Compare Large Language Models
Compare current text-generation listings by API (Application Programming Interface) price, context limit, image input and tool calling. Source: OpenRouter's public catalog, not a benchmark leaderboard.
Source checked: . 442 validated listings. Refresh attempted every six hours when visited.
Prices are OpenRouter-listed USD per million tokens, not necessarily direct-provider rates. A $0 listing can have quotas; it does not mean unlimited free usage. Dates below mean added to this catalog, not model release dates. Context limits and supported features can vary by endpoint. We do not invent parameter counts, licenses or benchmark scores.
442 matching listings. Select up to three to compare.
| Compare | Model | Catalog added | Context tokens | Input / 1M | Output / 1M | Capabilities |
|---|---|---|---|---|---|---|
| XingChen: Xing4.0 29B A4B (free)xingchen-agi/xing4.0-29b-a4b:free | 2026-10-16 | 262,144 | $0 listed | $0 listed | Tool calling | |
| Reflection: Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | 2026-10-16 | 1,048,576 | $1 | $3 | Tool calling | |
| Moondream: Moondream 3 Previewmoondream/moondream3-preview | 2026-10-15 | 32,000 | $0.3 | $2.5 | Image input | |
| Moondream: Moondream 3.1moondream/moondream3.1-9b-a2b | 2026-10-15 | 32,000 | $0.3 | $2.5 | Image input | |
| Meta: Muse Spark Openmeta/muse-spark-open | 2026-10-15 | 1,048,576 | $1.25 | $4.25 | Tool calling, Image input | |
| NVIDIA: Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl | 2026-10-15 | 1,048,576 | $0.1 | $0.4 | Tool calling, Image input | |
| NVIDIA: Nemotron 3.5 Super VL (free)nvidia/nemotron-3.5-super-vl:free | 2026-10-15 | 1,000,000 | $0 listed | $0 listed | Tool calling, Image input | |
| Pareto 26.9unbiased/pareto-26.9 | 2026-10-13 | 262,144 | $2.5 | $7.5 | Tool calling, Image input | |
| LiquidAI: LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2b | 2026-10-13 | 128,000 | $0.05 | $0.7 | Tool calling | |
| Google: Gemini 4 Argongoogle/gemini-4-argon | 2026-10-13 | 1,048,576 | $2 | $10 | Tool calling, Image input | |
| Google: Gemini 4 Argon (batch)google/gemini-4-argon:batch | 2026-10-13 | 1,048,576 | $1 | $5 | Tool calling, Image input | |
| ScaleDown: Summarizescaledown/summarize | 2026-10-13 | 1,000,000 | $0.04 | $0 listed | Image input | |
| ScaleDown: Extractscaledown/extract | 2026-10-13 | 1,000,000 | $0.04 | $0 listed | Image input | |
| Meta: Muse Wondermeta/muse-wonder | 2026-10-12 | 1,048,576 | $4 | $20 | Tool calling, Image input | |
| StepFun: Step 5 Previewstepfun/step-5-preview | 2026-10-08 | 1,048,576 | $1 | $2.7 | Tool calling, Image input | |
| Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5 | 2026-10-07 | 1,000,000 | $0.1 | $0.5 | Tool calling, Image input | |
| Anthropic: Claude Haiku 5.5 (batch)anthropic/claude-haiku-5.5:batch | 2026-10-07 | 1,000,000 | $0.05 | $0.25 | Tool calling, Image input | |
| Google: Nano Banana 2.1google/gemini-nano-banana-2.1 | 2026-10-06 | 65,536 | $1.5 | $7.5 | Tool calling, Image input | |
| Mistral: Mistral Large 4mistralai/mistral-large-4-0 | 2026-10-06 | 1,048,576 | $0.68 | $2.09 | Tool calling, Image input | |
| inclusionAI: Ling 3.1 Flashinclusionai/ling-3.1-flash | 2026-10-02 | 262,144 | $0.075 | $0.225 | Tool calling | |
| OpenAI: GPT-6.1 Sol Proopenai/gpt-6.1-sol-pro | 2026-09-29 | 1,050,000 | $2 | $10 | Tool calling, Image input | |
| OpenAI: GPT-6.1 Sol Pro (batch)openai/gpt-6.1-sol-pro:batch | 2026-09-29 | 1,050,000 | $1 | $5 | Tool calling, Image input | |
| OpenAI: GPT-6.1 Solopenai/gpt-6.1-sol | 2026-09-29 | 1,050,000 | $2 | $10 | Tool calling, Image input | |
| OpenAI: GPT-6.1 Sol (batch)openai/gpt-6.1-sol:batch | 2026-09-29 | 1,050,000 | $1 | $5 | Tool calling, Image input | |
| Anthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.5 | 2026-09-28 | 1,000,000 | $2 | $10 | Tool calling, Image input | |
| Anthropic: Claude Sonnet 5.5 (batch)anthropic/claude-sonnet-5.5:batch | 2026-09-28 | 1,000,000 | $1 | $5 | Tool calling, Image input | |
| Perceptron: Perceptron Mk1.5perceptron/perceptron-mk1.5 | 2026-09-25 | 36,864 | $0.15 | $1.5 | Tool calling, Image input | |
| Fireworks: Ember-1fireworks/ember-1 | 2026-09-24 | 1,048,576 | $3 | $15 | Tool calling, Image input | |
| Z.ai: GLM 5.3 Primez-ai/glm-5.3-prime | 2026-09-23 | 1,000,000 | $2.8 | $8.8 | Tool calling | |
| Qwen: Qwen3.8 Max Primeqwen/qwen3.8-max-prime | 2026-09-23 | 1,000,000 | $4 | $12 | Tool calling, Image input |
Which model should I choose?
Price and context are constraints, not quality scores. Shortlist models that support your inputs and tools, then measure task accuracy, latency and total cost on the same held-out examples. Check the provider's model card and license before deployment.
You Just Compared LLMs.
Now Learn to Actually Use the Best One.
2 hours. Live coding. Zero slides. You'll build a real project with Claude Code and leave with a deployable app in your portfolio.
Taught by Debasish Maji - Senior AI Engineer · Built AI agents at Atlassian (Rovo) · Ex-PhonePe (550M+ users)