Anthropic · anthropic/claude-opus-5.5
Anthropic's flagship tier: multi-step changes across large codebases and long-horizon agent work
$4.00 in / $20.00 out per 1M · OpenRouter ↗
OpenRouter model directory
OpenRouter Models Directory
A curated view of the models worth comparing: context window, price per million, modality and what each one is actually good for. Every field is read from the public catalogue and dated.
What this covers: models OpenRouter serves. One entry —
Jev — is listed here but absent from the /api/v1/models list this directory is generated
from, so it is read and dated by hand; the row is marked. If we ever cover a model OpenRouter does
not serve, it will not appear in this directory, and the index above it will stop being named after
a platform.
Models tracked
40
curated, not exhaustive
Largest window
1.05M
tokens of context
Vision-capable
35
accept image input
Free right now
0
$0 in and out
Every model, side by side
| Model | Vendor | Context | Input /M | Output /M | Modalities |
|---|---|---|---|---|---|
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | Text, Vision, Files | |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | Text, Vision, Files | |
| GPT-6.1 Sol | OpenAI | $2.00 | $10.00 | Text, Vision, Files | |
| Gemini 4 Argon | $2.00 | $10.00 | Text, Vision, Audio, Video, Files | ||
| Muse Wonder | Meta | $4.00 | $20.00 | Text, Vision, Audio, Video, Files | |
| Muse Spark Open | Meta | $1.25 | $4.25 | Text, Vision, Audio, Video, Files | |
| Moondream 3.1 | Moondream | $0.300 | $2.50 | Text, Vision | |
| Grok 4.7 | SpaceXAI | $2.00 | $6.00 | Text, Vision, Files | |
| Gemini 3.8 Flash | $0.825 | $4.13 | Text, Vision, Audio, Video, Files | ||
| Nemotron 3.5 Super VL | NVIDIA | $0.150 | $0.500 | Text, Vision, Video | |
| Gemini Nano Banana 2.1 | $1.50 | $7.50 | Text, Vision | ||
| Claude Haiku 5.5 | Anthropic | $0.100 | $0.500 | Text, Vision, Files | |
| Mistral Large 4 | Mistral | $0.680 | $2.09 | Text, Vision | |
| Command A+ | Cohere | $0.300 | $1.50 | Text, Vision | |
| Pareto 26.9 | Unbiased | $2.50 | $7.50 | Text, Vision | |
| DeepSeek V4.1 Flash | DeepSeek | $0.036 | $0.684 | Text, Vision | |
| GPT-6 Astra | OpenAI | $10.00 | $50.00 | Text, Vision, Files | |
| Step 5 Preview | StepFun | $1.00 | $2.70 | Text, Vision, Video | |
| ScaleDown Extract | ScaleDown | $0.040 | $0 | Text, Vision, Files | |
| ScaleDown Summarize | ScaleDown | $0.040 | $0 | Text, Vision, Files | |
| Ling 3.1 Flash | inclusionAI | $0.075 | $0.225 | Text | |
| LFM2.5-24B-A2B | Liquid AI | $0.050 | $0.700 | Text | |
| Xiaomi MiMo-V2.5 formerly Hunter Alpha | Xiaomi | $0.140 | $0.280 | Text, Vision, Audio, Video | |
| Xiaomi MiMo-V2.6-Flash | Xiaomi | $0.140 | $0.280 | Text, Vision, Audio, Video | |
| Xiaomi MiMo-V2.6-Pro | Xiaomi | $0.435 | $0.870 | Text, Vision, Audio, Video | |
| Xiaomi MiMo-V2.6-Pro-UltraSpeed | Xiaomi | $4.35 | $8.70 | Text, Vision, Audio, Video | |
| Z.ai GLM 5.3 Flash formerly OX Alpha | Z.ai | $0.150 | $0.500 | Text, Vision, Video | |
| DeepSeek V4 Flash | DeepSeek | $0.007 | $1.28 | Text | |
| DeepSeek V4 Pro | DeepSeek | $1.32 | $3.96 | Text | |
| Qwen3.8 Flash | Alibaba | $0.150 | $0.470 | Text, Vision, Video | |
| Qwen3.8 Max (0902) | Alibaba | $2.00 | $6.00 | Text, Vision, Video | |
| Google Gemini 3.7 Flash | $0.750 | $3.75 | Text, Vision, Audio, Video, Files | ||
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | Text, Vision, Files | |
| Claude Opus 5 | Anthropic | $5.00 | $25.00 | Text, Vision, Files | |
| OpenAI GPT-5.6 Luna | OpenAI | $0.200 | $1.20 | Text, Vision, Files | |
| OpenAI GPT-5.6 Sol | OpenAI | $4.00 | $20.00 | Text, Vision, Files | |
| OpenAI GPT-5.6 Terra | OpenAI | $2.00 | $12.00 | Text, Vision, Files | |
| Mistral Medium 3.5 | Mistral AI | $1.50 | $7.50 | Text, Vision, Files | |
| Meta Llama 4 Maverick | Meta | $0.188 | $0.652 | Text, Vision | |
| Cohere Command A | Cohere | $2.50 | $10.00 | Text |
Source
openrouter.ai/api/v1/models Verified 2026-10-16 Drift check daily 06:00 CST Model pages
Anthropic · anthropic/claude-sonnet-5.5
$2 / $10 per million with a 1M-token window — the balanced tier most product teams land on
$2.00 in / $10.00 out per 1M · OpenRouter ↗
GPT-6.1 Sol
1.05M OpenAI · openai/gpt-6.1-sol
$2 / $10 per million — the same price as the GPT-6 Sol it replaces, with a 6.1 revision
$2.00 in / $10.00 out per 1M · OpenRouter ↗
Gemini 4 Argon
1.05M Google · google/gemini-4-argon
Google's flagship tier at $2 / $10 per million — the same price as GPT-6.1 Sol and half of Claude Opus 5.5's
$2.00 in / $10.00 out per 1M · OpenRouter ↗
Muse Wonder
1.05M Meta · meta/muse-wonder
1,048,576-token window with a 943,718-token output ceiling — the largest output allowance in this hub
$4.00 in / $20.00 out per 1M · OpenRouter ↗
Muse Spark Open
1.05M Meta · meta/muse-spark-open
Open weights: meta-models/Muse-Spark-Open-816B-A42B on Hugging Face, so the checkpoint can leave Meta's API
$1.25 in / $4.25 out per 1M · OpenRouter ↗
Moondream 3.1
32K Moondream · moondream/moondream3.1-9b-a2b
A 9B vision-language model with 2B active parameters, open weights on Hugging Face
$0.300 in / $2.50 out per 1M · OpenRouter ↗
Grok 4.7
500K SpaceXAI · x-ai/grok-4.7
$2 / $6 per million, undercutting the Claude and OpenAI rows at the same input price
$2.00 in / $6.00 out per 1M · OpenRouter ↗
Gemini 3.8 Flash
1.05M Google · google/gemini-3.8-flash
The widest input set here: text, image, video, file and audio all go in at $0.75 / $3.75 per million
$0.825 in / $4.13 out per 1M · OpenRouter ↗
Nemotron 3.5 Super VL
1.05M NVIDIA · nvidia/nemotron-3.5-super-vl
Open weights (nvidia/NVIDIA-Nemotron-3.5-Super-VL): 12B active parameters out of 120B, and a 1M-token window
$0.150 in / $0.500 out per 1M · OpenRouter ↗
Google · google/gemini-nano-banana-2.1
Image generation and editing rather than chat — the catalogue lists image among its outputs
$1.50 in / $7.50 out per 1M · OpenRouter ↗
Anthropic · anthropic/claude-haiku-5.5
$0.10 in / $0.50 out per million — the cheapest row here from a frontier vendor
$0.100 in / $0.500 out per 1M · OpenRouter ↗
Mistral Large 4
1.05M Mistral · mistralai/mistral-large-4-0
1M-token window at $0.68 / $2.09 per million — the cheapest 1M row here from a European vendor
$0.680 in / $2.09 out per 1M · OpenRouter ↗
Command A+
192K Cohere · cohere/command-a-plus
$0.30 in / $1.50 out per million with a 192K window
$0.300 in / $1.50 out per 1M · OpenRouter ↗
Pareto 26.9
262K Unbiased · unbiased/pareto-26.9
The model behind Union Alpha — the fourth codename in the anonymous line, revealed on 2026-09-18 and repriced since
$2.50 in / $7.50 out per 1M · OpenRouter ↗
DeepSeek V4.1 Flash
1.05M DeepSeek · deepseek/deepseek-v4.1-flash
1,048,576-token window with a 943,718-token output ceiling at $0.0351 / $0.891 per million
$0.036 in / $0.684 out per 1M · OpenRouter ↗
GPT-6 Astra
1.05M OpenAI · openai/gpt-6-astra
OpenAI's flagship row: 1.05M-token context at $10 / $50 per million
$10.00 in / $50.00 out per 1M · OpenRouter ↗
Step 5 Preview
1.05M StepFun · stepfun/step-5-preview
Reads video as well as text and images — the second row here that does
$1.00 in / $2.70 out per 1M · OpenRouter ↗
ScaleDown · scaledown/extract
Output is billed at $0: this row charges for input only, at $0.04 per million tokens
$0.040 in / $0 out per 1M · OpenRouter ↗
ScaleDown · scaledown/summarize
Output is billed at $0: $0.04 per million input tokens and nothing per output token
$0.040 in / $0 out per 1M · OpenRouter ↗
Ling 3.1 Flash
262K inclusionAI · inclusionai/ling-3.1-flash
262,144-token window at $0.075 / $0.225 per million — cheap for the window, though no longer free
$0.075 in / $0.225 out per 1M · OpenRouter ↗
LFM2.5-24B-A2B
128K Liquid AI · liquid/lfm-2.5-24b-a2b
$0.05 in / $0.70 out per million with open weights (LiquidAI/LFM2.5-24B-A2B)
$0.050 in / $0.700 out per 1M · OpenRouter ↗
Xiaomi MiMo-V2.5
1.05M Xiaomi · xiaomi/mimo-v2.5
1.05M-token context window at a very low price
$0.140 in / $0.280 out per 1M · OpenRouter ↗
Xiaomi MiMo-V2.6-Flash
1.05M Xiaomi · xiaomi/mimo-v2.6-flash
Same price as MiMo-V2.5 on a newer generation — the catalogue lists both at $0.14 in / $0.28 out per million
$0.140 in / $0.280 out per 1M · OpenRouter ↗
Xiaomi MiMo-V2.6-Pro
1.05M Xiaomi · xiaomi/mimo-v2.6-pro
Xiaomi's flagship tier: the catalogue describes it as built at a scale of over 1T parameters
$0.435 in / $0.870 out per 1M · OpenRouter ↗
Xiaomi · xiaomi/mimo-v2.6-pro-ultraspeed
The catalogue describes it as built from the same 1T MiMo-V2.6-Pro checkpoint and matching that model's quality
$4.35 in / $8.70 out per 1M · OpenRouter ↗
Z.ai GLM 5.3 Flash
1.05M Z.ai · z-ai/glm-5.3-flash
Mid-tier pricing that undercuts the frontier models by a wide margin
$0.150 in / $0.500 out per 1M · OpenRouter ↗
DeepSeek V4 Flash
1.05M DeepSeek · deepseek/deepseek-v4-flash-0731
Still the cheapest paid input in this hub at $0.016 per million tokens, even after this read took it back up 3.5x from its floor
$0.007 in / $1.28 out per 1M · OpenRouter ↗
DeepSeek V4 Pro
1.05M DeepSeek · deepseek/deepseek-v4-pro-0813
Balanced cost/performance for long-form reasoning
$1.32 in / $3.96 out per 1M · OpenRouter ↗
Alibaba · qwen/qwen3.8-flash
Low-latency multimodal processing
$0.150 in / $0.470 out per 1M · OpenRouter ↗
Alibaba · qwen/qwen3.8-max-0902
Broad multimodal coverage
$2.00 in / $6.00 out per 1M · OpenRouter ↗
Google Gemini 3.7 Flash
1.05M Google · google/gemini-3.7-flash
Very broad multimodal input support
$0.750 in / $3.75 out per 1M · OpenRouter ↗
Anthropic · anthropic/claude-sonnet-5
Strong coding, writing and long-context reasoning
$2.00 in / $10.00 out per 1M · OpenRouter ↗
Anthropic · anthropic/claude-opus-5
Highest reasoning quality in the snapshot
$5.00 in / $25.00 out per 1M · OpenRouter ↗
OpenAI GPT-5.6 Luna
1.05M OpenAI · openai/gpt-5.6-luna
Fast, cost-efficient reasoning
$0.200 in / $1.20 out per 1M · OpenRouter ↗
OpenAI GPT-5.6 Sol
1.05M OpenAI · openai/gpt-5.6-sol
Balanced quality/cost for product work
$4.00 in / $20.00 out per 1M · OpenRouter ↗
OpenAI GPT-5.6 Terra
1.05M OpenAI · openai/gpt-5.6-terra
Strong multimodal and file reasoning
$2.00 in / $12.00 out per 1M · OpenRouter ↗
Mistral Medium 3.5
262K Mistral AI · mistralai/mistral-medium-3-5
Strong European/general-purpose option
$1.50 in / $7.50 out per 1M · OpenRouter ↗
Meta Llama 4 Maverick
1.05M Meta · meta-llama/llama-4-maverick
Low-cost open-weight family
$0.188 in / $0.652 out per 1M · OpenRouter ↗
Cohere Command A
256K Cohere · cohere/command-a
Strong enterprise search and RAG workflows
$2.50 in / $10.00 out per 1M · OpenRouter ↗
Jev (TypeSafe)
32K
TypeSafe · typesafe/jev-1.13 · hand-verified
Returns typed decisions with calibrated probabilities instead of text. Not in the API list this directory is built from, so it is read and dated by hand.
$0.042 in / free out per 1M · OpenRouter ↗