: New · LLM • Serverless · $0.042/M Input • $0/M Output • 262144 Context
- **[Seed OSS 36B Instruct](https://fireworks.ai/models/fireworks/seed-oss-36b-instruct)**: LLM · $0.9/M Input • $0.9/M Output • 524288 Context
- **[Snorkel Mistral PairRM DPO](https://fireworks.ai/models/fireworks/snorkel-mistral-7b-pairrm-dpo)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Stable Code 3B](https://fireworks.ai/models/fireworks/stablecode-3b)**: LLM · $0.1/M Input • $0.1/M Output
- **[StarCoder 16B](https://fireworks.ai/models/fireworks/starcoder-16b)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[StarCoder 7B](https://fireworks.ai/models/fireworks/starcoder-7b)**: LLM · $0.2/M Input • $0.2/M Output • 8192 Context
- **[StarCoder2 15B](https://fireworks.ai/models/fireworks/starcoder2-15b)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[StarCoder2 3B](https://fireworks.ai/models/fireworks/starcoder2-3b)**: LLM · $0.1/M Input • $0.1/M Output • 16384 Context
- **[StarCoder2 7B](https://fireworks.ai/models/fireworks/starcoder2-7b)**: LLM · $0.2/M Input • $0.2/M Output • 16384 Context
- **[Step 5 Preview](https://fireworks.ai/models/fireworks/step-5-preview-fp8)**: LLM · $0.9/M Input • $0.9/M Output • 1048576 Context
- **[Step-3.7-Flash-NVFP4](https://fireworks.ai/models/fireworks/step-3p7-flash-nvfp4)**: Vision · $1.2/M Input • $1.2/M Output • 262144 Context
- **[Toppy M 7B](https://fireworks.ai/models/fireworks/toppy-m-7b)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
- **[Ultramarine 1 Flash](https://fireworks.ai/models/fireworks/ultramarine-1-flash-us)**: New · Vision • Serverless · $0.15/M Input • $0.5/M Output • 1048576 Context
- **[Voyage 4](https://fireworks.ai/models/fireworks/voyage-4)**: $0/M Input • $0/M Output • 40960 Context
- **[Voyage 4 Large](https://fireworks.ai/models/fireworks/voyage-4-large)**: $0/M Input • $0/M Output • 40960 Context
- **[Voyage 4 Lite](https://fireworks.ai/models/fireworks/voyage-4-lite)**: $0/M Input • $0/M Output • 40960 Context
- **[Voyage 4 Nano](https://fireworks.ai/models/fireworks/voyage-4-nano)**: $0/M Input • $0/M Output • 40960 Context
- **[Voyage Multimodal 3.5](https://fireworks.ai/models/fireworks/voyage-multimodal-3-5)**: $0/M Input • $0/M Output • 32768 Context
- **[Voyage ReRank 2.5](https://fireworks.ai/models/fireworks/voyage-rerank-2-5)**: $0/M Input • $0/M Output • 32768 Context
- **[Yi 34B](https://fireworks.ai/models/yi-01-ai/yi-34b)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Yi 34B Chat](https://fireworks.ai/models/yi-01-ai/yi-34b-chat)**: LLM · $0.9/M Input • $0.9/M Output • 4096 Context
- **[Yi 6B](https://fireworks.ai/models/yi-01-ai/yi-6b)**: LLM · $0.2/M Input • $0.2/M Output • 4096 Context
- **[Yi-Large](https://fireworks.ai/models/yi-01-ai/yi-large)**: LLM · $0/M Input • $0/M Output • 32768 Context
- **[Zephyr 7B Beta](https://fireworks.ai/models/fireworks/zephyr-7b-beta)**: LLM · $0.2/M Input • $0.2/M Output • 32768 Context
