Fireworks AI models in Big-AGI
Fireworks exclusives like Alibaba's closed Qwen3.7-Plus, plus per-model fast serving tiers - with the names and prices Fireworks' API never returns, filled in.
All supported Fireworks AI models
ModelContextInputOutputReleased
Ultramarine 1 Flash Us (Vision)deprecatedFine-tuned adapter served on Fireworks AI.1M--Oct 2026DeepSeek V4.1 Flash 1017 (Vision)NEWPost-training update of DeepSeek V4.1 Flash (552B multimodal MoE, 1M-token context): stronger reasoning, coding, agentic and visual results with shorter output…1M$0.30$1.20Oct 2026DeepSeek V4.1 Flash 1017 Spot (Vision)NEWOpen-weights model served on Fireworks AI.1M--Oct 2026Ember-1 (Vision)NEWFireworks reasoning model built on Kimi K3: ~40% fewer reasoning tokens at comparable quality, with image input and a 1M-token context.1M$3.00$15.00Sep 2026DeepSeek V4.1 Flash (Vision)DeepSeek multimodal MoE (552B, 8B active on input) with native image input and a 1M-token context; ahead of V4 Pro on agentic benchmarks at a fraction of the p…1M$0.30$1.20Sep 2026DeepSeek V4.1 Flash Spot (Vision)Open-weights model served on Fireworks AI.1M--Sep 2026GLM 5.3 SpotOpen-weights model served on Fireworks AI.1M--Aug 2026GLM 5.3 Flash (Vision)First natively-multimodal model of the GLM-5 line: a 320B MoE (18B active) on a new base with hybrid sparse and linear attention, image input, and a 1M-token c…1M$0.15$0.50Aug 2026DeepSeek V4 Flash Vision Exp (Vision)deprecatedExperimental multimodal member of the DeepSeek V4 family: V4 Flash plus visual modules and continued training, for stronger multimodal agent work at parity on…1M$0.22$0.66Aug 2026GLM 5.3Z.ai flagship, post-trained on the GLM-5.2 base for frontier coding, cybersecurity and long-horizon agentic work, with a 1M-token context.1M$1.40$4.40Aug 2026GLM 5.3 FastFast serving path for GLM 5.3: same model and quality, lower latency, higher per-token price.1M$2.10$6.60Aug 2026DeepSeek V4 Pro 0813deprecatedOfficial release of DeepSeek V4 Pro, superseding the preview, with greatly enhanced agentic capabilities, most pronounced in production environments. Ships wit…1M$1.32$3.96Aug 2026Qwen3.8 2.4T-A95B (Vision)Open-weights release of the Qwen3.8 flagship: 2.4T sparse MoE with ~95B active parameters, built for multi-day coding runs and self-improving research.262K$2.00$6.00Aug 2026NVIDIA Nemotron 3.5 Lightning 30B A3BNVIDIA hybrid Mamba-Transformer MoE (30B params, 3B active) with a multi-token prediction head, for low-latency agentic serving at long context.262K$0.05$0.20Aug 2026Muse Glimmer 30B (Vision)deprecatedMeta dense 30B distilled from Muse Spark for local agentic work: multi-step reasoning, schema-based tool calling, and image input across 100+ languages.131K$0.35$1.50Aug 2026DeepSeek V4 Flash 0731deprecatedOfficial release of DeepSeek V4 Flash, superseding the preview, with substantially enhanced agentic capabilities. Ships with a speculative decoding module atta…1M$0.22$0.66Jul 2026Kimi K3 Spot (Vision)Open-weights model served on Fireworks AI.1M--Jul 2026Qwen3.8 Max (Vision)Alibaba flagship Qwen3.8 tier, available outside Alibaba infrastructure through Fireworks AI.262K$2.00$6.00Jul 2026Inkling (Vision)Thinking Machines Lab first open-weights model: a 975B MoE (41B active) trained natively across text, image, and audio, with controllable thinking effort.1M$1.00$4.05Jul 2026Kimi K3 (Vision)Moonshot AI 2.8T-parameter flagship on Kimi Delta Attention, with native visual understanding and a 1M-token context for long-horizon coding and reasoning.1M$3.00$15.00Jul 2026Kimi K3 Fast (Vision)Fast serving path for Kimi K3: same model and quality, lower latency, higher per-token price.1M$4.50$22.50Jul 2026Intent De 3CD022deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent De 6A34F8deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent De C9EC41deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent En 3CD022deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent En 6A34F8deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent En BC8D96deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent En C9EC41deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent En VERIFY1deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent Es 3CD022deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent Es 6A34F8deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026Intent Es C9EC41deprecatedFine-tuned adapter served on Fireworks AI.no specJul 2026GLM 5.2deprecatedZ.ai flagship with 1M-token context and multi-effort coding for long-horizon agentic tasks. New IndexShare architecture and improved MTP layer cut per-token co…1M$1.40$4.40Jun 2026GLM 5.2 FastdeprecatedFast serving path for GLM 5.2: same model and quality, lower latency, higher per-token price.1M$2.10$6.60Jun 2026Kimi K2.7 Code (Vision)deprecatedCoding-focused agentic model built on Kimi K2.6, with better end-to-end completion on long-horizon software engineering and ~30% fewer thinking tokens.262K$0.95$4.00Jun 2026Kimi K2.7 Code Fast (Vision)deprecatedFast serving path for Kimi K2.7 Code: same model and quality, lower latency, higher per-token price.262K$1.90$8.00Jun 2026Qwen3.7 Plus (Vision)deprecatedAlibaba flagship closed model, available outside Alibaba infrastructure exclusively through Fireworks AI.-$0.40$1.60Jun 2026NVIDIA Nemotron 3 Ultra NVFP4NVIDIA frontier-scale hybrid LatentMoE (550B params, 55B active) interleaving Mamba-2 and MoE layers, for multi-step agents and long-context reasoning.262K$0.60$2.40Jun 2026MiniMax M3MiniMax 428B MoE (23B active) with Sparse Attention for efficient long context, tuned for long-horizon agentic coding and cowork.512K$0.30$1.20May 2026Spot DeepSeek V4 FlashOpen-weights model served on Fireworks AI.1M--Apr 2026Kimi K2.6 (Vision)deprecatedMoonshot AI native-multimodal agentic model tuned for long-horizon coding, autonomous execution, and swarm task orchestration.262K$0.95$4.00Apr 2026Kimi K2.6 Fast (Vision)deprecatedFast serving path for Kimi K2.6: same model and quality, lower latency, higher per-token price.262K$2.00$8.00Apr 2026MiniMax M2.7deprecatedMiniMax MoE built for complex agent harnesses and elaborate productivity tasks, leveraging Agent Teams, Skills, and dynamic tool search.197K$0.30$1.20Apr 2026GLM 5.1deprecatedZ.ai 754B-parameter MoE built for agentic engineering, with strong coding and sustained performance across long multi-round tasks.203K$1.40$4.40Mar 2026glm 5.1 FastdeprecatedOpen-weights model served on Fireworks AI.203K--Mar 2026Kimi K2.5 (Vision)deprecatedOpen-weights model served on Fireworks AI.262K--Jan 2026QWEN3 Reranker 8BdeprecatedModel served on Fireworks AI.41K--Oct 2025QWEN3 Embedding 8BdeprecatedModel served on Fireworks AI.41K--Aug 2025GPT-OSS 20BdeprecatedOpenAI smaller open-weight model for lower-latency, local, and specialized use cases.131K$0.07$0.30Aug 2025GPT-OSS 120BOpenAI open-weight model for high-reasoning, agentic, general-purpose use that fits on a single H100.131K$0.15$0.60Aug 2025Auto (Vision)Model served on Fireworks AI.no specNov 2023MiniMax M3MiniMax 428B MoE (23B active) with Sparse Attention for efficient long context, tuned for long-horizon agentic coding and cowork.512K$0.30$1.20-52 models · sorted by release date · prices in USD per 1M tokens · refreshed hourlyCompare every model across vendors ->
Get started in 3 steps
1
Create an API key at the Fireworks AI console.
2
Paste it into Big-AGI's model settings.
3
Start chatting, or Beam it against other models and fuse the answers.
Running Fireworks AI in Big-AGI
Add your Fireworks API key over its OpenAI-compatible endpoint and reach the open-model catalog at Fireworks' own rates. Big-AGI adds no markup and no intermediary: the billing relationship runs directly between you and Fireworks.
- Your key, your billing. Usage is billed by Fireworks AI to your account.
- Exclusives, with the names filled in. Fireworks carries models you can't get elsewhere - Alibaba's closed Qwen3.7-Plus among them - and since its API returns no names or prices, Big-AGI supplies both from a curated table.
- Zero setup beyond the key. Big-AGI recognizes Fireworks endpoints by hostname and turns on the right vision and tool flags per model automatically.
- Speed as the product. Fireworks' custom inference stack pushes open models to interactive latencies, priced per token.
Why Big-AGI instead of the playground?
Fireworks' playground is built for one prompt at a time. Big-AGI turns the same key into a persistent workspace: chats that stick around, personas, and file and image attachments, all layered on top of the raw API. It's also the only place a Fireworks model runs next to Claude, GPT, and Gemini in Beam, with the parameters and the key still yours to control.
Your keys and your data
Turn on Direct Connection and the browser talks to Fireworks directly, skipping the Big-AGI server, when your key is client-side and Fireworks allows it. Your keys stay in your browser. Chats are stored locally first, and sync only if you turn it on. The AI Inspector shows the exact request, the token counts, and a cost estimate, so you always know what you're billed for.
Fireworks AI in Beam
Put a Fireworks model into a Beam alongside frontier labs, or run a few open models side by side at Fireworks' speed. Fusions then combine, cross-check, and synthesize the parallel answers instead of just picking the best one. Parallel runs use more tokens than a single chat.
Bring your Fireworks AI key. Keep control.
Your key, your data, your choice of model. Big-AGI's Open branch is open source and self-hostable, so you can check exactly how Fireworks AI is called.
Launch Big-AGIBIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego