Models
FastMetal supports various LLM models for different use cases. View the models available on your dashboard, or query the /models endpoint.
Available Models
Models are configured by your administrator. Use the /models endpoint to list available models:
| Model | Description |
|---|---|
mistral-voxtral-mini-3b-2507 | Japan: Mistral's voxtral-mini-3b-2507 |
anthropic-claude-opus-4-8 | Global: Claude Opus 4.8 - Most intelligent, best for agents and coding |
anthropic-claude-opus-4-6 | Global: Claude Opus 4.6 - Most intelligent, best for agents and coding |
anthropic-claude-sonnet-4-6 | Japan: Claude Sonnet 4.6 - Best balance of speed and intelligence |
anthropic-claude-haiku-4-5 | Japan: Claude Haiku 4.5 - Fastest with near-frontier intelligence |
minimax-m2.7 | Global: Minimax's M2.7 |
glm-5 | Global: Z.ai's GLM-5 |
llm-jp-3.1-8x13b-instruct4 | Japan: Japanese language model optimized for instruction following |
japan-gemma-4-31b | Japan: Google's Gemma 4 31B - hosted and run in Japan |
japan-qwen3.6-35b | Japan: Qwen 3.6 35B-A3B - hosted and run in Japan |
japan-kimi-k2.6 | Japan: Moonshot AI's Kimi K2.6 - hosted and run in Japan |
japan-kimi-k2.7-code | Japan: Moonshot AI's Kimi K2.7 Code - hosted and run in Japan |
gpt-oss-120b | Japan: gpt-oss-120b |
minimax-m3 | Global: MiniMax's M3 |
qwen3.6-27b | Global: Qwen 3.6 27B |
qwen3.8-27b | Global: Qwen 3.8 27B |
kimi-k2.6 | Global: Moonshot AI's Kimi K2.6 |
glm-4.7 | Global: Z.ai's GLM 4.7 |
glm-4.7-flash | Global: Z.ai's GLM 4.7 Flash |
deepseek-v4-flash | Global: DeepSeek's V4 Flash |
deepseek-v4-flash-0731 | Global: DeepSeek's V4 Flash 0731 |
deepseek-v4.1-flash | Global: DeepSeek's V4.1 Flash |
deepseek-v4-pro | Global: DeepSeek's V4 Pro |
glm-5.2 | Global: Z.ai's GLM 5.2 |
glm-5.3 | Global: Z.ai's GLM 5.3 |
kimi-k3 | Global: Moonshot AI's Kimi K3 |
qwen3.7-max | Global: Qwen 3.7 Max |
qwen3.8-max | Global: Qwen 3.8 Max |
grok-4.5 | Global: xAI's Grok 4.5 |
grok-4.6 | Global: xAI's Grok 4.6 |
gpt-5.6-sol | Global: OpenAI's GPT-5.6 Sol |
gpt-5.6-terra | Global: OpenAI's GPT-5.6 Terra |
gpt-5.6-luna | Global: OpenAI's GPT-5.6 Luna |
gemini-3.5-flash | Global: Google's Gemini 3.5 Flash |
gemini-3.7-flash | Global: Google's Gemini 3.7 Flash |
anthropic-claude-opus-5 | Global: Claude Opus 5 - Most intelligent, best for agents and coding |
anthropic-claude-sonnet-5 | Global: Claude Sonnet 5 - Best balance of speed and intelligence |
anthropic-claude-fable-5 | Global: Claude Fable 5 - Anthropic's flagship Mythos-class model |
anthropic-claude-fable-5-1 | Global: Claude Fable 5.1 - Anthropic's flagship, stronger agentic coding and long-horizon work than Fable 5 |
muse-glimmer-30b | Global: Meta's Muse Glimmer 30B |
muse-spark-1.2 | Global: Meta Muse Spark 1.2 |
muse-spark-1.3 | Global: Meta Muse Spark 1.3 |
muse-spark-1.3-contributor | Global: Meta Muse Spark 1.3 Contributor |
glm-5.3-flash | Global: Z.ai GLM 5.3 Flash |
solar-pro4 | Global: Upstage Solar Pro 4 |
qwen3.8-2.4t-a95b | Global: Qwen 3.8 2.4T-A95B |
gpt-6-astra | Global: OpenAI's GPT-6 Astra |
gpt-6-astra-pro | Global: OpenAI's GPT-6 Astra Pro |
gemini-3.8-flash | Global: Google's Gemini 3.8 Flash |
gpt-4.1-nano | Global: OpenAI's GPT-4.1 nano |
gpt-4o-mini | Global: OpenAI's GPT-4o mini |
qwen3-next-80b-a3b-instruct | Global: Qwen3-Next 80B-A3B Instruct |
llama-3.1-8b-instruct | Global: Meta Llama 3.1 8B Instruct |
llama-3.2-3b-instruct | Global: Meta Llama 3.2 3B Instruct |
gemini-3.1-pro-preview | Global: Google's Gemini 3.1 Pro (preview) |
glm-4.6v | Global: Z.ai GLM 4.6V |
nemotron-3-super-120b-a12b | Global: NVIDIA Nemotron 3 Super 120B-A12B |
hy3 | Global: Tencent Hy3 |
gemini-flash-lite-free | Global: Google's Gemini Flash Lite - free to try |
mercury-2.5 | Global: Inception Mercury 2.5 - diffusion LLM, the fastest reasoning model |
fugu-max | Global: Sakana AI Fugu Max - cost-performance multi-agent orchestration model |
fugu-ultra-v2 | Global: Sakana AI Fugu Ultra v2 - high-performance multi-agent orchestration model |
ling-3.0-flash-vl | Global: inclusionAI Ling 3.0 Flash VL - low-cost MoE vision-language model |
pareto | Global: Unbiased Pareto 26.10 - blended multimodal model for research, coding and agentic work, 1M context |
google-nano-banana-2 Image | Global: Google Nano Banana 2 - fast, high-quality image generation |
bytedance-seedream-4.5 Image | Global: Generate images |
z-image-turbo Image | Global: Generate realistic images |
glm-5.3-flashx | Global: Z.ai GLM 5.3 FlashX |
gpt-5-mini | Global: OpenAI's GPT-5 mini |
gpt-4.1-mini | Global: OpenAI's GPT-4.1 mini |
gpt-5.4-nano | Global: OpenAI's GPT-5.4 nano |
llama-4-maverick | Global: Meta Llama 4 Maverick |
llama-3.3-70b-instruct | Global: Meta Llama 3.3 70B Instruct |
qwen3-vl-235b-a22b-instruct | Global: Qwen3-VL 235B-A22B Instruct |
gemma-4-26b-a4b-it | Global: Google Gemma 4 26B-A4B |
gpt-oss-20b | Global: OpenAI gpt-oss-20B |
devstral-2512 | Global: Mistral Devstral 2512 |
grok-4.7 | Global: xAI's Grok 4.7 |
anthropic-claude-opus-5-5 | Global: Claude Opus 5.5 - Anthropic's most capable model, priced below Opus 5 |
mimo-v2.6-pro | Global: Xiaomi's MiMo-V2.6-Pro |
gpt-6-sol | Global: OpenAI GPT-6 Sol |
gpt-6-luna | Global: OpenAI GPT-6 Luna |
mimo-v2.6-flash | Global: Xiaomi's MiMo-V2.6-Flash |
gpt-6-sol-pro | Global: OpenAI GPT-6 Sol Pro |
gpt-6-luna-pro | Global: OpenAI GPT-6 Luna Pro |
solar-mini4 | Global: Upstage Solar Mini 4 |
ember-1 | Global: Fireworks Ember-1 - a reasoning model built on Kimi K3 |
gpt-6.1-sol | Global: OpenAI GPT-6.1 Sol |
gpt-6.1-sol-pro | Global: OpenAI GPT-6.1 Sol Pro |
anthropic-claude-sonnet-5-5 | Global: Claude Sonnet 5.5 - Anthropic's everyday model, succeeding Sonnet 5 |
anthropic-claude-haiku-5-5 | Global: Claude Haiku 5.5 - Anthropic's fastest, lowest-cost model, succeeding Haiku 4.5 |
gemini-4-argon | Global: Google Gemini 4 Argon - Google's flagship reasoning model for software engineering, math and science, and multi-step agents |
nemotron-3.5-super-vl | Global: NVIDIA Nemotron 3.5 Super VL - NVIDIA's open multimodal MoE reasoning model with image and PDF input |
beam-1.0 | Global: Reflection Beam 1.0 - Reflection AI's open-weight 501B MoE reasoning model for coding and agentic work, with a 1M-token context |
deepseek-v4.1-flash-1017 | Global: DeepSeek's V4.1 Flash 1017 - the October 17, 2026 snapshot, 1M context and image input |
minimax-m3.1-flash | Global: MiniMax's M3.1 Flash - fast, low-cost multimodal model with a 1M-token context |
kimi-k3.1-pro | Global: Moonshot AI's Kimi K3.1 Pro - flagship reasoning model, successor to Kimi K3, 1M context and image input |
deepseek-v4.1-flash-uncensored | Global: DeepSeek V4.1 Flash, uncensored - a fine-tune without the usual refusals, 1M context |
auto | Auto: routes each request to the model that is cheapest for its size among those supporting it (tools/vision/JSON) — billed at the resolved model's price; the listed price is what a typical small request resolves to |
Model Pricing
Pricing is calculated per token. Each model has separate input and output token rates. Check the pricing page or your dashboard for current rates.
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| mistral-voxtral-mini-3b-2507 | $0.0528 | $0.0528 |
| anthropic-claude-opus-4-8 | $5.28 | $26.38 |
| anthropic-claude-opus-4-6 | $5.42 | $26.77 |
| anthropic-claude-sonnet-4-6 | $3.49 | $17.41 |
| anthropic-claude-haiku-4-5 | $1.17 | $5.81 |
| minimax-m2.7 | $0.3165 | $1.27 |
| glm-5 | $1.06 | $3.38 |
| llm-jp-3.1-8x13b-instruct4 | $0.102 | $0.5035 |
| japan-gemma-4-31b | $0.1657 | $0.6436 |
| japan-qwen3.6-35b | $0.204 | $1.01 |
| japan-kimi-k2.6 | $0.4079 | $2.02 |
| japan-kimi-k2.7-code | $0.3505 | $3.38 |
| gpt-oss-120b | $0.102 | $0.5035 |
| minimax-m3 | $0.2954 | $1.17 |
| qwen3.6-27b | $0.3376 | $3.38 |
| qwen3.8-27b | $0.211 | $2.64 |
| kimi-k2.6 | $0.7913 | $3.70 |
| glm-4.7 | $0.422 | $1.85 |
| glm-4.7-flash | $0.0666 | $0.44 |
| deepseek-v4-flash | $0.095 | $0.1899 |
| deepseek-v4-flash-0731 | $0.1477 | $0.2954 |
| deepseek-v4.1-flash | $0.211 | $0.633 |
| deepseek-v4-pro | $1.38 | $2.75 |
| glm-5.2 | $1.48 | $4.65 |
| glm-5.3 | $1.48 | $4.65 |
| kimi-k3 | $3.17 | $15.83 |
| qwen3.7-max | $2.64 | $7.92 |
| qwen3.8-max | $2.11 | $6.33 |
| grok-4.5 | $2.20 | $6.60 |
| grok-4.6 | $2.20 | $6.60 |
| gpt-5.6-sol | $4.40 | $22.00 |
| gpt-5.6-terra | $2.11 | $12.66 |
| gpt-5.6-luna | $0.211 | $1.27 |
| gemini-3.5-flash | $1.65 | $9.90 |
| gemini-3.7-flash | $0.7913 | $3.96 |
| anthropic-claude-opus-5 | $5.28 | $26.38 |
| anthropic-claude-sonnet-5 | $2.11 | $10.55 |
| anthropic-claude-fable-5 | $10.55 | $52.75 |
| anthropic-claude-fable-5-1 | $10.55 | $52.75 |
| muse-glimmer-30b | $0.3693 | $1.59 |
| muse-spark-1.2 | $1.38 | $4.68 |
| muse-spark-1.3 | $1.38 | $4.68 |
| muse-spark-1.3-contributor | $0.11 | $0.22 |
| glm-5.3-flash | $0.1583 | $0.5275 |
| solar-pro4 | $0.165 | $0.66 |
| qwen3.8-2.4t-a95b | $2.20 | $6.60 |
| gpt-6-astra | $10.55 | $52.75 |
| gpt-6-astra-pro | $11.00 | $55.00 |
| gemini-3.8-flash | $0.7913 | $3.96 |
| gpt-4.1-nano | $0.11 | $0.44 |
| gpt-4o-mini | $0.1583 | $0.633 |
| qwen3-next-80b-a3b-instruct | $0.095 | $1.17 |
| llama-3.1-8b-instruct | $0.0211 | $0.0422 |
| llama-3.2-3b-instruct | $0.056 | $0.3685 |
| gemini-3.1-pro-preview | $2.11 | $12.66 |
| glm-4.6v | $0.33 | $0.99 |
| nemotron-3-super-120b-a12b | $0.0897 | $0.422 |
| hy3 | $0.1477 | $0.6119 |
| gemini-flash-lite-free | $0.00 | $0.00 |
| mercury-2.5 | $0.044 | $0.165 |
| fugu-max | $2.20 | $6.60 |
| fugu-ultra-v2 | $5.50 | $33.00 |
| ling-3.0-flash-vl | $0.0633 | $0.1899 |
| pareto | $0.88 | $3.52 |
| glm-5.3-flashx | $0.407 | $1.38 |
| gpt-5-mini | $0.2638 | $2.11 |
| gpt-4.1-mini | $0.44 | $1.76 |
| gpt-5.4-nano | $0.211 | $1.32 |
| llama-4-maverick | $0.22 | $0.88 |
| llama-3.3-70b-instruct | $0.1055 | $0.3376 |
| qwen3-vl-235b-a22b-instruct | $0.211 | $0.9284 |
| gemma-4-26b-a4b-it | $0.0739 | $0.3587 |
| gpt-oss-20b | $0.0317 | $0.1477 |
| devstral-2512 | $0.44 | $2.20 |
| grok-4.7 | $2.20 | $6.60 |
| anthropic-claude-opus-5-5 | $4.22 | $21.10 |
| mimo-v2.6-pro | $0.459 | $0.9179 |
| gpt-6-sol | $2.11 | $10.55 |
| gpt-6-luna | $0.1055 | $0.5275 |
| mimo-v2.6-flash | $0.1477 | $0.2954 |
| gpt-6-sol-pro | $2.20 | $11.00 |
| gpt-6-luna-pro | $0.11 | $0.55 |
| solar-mini4 | $0.055 | $0.22 |
| ember-1 | $3.30 | $16.50 |
| gpt-6.1-sol | $2.11 | $10.55 |
| gpt-6.1-sol-pro | $2.20 | $11.00 |
| anthropic-claude-sonnet-5-5 | $2.11 | $10.55 |
| anthropic-claude-haiku-5-5 | $0.1055 | $0.5275 |
| gemini-4-argon | $2.11 | $10.55 |
| nemotron-3.5-super-vl | $0.211 | $1.06 |
| beam-1.0 | $0.422 | $1.27 |
| deepseek-v4.1-flash-1017 | $0.211 | $0.633 |
| minimax-m3.1-flash | $0.1583 | $0.633 |
| kimi-k3.1-pro | $2.11 | $10.55 |
| deepseek-v4.1-flash-uncensored | $0.3482 | $1.40 |
| auto | resolved model's rate | resolved model's rate |
For full pricing details, see the pricing page.
Image Model Pricing
Image-generation models are billed per generated image rather than per token.
| Model | Per image |
|---|---|
| google-nano-banana-2 | $0.078 |
| bytedance-seedream-4.5 | $0.0456 |
| z-image-turbo | $0.0108 |
Model Capabilities
Chat/Conversation — Multi-turn dialogue with context
All models support chat/conversationText Completion — Single-turn text generation
Text completion support