tokenstat
tokenstat

Model catalog

Models and list rates

Published API list rates (USD per million tokens), who lists each model, and whether it can do tools, vision, or reasoning. Recommended order is newer first; among similarly new models, larger context wins. Free/$0 rows stay hidden unless you ask. Not a bill: measure real sessions with the CLI.

3,231 models in the merged catalog · as of . Sources: LiteLLM, OpenRouter, models.dev. · Providers · Plans · Benchmarks

Showing 48 of 3,231 matches · page 45 of 68 · including free/$0 list rates

ModelInputOutputContextOffers
Llama 4 Scout 17Bnovita/meta-llama/llama-4-scout-17b-16e-instruct
scores
$0.18LiteLLM$0.59N/A1
Llama 4 Scout 17Bnscale/meta-llama/Llama-4-Scout-17B-16E-Instruct
scores
$0.09LiteLLM$0.29N/A1
Llama 4 Scout 17Boci/meta.llama-4-scout-17b-16e-instruct
scores
$0.72LiteLLM$0.72N/A1
Llama 4 Scout 17Bsambanova/Llama-4-Scout-17B-16E-Instruct
scores
$0.4LiteLLM$0.7N/A1
Llama 4 Scout 17Bwandb/meta-llama/Llama-4-Scout-17B-16E-Instruct
scores
$17000LiteLLM$66000N/A1
Llama4 Mavericksnowflake/llama4-maverick
$0.24LiteLLM$0.97N/A2
Llama4 Maverick Instruct Basicaccounts/fireworks/models/llama4-maverick-instruct-basic
$0.22LiteLLM$0.88N/A3
Llama4 Scout Instruct Basicaccounts/fireworks/models/llama4-scout-instruct-basic
$0.15LiteLLM$0.6N/A3
Codestral Embed 2505mistralai/codestral-embed-2505
$0.15OpenRouter$08K1
Qwen3 235B A22B Fp8 TputQwen/Qwen3-235B-A22B-fp8-tput
$0.2LiteLLM$0.6N/A3
Qwen3 4BQwen/Qwen3-4B
$0.08LiteLLM$0.24N/A6
Qwen3 ASR Flashqwen/qwen3-asr-flash-2026-02-10
$35OpenRouter$0N/A1
Qwen3 Coder 480b A35b Instruct Maasqwen/qwen3-coder-480b-a35b-instruct-maas
$1LiteLLM$4N/A3
Qwen3 Next 80b A3b Instruct Maasqwen/qwen3-next-80b-a3b-instruct-maas
$0.15LiteLLM$1.20N/A3
Qwen3 Next 80b A3b Thinking Maasqwen/qwen3-next-80b-a3b-thinking-maas
$0.15LiteLLM$1.20N/A3
Qwen3 32Bfireworks_ai/accounts/fireworks/models/qwen3-32b
scores
$0.9LiteLLM$0.9N/A1
Qwen3 Coder 30B A3B Instructfireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct
$0.15LiteLLM$0.6N/A1
Qwen3 Next 80B A3B Instructfireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct
$0.9LiteLLM$0.9N/A1
Qwen3 Next 80B A3B Instructtogether_ai/Qwen/Qwen3-Next-80B-A3B-Instruct
$0.15LiteLLM$1.50N/A1
Qwen3 Next 80B A3B Thinkingfireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking
scores
$0.9LiteLLM$0.9N/A1
Qwen3 Next 80B A3B Thinkingtogether_ai/Qwen/Qwen3-Next-80B-A3B-Thinking
scores
$0.15LiteLLM$1.50N/A1
Qwen3 VL 235B A22B Instructfireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct
$0.22LiteLLM$0.88N/A1
Qwen3.5 397B A17Btogether_ai/Qwen/Qwen3.5-397B-A17B
scores
$0.6LiteLLM$3.60N/A1
Qwen3 0p6baccounts/fireworks/models/qwen3-0p6b
$0.1LiteLLM$0.1N/A3
Qwen3 1p7baccounts/fireworks/models/qwen3-1p7b
$0.1LiteLLM$0.1N/A3
Qwen3 1p7b Fp8 Draftaccounts/fireworks/models/qwen3-1p7b-fp8-draft
$0.1LiteLLM$0.1N/A3
Qwen3 1p7b Fp8 Draft 131072accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072
$0.1LiteLLM$0.1N/A3
Qwen3 1p7b Fp8 Draft 40960accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960
$0.1LiteLLM$0.1N/A3
Qwen3 235b A22b 2507 V1:0qwen3-235b-a22b-2507-v1:0
$0.22LiteLLM$0.88N/A1
Qwen3 32Baccounts/fireworks/models/qwen3-32b
scores
$0.9LiteLLM$0.9N/A1
Qwen3 32Bsambanova/Qwen3-32B
scores
$0.4LiteLLM$0.8N/A1
Qwen3 32b V1:0qwen3-32b-v1:0
$0.15LiteLLM$0.6N/A1
Qwen3 Coder 30B A3B Instructaccounts/fireworks/models/qwen3-coder-30b-a3b-instruct
$0.15LiteLLM$0.6N/A1
Qwen3 Coder 30B A3B Instructnovita/qwen/qwen3-coder-30b-a3b-instruct
$0.07LiteLLM$0.27N/A1
Qwen3 Coder 30B A3B Instructscaleway/qwen/qwen3-coder-30b-a3b-instruct
$0.2LiteLLM$0.8N/A1
Qwen3 Coder 30b A3b V1:0qwen3-coder-30b-a3b-v1:0
$0.15LiteLLM$0.6N/A1
Qwen3 Coder 480B A35Bvercel_ai_gateway/alibaba/qwen3-coder
$0.4LiteLLM$1.60N/A1
Qwen3 Coder 480b A35b V1:0qwen3-coder-480b-a35b-v1:0
$0.22LiteLLM$1.80N/A1
Qwen3 Coder 480b Instruct Bf16accounts/fireworks/models/qwen3-coder-480b-instruct-bf16
$0.9LiteLLM$0.9N/A3
Qwen3 Coder:480b Cloudollama/qwen3-coder:480b-cloud
$0LiteLLM$0N/A2
Qwen3 Embedding 0p6baccounts/fireworks/models/qwen3-embedding-0p6b
$0LiteLLM$0N/A3
Qwen3 Next 80b A3bqwen3-next-80b-a3b
$0.15LiteLLM$1.20N/A1
Qwen3 Next 80B A3B Instructaccounts/fireworks/models/qwen3-next-80b-a3b-instruct
$0.9LiteLLM$0.9N/A1
Qwen3 Next 80B A3B Instructdashscope/qwen3-next-80b-a3b-instruct
$0.15LiteLLM$1.20N/A1
Qwen3 Next 80B A3B Instructnovita/qwen/qwen3-next-80b-a3b-instruct
$0.15LiteLLM$1.50N/A1
Qwen3 Next 80B A3B Thinkingaccounts/fireworks/models/qwen3-next-80b-a3b-thinking
scores
$0.9LiteLLM$0.9N/A1
Qwen3 Next 80B A3B Thinkingdashscope/qwen3-next-80b-a3b-thinking
scores
$0.15LiteLLM$1.20N/A1
Qwen3 Next 80B A3B Thinkingdeepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking
scores
$0.14LiteLLM$1.40N/A1

Price this against your own usage

List rates are only half the story. The CLI reads the session logs your coding harnesses already write and shows tokens, cache share, and usage value on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash