Model Comparison
Put a workload next to a price. See the assumptions, compare the costs and keep a copy of the numbers.
Model data. Verified-price snapshots from . Details
35 of 39 tracked models have verified token rates in the saved catalogue. Rates come from the OpenRouter public API. Models missing from that catalogue have unknown pricing and are excluded from cost estimates and chat selection.
Rates are USD per million text tokens. Caching, reasoning tokens, images, tool charges, provider routing and long-context tiers can change the bill. Check the provider before budgeting.
Context limits have their own dated review. The Context Budget Planner shows the catalogue and top-provider quotes separately, using the smaller known limit. Output caps are a separate constraint. Weight links identify repository revisions whose file lists were checked. Licence labels come from the model cards and are not an open-source certification. Check the actual terms and access conditions. Published weights do not make a hosted API or self-hosting free.
01 / SET A WORKLOAD
What would your calls cost?
Every call uses the same counts. Include the system prompt, tools and any repeated conversation history in the input. For a growing conversation, use the turn-by-turn calculator.
02 / COMPARE THE SNAPSHOTS
A price is a starting point.
These are recorded OpenRouter text-token rates, in USD. Try the models on your own examples before choosing one. Cost does not measure answer quality.
39 of 39 models shown. 35 have an estimate for this workload.
Scroll the table sideways on smaller screens. Select a column heading to sort.
| Price snapshot | |||||
|---|---|---|---|---|---|
GPT-5 NanoOpenAIopenai/gpt-5-nano | 400,000Reply cap: 128,000 | $0.05 | $0.4 | $0.25 | Rates checkedSource ↗ |
Llama 4 ScoutMetameta-llama/llama-4-scoutWeight files · gated access ↗llama4 · checked 2026-09-13 | 327,680Reply cap: 16,384 | $0.1 | $0.3 | $0.25 | Rates checkedSource ↗ |
Nemotron 3 SuperNvidianvidia/nemotron-3-super-120b-a12bPublished weight files ↗nvidia-nemotron-open-model-license · checked 2026-09-13 | 262,144Reply cap: 16,384 | $0.08 | $0.45 | $0.305 | Rates checkedSource ↗ |
Mistral Small 4Mistralmistralai/mistral-small-2603Published weight files ↗apache-2.0 · checked 2026-09-13 | 262,144Reply cap: 209,715 | $0.15 | $0.6 | $0.45 | Rates checkedSource ↗ |
Llama 4 MaverickMetameta-llama/llama-4-maverickWeight files · gated access ↗llama4 · checked 2026-09-13 | 128,000Reply cap: 115,200 | $0.1875 | $0.6525 | $0.51375 | Rates checkedSource ↗ |
Qwen 2.5 72BAlibabaqwen/qwen-2.5-72b-instructPublished weight files ↗qwen · checked 2026-09-13 | 32,768Reply cap: 16,384 | $0.36 | $0.4 | $0.56 | Rates checkedSource ↗ |
Mistral Small 3.1Mistralmistralai/mistral-small-3.1-24b-instructPublished weight files ↗apache-2.0 · checked 2026-09-13 | 128,000Reply cap: 102,400 | $0.351 | $0.555 | $0.6285 | Rates checkedSource ↗ |
Qwen3.6 35B A3BAlibabaqwen/qwen3.6-35b-a3bPublished weight files ↗apache-2.0 · checked 2026-09-13 | 262,144Reply cap: 235,929 | $0.15 | $1 | $0.65 | Rates checkedSource ↗ |
Trinity Large ThinkingArcee-Aiarcee-ai/trinity-large-thinkingPublished weight files ↗openmdw-1.1 · checked 2026-09-13 | 262,144Reply cap: 80,000 | $0.25 | $0.8 | $0.65 | Rates checkedSource ↗ |
DeepSeek V3DeepSeekdeepseek/deepseek-chat-v3-0324Published weight files ↗mit · checked 2026-09-13 | 163,840Reply cap: 147,456 | $0.25 | $1 | $0.75 | Rates checkedSource ↗ |
MiniMax M2Minimaxminimax/minimax-m2Published weight files ↗modified-mit · checked 2026-09-13 | 204,800Reply cap: 131,072 | $0.255 | $1.02 | $0.765 | Rates checkedSource ↗ |
MiniMax M2.7Minimaxminimax/minimax-m2.7Published weight files ↗Custom licence, see model card · checked 2026-09-13 | 204,800Reply cap: 131,072 | $0.3 | $1.2 | $0.90 | Rates checkedSource ↗ |
GPT-5 MiniOpenAIopenai/gpt-5-mini | 400,000Reply cap: 128,000 | $0.25 | $2 | $1.25 | Rates checkedSource ↗ |
Qwen3.6 27BAlibabaqwen/qwen3.6-27bPublished weight files ↗apache-2.0 · checked 2026-09-13 | 262,144Reply cap: 65,536 | $0.3 | $2 | $1.30 | Rates checkedSource ↗ |
Gemini 2.5 FlashGooglegoogle/gemini-2.5-flash | 1,048,576Reply cap: 65,535 | $0.3 | $2.5 | $1.55 | Rates checkedSource ↗ |
GLM-5Z.aiz-ai/glm-5Published weight files ↗mit · checked 2026-09-13 | 198,000Reply cap: 128,000 | $0.6 | $1.92 | $1.56 | Rates checkedSource ↗ |
Kimi k2Moonshot AImoonshotai/kimi-k2Published weight files ↗modified-mit · checked 2026-09-13 | 131,072Reply cap: 100,352 | $0.57 | $2.3 | $1.72 | Rates checkedSource ↗ |
DeepSeek R1DeepSeekdeepseek/deepseek-r1Published weight files ↗mit · checked 2026-09-13 | 64,000Reply cap: 16,000 | $0.7 | $2.5 | $1.95 | Rates checkedSource ↗ |
GLM 5.1Z.aiz-ai/glm-5.1Published weight files ↗mit · checked 2026-09-13 | 200,000Reply cap: 128,000 | $0.966 | $3.036 | $2.484 | Rates checkedSource ↗ |
Grok 4.3xAIx-ai/grok-4.3 | 1,000,000Reply cap: 900,000 | $1.25 | $2.5 | $2.50 | Rates checkedSource ↗ |
Kimi K2.6Moonshot AImoonshotai/kimi-k2.6Published weight files ↗modified-mit · checked 2026-09-13 | 262,144Reply cap: 235,929 | $0.95 | $4 | $2.95 | Rates checkedSource ↗ |
o3-miniOpenAIopenai/o3-mini | 200,000Reply cap: 100,000 | $1.1 | $4.4 | $3.30 | Rates checkedSource ↗ |
Claude Haiku 4.5Anthropicanthropic/claude-haiku-4.5 | 200,000Reply cap: 64,000 | $1 | $5 | $3.50 | Rates checkedSource ↗ |
Gemini 3.5 FlashGooglegoogle/gemini-3.5-flash | 1,048,576Reply cap: 65,536 | $1.5 | $9 | $6.00 | Rates checkedSource ↗ |
GPT-4.1OpenAIopenai/gpt-4.1 | 1,047,576Reply cap: 32,768 | $2 | $8 | $6.00 | Rates checkedSource ↗ |
o3OpenAIopenai/o3 | 200,000Reply cap: 100,000 | $2 | $8 | $6.00 | Rates checkedSource ↗ |
Gemini 2.5 ProGooglegoogle/gemini-2.5-pro-preview | 1,048,576Reply cap: 65,536 | $1.25 | $10 | $6.25 | Rates checkedSource ↗ |
GPT-5OpenAIopenai/gpt-5 | 400,000Reply cap: 128,000 | $1.25 | $10 | $6.25 | Rates checkedSource ↗ |
GPT-4oOpenAIopenai/gpt-4o | 128,000Reply cap: 16,384 | $2.5 | $10 | $7.50 | Rates checkedSource ↗ |
GPT-5.4OpenAIopenai/gpt-5.4 | 1,050,000Reply cap: 128,000 | $2.5 | $15 | $10.00 | Rates checkedSource ↗ |
Claude Sonnet 4Anthropicanthropic/claude-sonnet-4 | 200,000Reply cap: 64,000 | $3 | $15 | $10.50 | Rates checkedSource ↗ |
Claude Opus 4.7Anthropicanthropic/claude-opus-4.7 | 1,000,000Reply cap: 128,000 | $5 | $25 | $17.50 | Rates checkedSource ↗ |
GPT-5.5OpenAIopenai/gpt-5.5 | 1,050,000Reply cap: 128,000 | $5 | $30 | $20.00 | Rates checkedSource ↗ |
Claude Fable 5Anthropicanthropic/claude-fable-5 | 1,000,000Reply cap: 128,000 | $10 | $50 | $35.00 | Rates checkedSource ↗ |
GPT-5.5 ProOpenAIopenai/gpt-5.5-pro | 1,050,000Reply cap: 128,000 | $30 | $180 | $120.00 | Rates checkedSource ↗ |
Claude Opus 4Anthropicanthropic/claude-opus-4 | 200,000Reply cap: 32,000 | Not listed | Not listed | Price unknown | not listedSource ↗ |
Gemini 2.0 FlashGooglegoogle/gemini-2.0-flash-001 | UnknownReply cap: Unknown | Not listed | Not listed | Price unknown | not listedSource ↗ |
Laguna XS.2Poolsidepoolside/laguna-xs.2Published weight files ↗apache-2.0 · checked 2026-09-13 | UnknownReply cap: Unknown | Not listed | Not listed | Price unknown | not listedSource ↗ |
Mistral Large 3Mistralmistralai/mistral-large-2512Published weight files ↗apache-2.0 · checked 2026-09-13 | 262,144Reply cap: 209,715 | Not listed | Not listed | Price unknown | not listedSource ↗ |
Input plus output must fit the smaller recorded context limit, and a known output cap is checked separately. These are dated catalogue quotes, not a promise that every provider route accepts the request. Inspect both source values in the Context Budget Planner. Weight links point to recorded repository revisions with published files. Licences vary, and gated files may require approval from their host. A missing weight record does not establish that a model is closed.
Caching, reasoning tokens, images, tools, routing and long-context pricing can change the bill. Unknown rates stay unknown, including for zero calls. Open weights do not make hosted calls or hardware free.