Models

Model catalog

One OpenAI-compatible API for open-source and frontier LLMs, plus Google's Gemini family for multimodal chat, reasoning, and image generation. Prices are listed per 1M tokens in USD, as of July 2026. The model ID is what you pass in the request body.

At a glance

Model ID	Context	Input	Output	Notes
deepseek-v4-flash	1M	$0.112	$0.224	Official 0731 agent model. 1M context with Chat Completions and Responses for Codex.
deepseek-v4-pro	1M	$0.435	$0.87	Premium reasoning with 1M-token context. Maps to o3-mini at ~6× lower output cost.
qwen3.8-max	1M	$2.00	$6.00	Alibaba's Qwen 3.8 flagship, released 2026-08-03: a 2.4T-parameter MoE that Alibaba pitches at autonomous coding and long-horizon agents. Thinks by default — the gateway suppresses thinking by default; pass enable_thinking=true to opt into the reasoning trace.
qwen3.7-max	1M	$1.25	$3.75	Qwen 3.7 flagship. Agent-centric, coding & productivity tasks. Thinks by default — the gateway suppresses thinking by default; pass enable_thinking=true to opt into the reasoning trace.
qwen3.7-plus	1M	$0.256	$1.024	Alibaba's hosted multimodal agent flagship. Long-running coding/agent loops, 1M context. Thinks by default; pass reasoning.enabled=true to opt into the trace.
qwen3.7-flash	1M	$0.024	$0.104	Fast multimodal agent model for vision, visual coding, search, tool use, and high-volume automation. Selectable reasoning.
qwen3.6-plus	1M	$0.26	$1.56	1T-parameter MoE flagship. 1M context. Top Qwen on OpenRouter by token volume. Thinks by default — the gateway suppresses thinking by default; pass reasoning.enabled=true to opt into the reasoning trace.
qwen3.6-35b	262K	$0.112	$0.80	35B/3B-active MoE. Long-context RAG and summarization with strong reasoning.
kimi-k2.6	256K	$0.5472	$2.728	Opus-class agentic / planning. Best fit when your eval picks Claude Opus.
kimi-k2.7-code	256K	$0.584	$2.80	Always-thinking K2 tuned for long-horizon agentic coding. Fixed sampling parameters; Moonshot reports ~30% less overthinking than K2.6.
kimi-k3	1M	$2.40	$12.00	Moonshot's 2.8T open-weight multimodal reasoning flagship. Complex coding, knowledge work, and long-horizon agentic workflows.
muse-spark-1.2	1M	$1.00	$3.40	Coding-focused reasoning model, 1M context
muse-glimmer-30b	131,072	$0.28	$1.20	Compact agentic multimodal model, distilled from Muse Spark
glm-5.3	1M	$1.12	$3.52	Z.ai latest reasoning flagship, 1M context, complex software engineering & long-horizon agents
glm-5.2	1M	$1.12	$3.52	Z.ai's large-scale reasoning flagship. 1M context, built for long-horizon agent workflows and project-level software engineering. Thinks by default — the gateway suppresses thinking by default; pass reasoning.enabled=true to opt into the reasoning trace.
nemotron-3.5-lightning	262K	$0.08	$0.20	30B-A3B open MoE for fast, tool-heavy agents
gpt-5.6-luna	1M	$0.08	$0.48	OpenAI's fast, cost-efficient GPT-5.6 tier. High-volume, latency-sensitive chat and classification. Reasoning model; pass reasoning.enabled=false to suppress the trace.
gpt-5.6-terra	1M	$0.80	$4.80	OpenAI's balanced GPT-5.6 mid-tier, between Luna and Sol. Everyday coding, reasoning and agentic work.
gpt-5.6-sol	1M	$4.00	$24.00	OpenAI's flagship GPT-5.6. Complex reasoning, coding and agentic workflows, especially on hard multi-step tasks.
grok-4.5	500K	$1.60	$4.80	xAI's frontier model for coding, knowledge work and STEM. Always reasons — reasoning.enabled=false is rejected; control depth with reasoning_effort.
grok-4.6	500K	$2.00 ($4.00 >200K)	$6.00 ($12.00 >200K)	frontier coding, knowledge work and STEM, vision, 500K context
minimax-m3	1M	$0.24	$0.96	MiniMax's open-weight frontier model. Text-only input, tuned for long-horizon agentic coding.
mimo-v2.5	1M	$0.112	$0.224	Xiaomi's open-weight MiMo-V2.5. Cost-efficient everyday coding and agentic workflows.
hy3	262K	$0.1056	$0.4224	Tencent's Hy3. General-purpose coding and agentic workflows with selectable reasoning.
claude-opus-5	1M	$4.00	$20.00	Anthropic's flagship for demanding reasoning, coding and long-horizon agentic work. Accepts image input.
claude-fable-5	1M	$8.00	$40.00	Anthropic's Mythos-class flagship. The most capable tier for long-horizon agentic work.
claude-opus-4-8	1M	$4.00	$20.00	Anthropic flagship. Top-tier reasoning, coding and agentic workloads.
claude-opus-4-6	1M	$4.00	$20.00	Anthropic flagship. Deep reasoning and coding.
claude-sonnet-4-6	1M	$2.40	$12.00	Balanced Anthropic mid-tier. Fast and capable for most workloads.
claude-sonnet-5	1M	$2.00	$10.00	Anthropic's newest Sonnet. Stronger reasoning and coding at a lower price than the previous mid-tier.
claude-haiku-4-5	200K	$0.80	$4.00	Fast, low-cost Anthropic tier for high-volume work. Does not emit a reasoning trace.
gemini-3.7-flash	1M	$0.6375	$3.1875	most capable Flash for agents; promotional pricing through 2026-12-31
gemini-3.6-flash	1M	$1.275	$6.375	Current general-purpose Flash GA. Recommended for new Flash integrations.
gemini-3.5-flash-lite	1M	$0.255	$2.125	Current low-cost Flash-Lite GA. Recommended for high-volume workloads.
gemini-3.5-flash	1M	$1.275	$7.65	Next-gen Flash GA from Google. 1M context, thinks by default. Sits between 3 Flash Preview and 3.1 Pro on capability and price.
gemini-3.1-pro-preview	1M	$1.70	$10.20	Google's flagship reasoning model. 1M context, thinks deeply. Preview API; semantics may shift before GA.
gemini-3-pro-image	1M	$1.70	$10.20	GA pro-grade image generation. Replaces the retired preview model ID.
gemini-3-flash-preview	1M	$0.425	$2.55	Legacy compatibility only. Migrate new and existing workloads to gemini-3.6-flash.
gemini-3.1-flash-lite	1M	$0.2125	$1.275	Legacy compatibility only. Migrate new and existing workloads to gemini-3.5-flash-lite.
flux.2-pro	-	—	$0.027 per image	Flagship image generation via /v1/images/generations. Billed per generated image.

Which model should I use?

Code-first default - deepseek-v4-flash. A practical starting point for code, chat, and production agents. 1M context; input $0.112, output $0.224.
Hard reasoning - deepseek-v4-pro. Use for math, theorem proving, and difficult multi-step problems. 1M context; input $0.435, output $0.87.
Long-document RAG - qwen3.6-35b. A compact MoE choice for retrieval and long-document summarization. 262K context; input $0.112, output $0.80.
Agentic planning - kimi-k2.6. A strong option when your evaluations favor Opus-class planning behavior. 256K context; input $0.5472, output $2.728.
Multimodal workloads - gemini-3.6-flash. Use when prompts include images as well as text. 1M context; input $1.275, output $6.375.
Image generation - gemini-3-pro-image. Use for pro-grade generated image output. 1M context; input $1.70, output $10.20.
High-volume short turns - gemini-3.5-flash-lite. Use for cost-sensitive routing, classification, and extraction. 1M context; input $0.255, output $2.125.

Thinking vs. non-thinking

The V4 wave (V4 Flash, V4 Pro, Kimi K2.6) and Qwen 3.6 emit a chain-of-thought trace before the final answer. A one-token "Hi" can return ~175 reasoning tokens. To get non-thinking low-cost chat behavior on these models, pass:

See quickstart for full code →

Some always-reasoning models (e.g. Grok 4.5) ignore reasoning.enabled=false— reasoning IS the model. Use V4 Flash if you don't want the trace.

Per-model deep dives

Each model has its own page with pricing comparisons, FAQs, and quickstart code. Linked here for convenience:

Per-model deep-dive pages for the Gemini family are in progress — the catalog table above carries the canonical pricing and capability summary in the meantime.