Fireworks AI
Inference
Models
304
Frontier
1
Cheaper here
8
than the headline price
Dearer here
70
than the headline price
Cheapest listing per model, USD per million tokens.
| Model | Here, input / output | Released |
|---|---|---|
| gpt-oss-safeguard-120b OpenAI · Moderation | $1.20 / $1.20 +357% vs Amazon Bedrock | - |
| Kimi K3.1 Pro Moonshot AIkimi-k3p1-pro | $2.00 / $10.00 | Oct 2026 |
| MiniMax M3.1 Flash MiniMaxminimax-m3p1-flash | $0.15 / $0.60 | Oct 2026 |
| Muse Spark Open | $1.25 / $4.25 | Oct 2026 |
| DeepSeek Flash DeepSeekdeepseek-flash-latest | $0.30 / $1.20 | Sep 2026 |
| DeepSeek V4.1 Flash DeepSeekdeepseek-v4p1-flash | $0.30 / $1.20 +150% vs DeepInfra | Sep 2026 |
| Qwen3.8 Max Alibaba Qwenqwen3p8-max | $2.00 / $6.00 | Sep 2026 |
| GLM 5.3 Flash Zhipu AIglm-5p3-flash | $0.15 / $0.50 | Aug 2026 |
| DeepSeek V4 Flash Vision Exp | $0.22 / $0.66 −37% vs DeepSeek | Aug 2026 |
| GLM 5.3 Zhipu AIglm-5p3 | $1.40 / $4.40 | Aug 2026 |
| Muse Glimmer 30B | $0.35 / $1.50 +21% vs DeepInfra | Aug 2026 |
| Inkling | $1.00 / $4.05 +2% vs DeepInfra | Jul 2026 |
| Kimi K3 | $3.00 / $15.00 | Jul 2026 |
| GLM 5.2 Zhipu AIglm-5p2 | $1.40 / $4.40 | Jun 2026 |
| Kimi K2.7 Code Moonshot AIkimi-k2p7-code | $0.95 / $4.00 | Jun 2026 |
| Qwen3.7 Plus Alibaba Qwenqwen3p7-plus | $0.40 / $1.60 | Jun 2026 |
| MiniMax M3 | $0.30 / $1.20 | May 2026 |
| DeepSeek V4 Flash | $0.14 / $0.28 −67% vs DeepSeek | Apr 2026 |
| DeepSeek V4 Pro | $1.20 / $1.20 −39% vs DeepSeek | Apr 2026 |
| Kimi K2.6 Moonshot AIkimi-k2p6 | $0.95 / $4.00 | Apr 2026 |
| GLM 5.1 Zhipu AIglm-5p1 | $1.40 / $4.40 | Apr 2026 |
| MiniMax M2.7 MiniMaxminimax-m2p7 | Not listed | Mar 2026 |
| Kimi K2.5 Moonshot AIkimi-k2p5 | $0.60 / $3.00 | Jan 2026 |
| GLM 4.7 Zhipu AIglm-4p7 | $0.60 / $2.20 | Dec 2025 |
| DeepSeek V3.2 DeepSeekdeepseek-v3p2 | $0.56 / $1.68 +171% vs DeepSeek | Dec 2025 |
| Kimi K2 Thinking | $0.60 / $2.50 +19% vs GMI Cloud | Nov 2025 |
| gpt-oss-safeguard-20b OpenAI · Moderation | $0.50 / $0.50 +388% vs Amazon Bedrock | Oct 2025 |
| Qwen3 VL 8B Instruct | $0.20 / $0.20 +8% vs Novita AI | Oct 2025 |
| Qwen3 VL 30B A3B Instruct | $0.15 / $0.60 | Oct 2025 |
| GLM 4.6 Zhipu AIglm-4p6 | $0.55 / $2.19 −4% vs Z.ai | Sep 2025 |
| Qwen3 VL 235B A22B Instruct | $0.22 / $0.88 −45% vs Alibaba DashScope | Sep 2025 |
| DeepSeek V3.1 Terminus DeepSeekdeepseek-v3p1-terminus | $0.56 / $1.68 +86% vs DeepInfra | Sep 2025 |
| Qwen3 Next 80B A3B Instruct | $0.90 / $0.90 +118% vs Alibaba DashScope | Sep 2025 |
| GLM 4 5v Zhipu AIglm-4p5v | $1.20 / $1.20 +33% vs Z.ai | Aug 2025 |
| gpt-oss-120b | $0.15 / $0.60 +304% vs W&B Inference | Aug 2025 |
| gpt-oss-20b | $0.07 / $0.30 +132% vs W&B Inference | Aug 2025 |
| Qwen3 Coder 30B A3B Instruct | $0.15 / $0.60 +119% vs Novita AI | Jul 2025 |
| Qwen3 30B A3B Instruct 2507 | $0.50 / $0.50 +233% vs Nebius AI Studio | Jul 2025 |
| GLM 4.5 Air Zhipu AIglm-4p5-air | $0.22 / $0.88 −9% vs Z.ai | Jul 2025 |
| GLM 4.5 Zhipu AIglm-4p5 | $0.55 / $2.19 −4% vs Z.ai | Jul 2025 |
| Qwen3 235B A22B Thinking 2507 | $0.22 / $0.88 | Jul 2025 |
| DeepSeek R1 | $3.00 / $8.00 +343% vs DeepSeek | May 2025 |
| Qwen3 30B A3B | $0.15 / $0.60 | Apr 2025 |
| Qwen3 32B | $0.90 / $0.90 +1340% vs Lambda AI | Apr 2025 |
| Qwen3 14B | $0.20 / $0.20 +67% vs Nebius AI Studio | Apr 2025 |
| Gemma 3 27B IT | $0.90 / $0.90 | Mar 2025 |
| Qwen2.5 VL 72B Instruct Alibaba Qwenqwen2p5-vl-72b-instruct | $0.90 / $0.90 +140% vs Nebius AI Studio | Feb 2025 |
| Mistral Small 24B Instruct 2501 | $0.90 / $0.90 +1465% vs DeepInfra | Jan 2025 |
| Llama 3.3 70B Instruct Metallama-v3p3-70b-instruct | $0.90 / $0.90 | Dec 2024 |
| Qwen2.5 Coder 32B Instruct Alibaba Qwenqwen2p5-coder-32b-instruct | $0.90 / $0.90 +847% vs Nscale | Nov 2024 |
| Llama 3.2 3B Instruct Metallama-v3p2-3b-instruct | $0.10 / $0.10 +400% vs DeepInfra | Sep 2024 |
| Llama 3.2 1B Instruct Metallama-v3p2-1b-instruct | $0.10 / $0.10 +400% vs Novita AI | Sep 2024 |
| Qwen2.5 72B Instruct Alibaba Qwenqwen2p5-72b-instruct | $0.90 / $0.90 +445% vs Hyperbolic | Sep 2024 |
| Llama 3.1 8B Instruct Metallama-v3p1-8b-instruct | $0.10 / $0.10 +264% vs Novita AI | Jul 2024 |
| Llama 3.1 70B Instruct Metallama-v3p1-70b-instruct | $0.90 / $0.90 +25% vs Oracle OCI | Jul 2024 |
| Mixtral 8x22b Instruct | $1.20 / $1.20 | Apr 2024 |
| Mythomax L2 13B | $0.20 / $0.20 +122% vs Novita AI | Jul 2023 |
| DeepSeek V3.1 DeepSeekdeepseek-v3p1 | $0.56 / $1.68 +98% vs DeepInfra | - |
| DeepSeek DeepSeekdeepseek-v3 | $0.90 / $0.90 +88% vs DeepSeek | - |
| DeepSeek V3 DeepSeekdeepseek-v3-0324 | $0.90 / $0.90 +1% vs Novita AI | - |
| Qwen3 Next 80B A3B Thinking | $0.90 / $0.90 +118% vs Alibaba DashScope | - |
| DeepSeek R1 Distill Llama 70B | $0.90 / $0.90 +200% vs DeepInfra | - |
| Qwen3 235B A22B Instruct 2507 | $0.22 / $0.88 +151% vs GMI Cloud | - |
| Kimi K2 Instruct | $0.60 / $2.50 +23% vs DeepInfra | - |
| Qwen3 Coder 480B A35B Instruct | $0.45 / $1.80 +28% vs Vertex AI | - |
| DeepSeek R1 Distill Qwen 32B | $0.90 / $0.90 +500% vs Nscale | - |
| MiniMax M2 | $0.30 / $1.20 | - |
| Qwen3 235B A22B | $0.22 / $0.88 +43% vs DeepInfra | - |
| QwQ 32B | $0.90 / $0.90 +386% vs Nscale | - |
| Llama 3.2 11B Vision Instruct Metallama-v3p2-11b-vision-instruct | $0.20 / $0.20 +308% vs DeepInfra | - |
| Llama 3.2 90B Vision Instruct Metallama-v3p2-90b-vision-instruct | $0.90 / $0.90 | - |
| MiniMax M2.1 MiniMaxminimax-m2p1 | $0.30 / $1.20 | - |
| Mistral Nemo Instruct 2407 | $0.20 / $0.20 +584% vs DeepInfra | - |
| Qwen3 Embedding 8B Alibaba Qwen · Embedding | $0.10 / $0.00 +900% vs Nebius AI Studio | - |
| Qwen3 VL 235B A22B Thinking | $0.22 / $0.88 −70% vs Alibaba DashScope | - |
| Qwen3 VL 32B Instruct | $0.90 / $0.90 +221% vs Alibaba DashScope | - |
| DeepSeek R1 Distill Qwen 14B | $0.20 / $0.20 +186% vs Nscale | - |
| Llama 3.1 405B Instruct Metallama-v3p1-405b-instruct | $3.00 / $3.00 | - |
| Llama Guard 3 8B Meta · Moderation | $0.20 / $0.20 +567% vs Nebius AI Studio | - |
| Qwen Max Alibaba Qwenqwen-max-latest | $2.00 / $6.00 +7% vs Alibaba DashScope | - |
| DeepSeek R1 Distill Llama 8B | $0.20 / $0.20 +700% vs Nscale | - |
| DeepSeek R1 Distill Qwen 7B | $0.20 / $0.20 +60% vs GMI Cloud | - |
| Llama 2 70B Chat Metallama-v2-70b-chat | $0.90 / $0.90 | - |
| Llama 2 7B Chat Metallama-v2-7b-chat | $0.20 / $0.20 +100% vs Replicate | - |
| Llama 3 70B Instruct Metallama-v3-70b-instruct | $0.90 / $0.90 +59% vs Novita AI | - |
| Llama 3 8B Metallama-v3-8b | $0.20 / $0.20 +248% vs Vercel AI Gateway | - |
| Llama 3.1 Nemotron 70B Instruct NVIDIAllama-v3p1-nemotron-70b-instruct | $0.90 / $0.90 | - |
| Llama 3.2 3B Metallama-v3p2-3b | $0.10 / $0.10 +100% vs LlamaGate | - |
| Mistral 7B Instruct Mistral AImistral-7b-instruct-v3 | $0.20 / $0.20 +63% vs Perplexity | - |
| Mixtral 8x7b Instruct | $0.50 / $0.50 +308% vs Perplexity | - |
| Nvidia Nemotron Nano 9B NVIDIAnvidia-nemotron-nano-9b-v2 | $0.20 / $0.20 +186% vs DeepInfra | - |
| Qwen2.5 7B Instruct Alibaba Qwenqwen2p5-7b-instruct | $0.20 / $0.20 +264% vs DeepInfra | - |
| Qwen2.5 Coder 7B Alibaba Qwenqwen2p5-coder-7b | $0.20 / $0.20 +1233% vs Nebius AI Studio | - |
| Qwen3 4B | $0.20 / $0.20 +567% vs Novita AI | - |
| Qwen3 8B | $0.20 / $0.20 +229% vs Novita AI | - |
| Qwen3 Embedding 0 6B Alibaba Qwen · Embeddingqwen3-embedding-0p6b | Not listed | - |
| Codegemma 7B | $0.20 / $0.20 | - |
| Dbrx Instruct | $1.20 / $1.20 | - |
| DeepSeek R1 Distill Qwen 1 5B DeepSeekdeepseek-r1-distill-qwen-1p5b | $0.10 / $0.10 +11% vs Nscale | - |
| Gemma 7B | $0.20 / $0.20 | - |
1-100 of 304